diff --git "a/checkpoint-2442240/trainer_state.json" "b/checkpoint-2442240/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2442240/trainer_state.json" @@ -0,0 +1,28901 @@ +{ + "best_metric": 3.8435444831848145, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/transformer/0/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2442240, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0151, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8282, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1915, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9799, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8143, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7046, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6062, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5397, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4571, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4013, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3502, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3109, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2632, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2113, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.1805, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1309, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1241, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0792, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0461, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0263, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0135, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9822, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9566, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9371, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9218, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8922, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8754, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8546, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8375, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8217, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8077, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7973, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7901, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7719, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7577, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7452, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7374, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7117, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.711, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6792, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6816, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6747, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6752, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6439, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6497, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6378, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.627, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6328, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5953, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5983, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6034, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5958, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5771, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5579, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5662, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5471, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5715, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5225, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5414, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5312, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5223, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5258, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.506, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4908, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4933, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5072, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4777, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4792, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4632, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4632, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.479, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4765, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4503, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4618, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4683, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4532, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4324, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4377, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4333, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4256, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4223, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4212, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4233, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4156, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3953, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3987, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4002, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3963, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.394, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3829, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3803, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3712, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.9228804026303046e-05, + "loss": 4.3827, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.3731, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.3736, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3721, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3563, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3602, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3535, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3519, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3562, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3373, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3435, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3424, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3356, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.326, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3262, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3292, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3213, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3209, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3137, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.306, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3248, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3046, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3103, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3086, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3084, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.3002, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2947, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.3083, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2965, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.284, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2857, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2817, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.281, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2745, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.279, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2668, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2686, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2638, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2822, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2745, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2591, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2605, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2603, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2651, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.262, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2549, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2565, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2531, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2487, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2411, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2485, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2396, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2279, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2444, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2365, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2419, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2289, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2292, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.196406364440918, + "eval_runtime": 307.1617, + "eval_samples_per_second": 1242.313, + "eval_steps_per_second": 38.823, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2194, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2166, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2304, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2154, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2235, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.208, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.216, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.2032, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.2097, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2052, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.214, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2099, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1929, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1917, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1884, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1866, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1889, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.183, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.183, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1996, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1848, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1844, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1786, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.191, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1621, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1781, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1668, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1661, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1632, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1571, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849111908504072e-05, + "loss": 4.1635, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.84827331375302e-05, + "loss": 4.1748, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847434719001968e-05, + "loss": 4.1599, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1622, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1534, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.159, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.149, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1552, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.137, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1465, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407292367542976e-05, + "loss": 4.1427, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1574, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1308, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1421, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.1417, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1322, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1445, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.1185, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1267, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833186797635949e-05, + "loss": 4.1391, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832348202884897e-05, + "loss": 4.1314, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.123, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1186, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829834056512114e-05, + "loss": 4.1222, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289954617610625e-05, + "loss": 4.1119, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1302, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.105, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264813153882794e-05, + "loss": 4.117, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256427206372274e-05, + "loss": 4.1177, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248041258861754e-05, + "loss": 4.111, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1191, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823128574264444e-05, + "loss": 4.1109, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822289979513392e-05, + "loss": 4.0973, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.82145138476234e-05, + "loss": 4.0967, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1218, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819775833140609e-05, + "loss": 4.0991, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818937238389558e-05, + "loss": 4.1, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818098643638506e-05, + "loss": 4.0921, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.0957, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816423092016775e-05, + "loss": 4.1082, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815584497265723e-05, + "loss": 4.1111, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814745902514671e-05, + "loss": 4.0977, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.106, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81307035089294e-05, + "loss": 4.1112, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812231756141888e-05, + "loss": 4.1066, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.0856, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.0979, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097176097691046e-05, + "loss": 4.092, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808879015018053e-05, + "loss": 4.0919, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808040420267001e-05, + "loss": 4.0876, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0915, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.80636486864527e-05, + "loss": 4.0988, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805527911774591e-05, + "loss": 4.0923, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804689317023539e-05, + "loss": 4.0735, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803850722272487e-05, + "loss": 4.0777, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803012127521435e-05, + "loss": 4.0832, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802173532770383e-05, + "loss": 4.0853, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801334938019331e-05, + "loss": 4.0843, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800496343268279e-05, + "loss": 4.0722, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996593863976e-05, + "loss": 4.082, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988207916465486e-05, + "loss": 4.0623, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979821968954966e-05, + "loss": 4.0784, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971436021444446e-05, + "loss": 4.0778, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963066452737655e-05, + "loss": 4.0744, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954696884030864e-05, + "loss": 4.0813, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946310936520344e-05, + "loss": 4.0668, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937924989009824e-05, + "loss": 4.068, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929539041499304e-05, + "loss": 4.071, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921153093988784e-05, + "loss": 4.0713, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912767146478264e-05, + "loss": 4.0682, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0626, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789601163026095e-05, + "loss": 4.0612, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788762568275043e-05, + "loss": 4.0688, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787925611404365e-05, + "loss": 4.0678, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787087016653313e-05, + "loss": 4.0473, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.0595, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0659, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.0578, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783734275529478e-05, + "loss": 4.0527, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782895680778426e-05, + "loss": 4.0527, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782057086027374e-05, + "loss": 4.045, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781218491276322e-05, + "loss": 4.0681, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.78037989652527e-05, + "loss": 4.0491, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.0554, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0529, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0629, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777028793281808e-05, + "loss": 4.0491, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776190198530756e-05, + "loss": 4.0528, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775351603779704e-05, + "loss": 4.0592, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774513009028652e-05, + "loss": 4.0503, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736744142776e-05, + "loss": 4.0429, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772835819526548e-05, + "loss": 4.0441, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719972247754956e-05, + "loss": 4.0386, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771160267904817e-05, + "loss": 4.0421, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770321673153765e-05, + "loss": 4.0409, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769483078402713e-05, + "loss": 4.0414, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768644483651661e-05, + "loss": 4.0344, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767805888900609e-05, + "loss": 4.0365, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766967294149557e-05, + "loss": 4.0331, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766130337278878e-05, + "loss": 4.0503, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765291742527826e-05, + "loss": 4.0501, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764453147776774e-05, + "loss": 4.0376, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763614553025722e-05, + "loss": 4.0271, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.76277595827467e-05, + "loss": 4.0402, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761937363523618e-05, + "loss": 4.0398, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761098768772566e-05, + "loss": 4.0406, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760260174021514e-05, + "loss": 4.0347, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759424855031208e-05, + "loss": 4.0393, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585862602801565e-05, + "loss": 4.0324, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577476655291045e-05, + "loss": 4.0345, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569090707780525e-05, + "loss": 4.0296, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560704760270005e-05, + "loss": 4.0319, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552318812759485e-05, + "loss": 4.0257, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.0191, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0346, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527177349031654e-05, + "loss": 4.0275, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518791401521134e-05, + "loss": 4.0317, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510405454010614e-05, + "loss": 4.0216, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502019506500094e-05, + "loss": 4.0231, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026560306549072, + "eval_runtime": 307.2428, + "eval_samples_per_second": 1241.985, + "eval_steps_per_second": 38.813, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493633558989574e-05, + "loss": 4.0154, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485247611479054e-05, + "loss": 4.0137, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476861663968534e-05, + "loss": 4.0273, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468475716458014e-05, + "loss": 4.0172, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460089768947494e-05, + "loss": 4.0273, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451703821436974e-05, + "loss": 4.0092, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443317873926453e-05, + "loss": 4.0198, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434931926415933e-05, + "loss": 4.0071, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742656235770914e-05, + "loss": 4.0183, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.012, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.74097904626881e-05, + "loss": 4.0205, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740140451517758e-05, + "loss": 4.0158, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0013, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.007, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0019, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 4.0026, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0028, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 3.9984, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734271926140768e-05, + "loss": 4.0, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733434969270089e-05, + "loss": 4.02, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732596374519037e-05, + "loss": 4.0052, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731757779767985e-05, + "loss": 4.0036, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730919185016933e-05, + "loss": 4.0017, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0088, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292436333952016e-05, + "loss": 3.9851, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284050386441496e-05, + "loss": 4.0005, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275664438930976e-05, + "loss": 3.9973, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 3.991, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.986, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9848, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724213702769263e-05, + "loss": 3.9931, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723375108018211e-05, + "loss": 4.0048, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 3.9935, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9935, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9879, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 3.9894, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9823, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9953, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.9707, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9845, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715831031019489e-05, + "loss": 3.9789, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9941, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9747, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9798, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.984, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9761, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.9842, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.965, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9715, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.9838, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9725, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9693, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9651, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9728, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.9576, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9744, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.9552, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701579833892724e-05, + "loss": 3.9689, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700742877022045e-05, + "loss": 3.9733, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699904282270993e-05, + "loss": 3.9605, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699065687519941e-05, + "loss": 3.9675, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698227092768889e-05, + "loss": 3.9694, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9492, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696551541147158e-05, + "loss": 3.9551, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695712946396106e-05, + "loss": 3.9676, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694874351645054e-05, + "loss": 3.9602, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694035756894003e-05, + "loss": 3.957, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693198800023324e-05, + "loss": 3.9462, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692360205272272e-05, + "loss": 3.9501, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.69152161052122e-05, + "loss": 3.9675, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906830157701677e-05, + "loss": 3.9677, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9534, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.967, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881688693973846e-05, + "loss": 3.9717, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873302746463326e-05, + "loss": 3.9718, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9429, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9624, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9544, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9505, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9549, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9554, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681463387149715e-05, + "loss": 3.959, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680624792398663e-05, + "loss": 3.961, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9374, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9456, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.948, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677272051274828e-05, + "loss": 3.9517, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9541, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.939, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9522, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.9324, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9476, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9458, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9449, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9521, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697279742761064e-05, + "loss": 3.946, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688893795250544e-05, + "loss": 3.9368, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9474, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9448, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666375233152271e-05, + "loss": 3.9431, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.9345, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9379, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9424, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9441, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662183897277385e-05, + "loss": 3.9209, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9345, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.9449, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9355, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9297, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9328, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9265, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9452, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9272, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654638182398289e-05, + "loss": 3.9368, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9376, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9404, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9315, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9368, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9401, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9332, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.922, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9263, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9222, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462571485288884e-05, + "loss": 3.929, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9235, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445799590267844e-05, + "loss": 3.9287, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9176, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642904407405054e-05, + "loss": 3.9199, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9184, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.937, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640388623151898e-05, + "loss": 3.9365, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639551666281219e-05, + "loss": 3.9285, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.9141, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9269, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9302, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636198925157384e-05, + "loss": 3.9266, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635360330406332e-05, + "loss": 3.9218, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.9286, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.9224, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328461840335494e-05, + "loss": 3.9283, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320075892824974e-05, + "loss": 3.9147, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311689945314454e-05, + "loss": 3.9247, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.915, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.907, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9241, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9227, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9193, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9166, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9118, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9520654678344727, + "eval_runtime": 302.4622, + "eval_samples_per_second": 1261.615, + "eval_steps_per_second": 39.426, + "step": 228960 + }, + { + "epoch": 0.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9135, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9081, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622784684901298e-05, + "loss": 3.9207, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9083, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.9281, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.9004, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9174, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.9012, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617754754275359e-05, + "loss": 3.916, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616916159524307e-05, + "loss": 3.9102, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.9076, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9166, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.8959, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9045, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9004, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.9011, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.6110492720276896e-05, + "loss": 3.9022, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.6102106772766376e-05, + "loss": 3.8991, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093720825255856e-05, + "loss": 3.8985, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085334877745336e-05, + "loss": 3.9197, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.6076965309038545e-05, + "loss": 3.9037, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068579361528025e-05, + "loss": 3.9053, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6060193414017505e-05, + "loss": 3.9047, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051807466506985e-05, + "loss": 3.9069, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043437897800194e-05, + "loss": 3.8877, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6035051950289674e-05, + "loss": 3.9098, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026666002779154e-05, + "loss": 3.8936, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018280055268634e-05, + "loss": 3.894, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8855, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600152453905133e-05, + "loss": 3.8943, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599313859154081e-05, + "loss": 3.8946, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598475264403029e-05, + "loss": 3.9092, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.59763830753235e-05, + "loss": 3.901, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596799712781298e-05, + "loss": 3.8959, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595961118030246e-05, + "loss": 3.8881, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595122523279194e-05, + "loss": 3.8977, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594283928528142e-05, + "loss": 3.8845, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593446971657463e-05, + "loss": 3.902, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592608376906411e-05, + "loss": 3.8762, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591769782155359e-05, + "loss": 3.8878, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590931187404307e-05, + "loss": 3.8873, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590094230533628e-05, + "loss": 3.9013, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589255635782576e-05, + "loss": 3.8845, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588417041031524e-05, + "loss": 3.8863, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587578446280472e-05, + "loss": 3.8902, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586741489409793e-05, + "loss": 3.8868, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585902894658741e-05, + "loss": 3.8919, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585064299907689e-05, + "loss": 3.8773, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584225705156637e-05, + "loss": 3.8737, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583388748285958e-05, + "loss": 3.8914, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.8808, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581711558783854e-05, + "loss": 3.8794, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580872964032802e-05, + "loss": 3.8765, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580036007162124e-05, + "loss": 3.8807, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579197412411072e-05, + "loss": 3.8659, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.8854, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.8655, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.5766832660382886e-05, + "loss": 3.882, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758446712872366e-05, + "loss": 3.8781, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.5750060765361846e-05, + "loss": 3.8808, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741674817851326e-05, + "loss": 3.8724, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733305249144535e-05, + "loss": 3.8828, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724919301634015e-05, + "loss": 3.8602, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.5716533354123495e-05, + "loss": 3.8707, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.8792, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569977783790619e-05, + "loss": 3.8757, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.569139189039567e-05, + "loss": 3.866, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568300594288515e-05, + "loss": 3.866, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567461999537463e-05, + "loss": 3.8647, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566625042666784e-05, + "loss": 3.8754, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565786447915732e-05, + "loss": 3.8821, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.56494785316468e-05, + "loss": 3.8702, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564109258413628e-05, + "loss": 3.8829, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563272301542949e-05, + "loss": 3.8851, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562433706791897e-05, + "loss": 3.8899, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561595112040845e-05, + "loss": 3.856, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560756517289793e-05, + "loss": 3.8733, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.5599195604191144e-05, + "loss": 3.8761, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.5590809656680624e-05, + "loss": 3.8622, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582423709170104e-05, + "loss": 3.8716, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.5574037761659584e-05, + "loss": 3.8754, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556566819295279e-05, + "loss": 3.8768, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555728224544227e-05, + "loss": 3.8689, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554889629793175e-05, + "loss": 3.8593, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554051035042123e-05, + "loss": 3.8588, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553214078171444e-05, + "loss": 3.8636, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552375483420392e-05, + "loss": 3.8712, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.55153688866934e-05, + "loss": 3.8725, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550698293918288e-05, + "loss": 3.8556, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.54986133704761e-05, + "loss": 3.8677, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549022742296558e-05, + "loss": 3.8528, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548184147545506e-05, + "loss": 3.861, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547345552794454e-05, + "loss": 3.8664, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546508595923775e-05, + "loss": 3.8607, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545670001172723e-05, + "loss": 3.8745, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544831406421671e-05, + "loss": 3.8642, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543992811670619e-05, + "loss": 3.8578, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431558547999396e-05, + "loss": 3.8667, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423172600488876e-05, + "loss": 3.8649, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.5414786652978356e-05, + "loss": 3.8657, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406400705467836e-05, + "loss": 3.8523, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539803113676105e-05, + "loss": 3.8586, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538964518925053e-05, + "loss": 3.8633, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538125924174001e-05, + "loss": 3.8678, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537287329422949e-05, + "loss": 3.8462, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.53645037255227e-05, + "loss": 3.8505, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535611777801218e-05, + "loss": 3.8662, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534773183050166e-05, + "loss": 3.8594, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533934588299114e-05, + "loss": 3.8501, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533097631428435e-05, + "loss": 3.8509, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532259036677383e-05, + "loss": 3.8546, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531420441926331e-05, + "loss": 3.8612, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530581847175279e-05, + "loss": 3.8525, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297448903046005e-05, + "loss": 3.8546, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5289062955535485e-05, + "loss": 3.8618, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280677008024965e-05, + "loss": 3.864, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.5272291060514445e-05, + "loss": 3.8623, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263921491807654e-05, + "loss": 3.8534, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255535544297134e-05, + "loss": 3.8674, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247149596786614e-05, + "loss": 3.857, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523876364927609e-05, + "loss": 3.8436, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.52303940805693e-05, + "loss": 3.8517, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522200813305878e-05, + "loss": 3.8475, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521362218554826e-05, + "loss": 3.8522, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520523623803774e-05, + "loss": 3.8451, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.8555, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518848072182044e-05, + "loss": 3.8434, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.518009477430992e-05, + "loss": 3.8443, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517170882679939e-05, + "loss": 3.8441, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8625, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515495331058209e-05, + "loss": 3.8551, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514656736307156e-05, + "loss": 3.8551, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513818141556104e-05, + "loss": 3.8395, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512981184685426e-05, + "loss": 3.8555, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512142589934374e-05, + "loss": 3.8583, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511303995183322e-05, + "loss": 3.8492, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.5104654004322697e-05, + "loss": 3.8474, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509628443561591e-05, + "loss": 3.8555, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508789848810539e-05, + "loss": 3.8486, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.5079512540594866e-05, + "loss": 3.8565, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.5071126593084346e-05, + "loss": 3.8396, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506275702437756e-05, + "loss": 3.8532, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054371076867035e-05, + "loss": 3.8418, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.5045985129356515e-05, + "loss": 3.8393, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.5037599181845995e-05, + "loss": 3.8485, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502922961313921e-05, + "loss": 3.8532, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.5020843665628684e-05, + "loss": 3.8467, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501245771811817e-05, + "loss": 3.8399, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500407177060765e-05, + "loss": 3.8436, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9110300540924072, + "eval_runtime": 305.4762, + "eval_samples_per_second": 1249.168, + "eval_steps_per_second": 39.037, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499568582309713e-05, + "loss": 3.8389, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498729987558661e-05, + "loss": 3.8387, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497891392807609e-05, + "loss": 3.8463, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497052798056557e-05, + "loss": 3.8398, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496214203305505e-05, + "loss": 3.8554, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495375608554453e-05, + "loss": 3.8353, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494537013803401e-05, + "loss": 3.8439, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493698419052349e-05, + "loss": 3.8311, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.49286146218167e-05, + "loss": 3.8424, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492024505310991e-05, + "loss": 3.8435, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491185910559939e-05, + "loss": 3.8392, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490347315808887e-05, + "loss": 3.8427, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895087210578355e-05, + "loss": 3.8295, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886701263067835e-05, + "loss": 3.8353, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878315315557315e-05, + "loss": 3.8329, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869929368046795e-05, + "loss": 3.83, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861543420536275e-05, + "loss": 3.834, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853173851829484e-05, + "loss": 3.8305, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844787904318964e-05, + "loss": 3.8312, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836401956808444e-05, + "loss": 3.8465, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4828016009297924e-05, + "loss": 3.8404, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481964644059113e-05, + "loss": 3.8354, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481126049308061e-05, + "loss": 3.8374, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480287454557009e-05, + "loss": 3.8382, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479448859805957e-05, + "loss": 3.8199, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478611902935279e-05, + "loss": 3.8403, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477773308184227e-05, + "loss": 3.8281, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476934713433175e-05, + "loss": 3.825, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476096118682122e-05, + "loss": 3.8188, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475259161811444e-05, + "loss": 3.8279, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474420567060392e-05, + "loss": 3.8275, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735836101897126e-05, + "loss": 3.8424, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727450154386606e-05, + "loss": 3.834, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719064206876086e-05, + "loss": 3.8281, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710678259365566e-05, + "loss": 3.8215, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702292311855046e-05, + "loss": 3.8312, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693906364344526e-05, + "loss": 3.8253, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685520416834006e-05, + "loss": 3.8322, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677134469323486e-05, + "loss": 3.811, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668764900616695e-05, + "loss": 3.8199, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466039533190991e-05, + "loss": 3.8216, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465200938439939e-05, + "loss": 3.8365, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464362343688887e-05, + "loss": 3.8241, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635237489378344e-05, + "loss": 3.8211, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626851541867824e-05, + "loss": 3.824, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618465594357304e-05, + "loss": 3.8201, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610079646846784e-05, + "loss": 3.8269, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601693699336264e-05, + "loss": 3.8136, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459332413062948e-05, + "loss": 3.8086, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458493818311896e-05, + "loss": 3.8275, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457655223560844e-05, + "loss": 3.8139, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456816628809792e-05, + "loss": 3.8172, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455979671939113e-05, + "loss": 3.8119, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455141077188061e-05, + "loss": 3.8179, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.8033, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8179, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452626930815278e-05, + "loss": 3.8066, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451788336064226e-05, + "loss": 3.8152, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450949741313174e-05, + "loss": 3.8194, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.8156, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492741896914433e-05, + "loss": 3.8119, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484355949403913e-05, + "loss": 3.825, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475970001893393e-05, + "loss": 3.7993, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.8046, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445921448567608e-05, + "loss": 3.8202, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445082853816556e-05, + "loss": 3.8106, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444244259065504e-05, + "loss": 3.8077, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443405664314452e-05, + "loss": 3.8007, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442568707443773e-05, + "loss": 3.8021, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441730112692721e-05, + "loss": 3.8113, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440891517941669e-05, + "loss": 3.8192, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440052923190617e-05, + "loss": 3.8116, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439215966319939e-05, + "loss": 3.8204, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438377371568887e-05, + "loss": 3.8203, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437538776817835e-05, + "loss": 3.8326, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436700182066783e-05, + "loss": 3.7987, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358632251961036e-05, + "loss": 3.8103, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350246304450516e-05, + "loss": 3.8182, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341860356939996e-05, + "loss": 3.7994, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333474409429476e-05, + "loss": 3.8138, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325104840722685e-05, + "loss": 3.8126, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316718893212165e-05, + "loss": 3.8147, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308332945701645e-05, + "loss": 3.812, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299946998191125e-05, + "loss": 3.7987, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429157742948434e-05, + "loss": 3.8001, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428319148197382e-05, + "loss": 3.8039, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.42748055344633e-05, + "loss": 3.8094, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426641958695278e-05, + "loss": 3.8142, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425805001824599e-05, + "loss": 3.7969, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424966407073547e-05, + "loss": 3.8061, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424127812322495e-05, + "loss": 3.7939, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423289217571443e-05, + "loss": 3.8008, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422452260700764e-05, + "loss": 3.8069, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421613665949712e-05, + "loss": 3.8059, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.42077507119866e-05, + "loss": 3.8163, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419936476447608e-05, + "loss": 3.802, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190995195769294e-05, + "loss": 3.8011, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182609248258774e-05, + "loss": 3.8061, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174223300748254e-05, + "loss": 3.8016, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165837353237734e-05, + "loss": 3.8097, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157467784530943e-05, + "loss": 3.7956, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149081837020423e-05, + "loss": 3.8017, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.41406958895099e-05, + "loss": 3.8035, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413230994199938e-05, + "loss": 3.8094, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412394037329259e-05, + "loss": 3.7867, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411555442578207e-05, + "loss": 3.7974, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410716847827155e-05, + "loss": 3.8081, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409878253076103e-05, + "loss": 3.8023, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409042934085798e-05, + "loss": 3.79, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408204339334746e-05, + "loss": 3.8006, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407365744583694e-05, + "loss": 3.7931, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406527149832642e-05, + "loss": 3.8078, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568855508159e-05, + "loss": 3.7948, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404849960330538e-05, + "loss": 3.7949, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404011365579486e-05, + "loss": 3.806, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403172770828434e-05, + "loss": 3.8112, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023358139577546e-05, + "loss": 3.8017, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014972192067026e-05, + "loss": 3.7979, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006586244556506e-05, + "loss": 3.8049, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998200297045986e-05, + "loss": 3.7993, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.39898307283392e-05, + "loss": 3.7885, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398144478082868e-05, + "loss": 3.8001, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397305883331816e-05, + "loss": 3.7894, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396467288580764e-05, + "loss": 3.797, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395630331710085e-05, + "loss": 3.7912, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394791736959033e-05, + "loss": 3.7991, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393953142207981e-05, + "loss": 3.7882, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393114547456929e-05, + "loss": 3.7866, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.39227759058625e-05, + "loss": 3.7934, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391438995835198e-05, + "loss": 3.8044, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390600401084146e-05, + "loss": 3.8015, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389761806333094e-05, + "loss": 3.8015, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889248494624155e-05, + "loss": 3.7834, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880862547113635e-05, + "loss": 3.8024, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872476599603115e-05, + "loss": 3.8001, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864090652092595e-05, + "loss": 3.7971, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855721083385804e-05, + "loss": 3.789, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847335135875284e-05, + "loss": 3.8039, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838949188364764e-05, + "loss": 3.7914, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830563240854244e-05, + "loss": 3.8026, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822193672147453e-05, + "loss": 3.7803, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381380772463693e-05, + "loss": 3.8036, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380542177712641e-05, + "loss": 3.7851, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379705220841962e-05, + "loss": 3.787, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378866626090911e-05, + "loss": 3.798, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378028031339859e-05, + "loss": 3.794, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377189436588807e-05, + "loss": 3.7964, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376352479718128e-05, + "loss": 3.7799, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375513884967076e-05, + "loss": 3.7942, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.886220693588257, + "eval_runtime": 303.2622, + "eval_samples_per_second": 1258.287, + "eval_steps_per_second": 39.322, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374675290216024e-05, + "loss": 3.7904, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373836695464972e-05, + "loss": 3.7844, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372999738594293e-05, + "loss": 3.7943, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372161143843241e-05, + "loss": 3.7862, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371322549092189e-05, + "loss": 3.8005, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370483954341137e-05, + "loss": 3.7825, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696469974704576e-05, + "loss": 3.7851, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368808402719406e-05, + "loss": 3.7835, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367969807968354e-05, + "loss": 3.7885, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367132851097675e-05, + "loss": 3.7908, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366294256346623e-05, + "loss": 3.7833, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365455661595571e-05, + "loss": 3.792, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364617066844519e-05, + "loss": 3.7774, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637784720934665e-05, + "loss": 3.7823, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629398773424145e-05, + "loss": 3.7832, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3621012825913625e-05, + "loss": 3.7744, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612626878403105e-05, + "loss": 3.7835, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604257309696314e-05, + "loss": 3.7767, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.35958713621858e-05, + "loss": 3.7766, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358748541467528e-05, + "loss": 3.7978, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357909946716476e-05, + "loss": 3.7856, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357072989845797e-05, + "loss": 3.7903, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562360329751186e-05, + "loss": 3.783, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553974382240665e-05, + "loss": 3.7865, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354558843473014e-05, + "loss": 3.7678, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353720248721962e-05, + "loss": 3.7905, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.35288165397091e-05, + "loss": 3.7791, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352043059219858e-05, + "loss": 3.7697, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351204464468806e-05, + "loss": 3.7709, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350367507598127e-05, + "loss": 3.7735, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349528912847075e-05, + "loss": 3.7802, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486919559763963e-05, + "loss": 3.7888, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347853361225344e-05, + "loss": 3.7877, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347014766474292e-05, + "loss": 3.7769, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34617617172324e-05, + "loss": 3.7722, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345337576972188e-05, + "loss": 3.7796, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344498982221136e-05, + "loss": 3.7746, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343660387470084e-05, + "loss": 3.7786, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342823430599405e-05, + "loss": 3.7653, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341984835848353e-05, + "loss": 3.7694, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341146241097301e-05, + "loss": 3.7737, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340309284226622e-05, + "loss": 3.7856, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.33947068947557e-05, + "loss": 3.7759, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338632094724519e-05, + "loss": 3.7702, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337793499973467e-05, + "loss": 3.7774, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336954905222415e-05, + "loss": 3.7675, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336116310471363e-05, + "loss": 3.7776, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7666, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334440758849632e-05, + "loss": 3.7559, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33360216409858e-05, + "loss": 3.7775, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332763569347528e-05, + "loss": 3.769, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331924974596476e-05, + "loss": 3.7673, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331086379845424e-05, + "loss": 3.7665, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302494229747446e-05, + "loss": 3.7647, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294108282236926e-05, + "loss": 3.7561, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285722334726406e-05, + "loss": 3.7676, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277336387215886e-05, + "loss": 3.7601, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.765, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.7738, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252178544684325e-05, + "loss": 3.7633, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243792597173805e-05, + "loss": 3.7641, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.7773, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.32270370809565e-05, + "loss": 3.7546, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218651133445974e-05, + "loss": 3.7566, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321028156473919e-05, + "loss": 3.7667, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.767, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.7565, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185123722207623e-05, + "loss": 3.7563, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317675415350084e-05, + "loss": 3.7529, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168368205990326e-05, + "loss": 3.7654, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.7694, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315159631096928e-05, + "loss": 3.7656, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143226742262495e-05, + "loss": 3.7734, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134840794751975e-05, + "loss": 3.7671, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.7901, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311806889973093e-05, + "loss": 3.7518, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109699331024144e-05, + "loss": 3.7627, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310131338351362e-05, + "loss": 3.7733, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30929274360031e-05, + "loss": 3.7507, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308454148849258e-05, + "loss": 3.7689, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307617191978579e-05, + "loss": 3.7665, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306778597227527e-05, + "loss": 3.7669, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305940002476475e-05, + "loss": 3.7649, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305101407725423e-05, + "loss": 3.7511, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304264450854745e-05, + "loss": 3.7588, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303425856103692e-05, + "loss": 3.7524, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.30258726135264e-05, + "loss": 3.7646, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301748666601588e-05, + "loss": 3.7676, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300911709730909e-05, + "loss": 3.7483, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300073114979857e-05, + "loss": 3.7617, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299234520228805e-05, + "loss": 3.7511, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298395925477753e-05, + "loss": 3.7522, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297558968607075e-05, + "loss": 3.7564, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967203738560227e-05, + "loss": 3.7666, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958817791049707e-05, + "loss": 3.772, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950431843539186e-05, + "loss": 3.7542, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2942062274832396e-05, + "loss": 3.7528, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933676327321876e-05, + "loss": 3.763, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925290379811355e-05, + "loss": 3.7536, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916904432300835e-05, + "loss": 3.7677, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908534863594045e-05, + "loss": 3.7506, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.7547, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891762968573004e-05, + "loss": 3.7603, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883377021062484e-05, + "loss": 3.764, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.28750074523557e-05, + "loss": 3.7415, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.7524, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285823555733466e-05, + "loss": 3.76, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284984960982414e-05, + "loss": 3.7584, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841496419921085e-05, + "loss": 3.7428, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833110472410565e-05, + "loss": 3.7605, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282472452490004e-05, + "loss": 3.7451, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281633857738952e-05, + "loss": 3.7586, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807952629879e-05, + "loss": 3.7545, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799583061172214e-05, + "loss": 3.7503, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791197113661694e-05, + "loss": 3.757, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782811166151174e-05, + "loss": 3.7703, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774425218640654e-05, + "loss": 3.7564, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.7551, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7607, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.7563, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740881428598574e-05, + "loss": 3.7459, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.753, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.746, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271575634367447e-05, + "loss": 3.7512, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270737039616395e-05, + "loss": 3.7524, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269898444865343e-05, + "loss": 3.7525, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7483, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.74, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267382660612187e-05, + "loss": 3.7524, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266544065861136e-05, + "loss": 3.7596, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265707108990457e-05, + "loss": 3.7558, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7584, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264029919488353e-05, + "loss": 3.7364, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263191324737301e-05, + "loss": 3.7622, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623543678666216e-05, + "loss": 3.7558, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7527, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606771783645176e-05, + "loss": 3.7508, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598385836134656e-05, + "loss": 3.7551, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589999888624136e-05, + "loss": 3.7483, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581613941113616e-05, + "loss": 3.7649, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573227993603096e-05, + "loss": 3.7359, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564842046092576e-05, + "loss": 3.7577, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255647247738579e-05, + "loss": 3.7426, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254808652987527e-05, + "loss": 3.7452, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253970058236475e-05, + "loss": 3.7525, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253131463485423e-05, + "loss": 3.7466, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252294506614744e-05, + "loss": 3.7598, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251455911863692e-05, + "loss": 3.733, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25061731711264e-05, + "loss": 3.7539, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.869997501373291, + "eval_runtime": 303.6572, + "eval_samples_per_second": 1256.65, + "eval_steps_per_second": 39.271, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497787223615874e-05, + "loss": 3.7486, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489401276105354e-05, + "loss": 3.741, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2481015328594834e-05, + "loss": 3.7533, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472629381084314e-05, + "loss": 3.7448, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464243433573794e-05, + "loss": 3.7566, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245585748606328e-05, + "loss": 3.7407, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244747153855276e-05, + "loss": 3.7398, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243908559104224e-05, + "loss": 3.7449, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243071602233545e-05, + "loss": 3.7457, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242234645362866e-05, + "loss": 3.7465, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241396050611814e-05, + "loss": 3.7455, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7458, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.23971886110971e-05, + "loss": 3.7409, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238880266358658e-05, + "loss": 3.7398, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238041671607606e-05, + "loss": 3.743, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237203076856554e-05, + "loss": 3.7343, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236364482105502e-05, + "loss": 3.7393, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355275252348234e-05, + "loss": 3.7341, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346889304837714e-05, + "loss": 3.7337, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7557, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.23301337886204e-05, + "loss": 3.7463, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232174784110988e-05, + "loss": 3.7476, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231336189359936e-05, + "loss": 3.7407, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230497594608884e-05, + "loss": 3.7471, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229658999857832e-05, + "loss": 3.7268, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.22882040510678e-05, + "loss": 3.7486, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227981810355728e-05, + "loss": 3.7376, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227144853485049e-05, + "loss": 3.7308, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226306258733997e-05, + "loss": 3.73, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225467663982945e-05, + "loss": 3.7374, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224629069231893e-05, + "loss": 3.7402, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223792112361215e-05, + "loss": 3.7476, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222953517610163e-05, + "loss": 3.7454, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222114922859111e-05, + "loss": 3.7383, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221276328108059e-05, + "loss": 3.7289, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220437733357006e-05, + "loss": 3.7408, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219599138605954e-05, + "loss": 3.7393, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218760543854902e-05, + "loss": 3.7315, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.73, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217084992233171e-05, + "loss": 3.7273, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162480353624926e-05, + "loss": 3.7339, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154094406114406e-05, + "loss": 3.7418, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145708458603886e-05, + "loss": 3.7374, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137322511093366e-05, + "loss": 3.7301, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128936563582846e-05, + "loss": 3.7371, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212056699487606e-05, + "loss": 3.7296, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112181047365535e-05, + "loss": 3.7386, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103795099855015e-05, + "loss": 3.7266, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095409152344495e-05, + "loss": 3.7131, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087023204833975e-05, + "loss": 3.7364, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078653636127184e-05, + "loss": 3.7323, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070267688616664e-05, + "loss": 3.7283, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061881741106144e-05, + "loss": 3.7242, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053495793595623e-05, + "loss": 3.7249, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045109846085103e-05, + "loss": 3.7191, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203672389857459e-05, + "loss": 3.7251, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.20283543298678e-05, + "loss": 3.7221, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201996838235728e-05, + "loss": 3.7299, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201158243484676e-05, + "loss": 3.7317, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200319648733624e-05, + "loss": 3.7253, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199481053982572e-05, + "loss": 3.7238, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19864245923152e-05, + "loss": 3.7442, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197803864480468e-05, + "loss": 3.711, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196965269729416e-05, + "loss": 3.7149, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196128312858737e-05, + "loss": 3.7283, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7318, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7173, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7169, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927755717349024e-05, + "loss": 3.716, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919369769838504e-05, + "loss": 3.7224, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910983822327984e-05, + "loss": 3.7351, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902597874817464e-05, + "loss": 3.7253, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189422830611067e-05, + "loss": 3.7301, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7341, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.7476, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186907046357911e-05, + "loss": 3.7177, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7263, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.731, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184394537865501e-05, + "loss": 3.7122, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.18355594311445e-05, + "loss": 3.7292, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182717348363398e-05, + "loss": 3.7272, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181878753612346e-05, + "loss": 3.7289, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181040158861294e-05, + "loss": 3.7288, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.712, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17936296935919e-05, + "loss": 3.7189, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178524374608137e-05, + "loss": 3.719, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.7238, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.7299, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760102282353546e-05, + "loss": 3.7128, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175171633484302e-05, + "loss": 3.7242, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7136, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173497719742945e-05, + "loss": 3.7113, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172659124991893e-05, + "loss": 3.7222, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171820530240841e-05, + "loss": 3.726, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170981935489789e-05, + "loss": 3.7344, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170143340738737e-05, + "loss": 3.7199, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693047459876844e-05, + "loss": 3.7152, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684661512366324e-05, + "loss": 3.7246, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676275564855804e-05, + "loss": 3.718, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166790599614902e-05, + "loss": 3.7244, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165952004863849e-05, + "loss": 3.7169, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165113410112797e-05, + "loss": 3.7172, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164274815361745e-05, + "loss": 3.7203, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634394963714405e-05, + "loss": 3.7285, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1626009016203885e-05, + "loss": 3.7, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617623068693365e-05, + "loss": 3.7194, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7182, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160085117367232e-05, + "loss": 3.7244, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592481604965534e-05, + "loss": 3.705, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584095657455014e-05, + "loss": 3.7204, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575709709944494e-05, + "loss": 3.716, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156732376243397e-05, + "loss": 3.7177, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155893781492345e-05, + "loss": 3.7228, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155056824621666e-05, + "loss": 3.7148, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154218229870614e-05, + "loss": 3.7175, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153379635119562e-05, + "loss": 3.734, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254104036851e-05, + "loss": 3.7203, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7155, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7263, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150025256115354e-05, + "loss": 3.7214, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149186661364302e-05, + "loss": 3.7044, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148349704493623e-05, + "loss": 3.7205, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147511109742571e-05, + "loss": 3.71, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146674152871892e-05, + "loss": 3.7139, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.14583555812084e-05, + "loss": 3.7161, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144996963369788e-05, + "loss": 3.7163, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144158368618736e-05, + "loss": 3.714, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143319773867684e-05, + "loss": 3.7073, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142481179116632e-05, + "loss": 3.7129, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141642584365581e-05, + "loss": 3.7259, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408056274949016e-05, + "loss": 3.7168, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399670327438496e-05, + "loss": 3.7223, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391284379927976e-05, + "loss": 3.7018, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382898432417456e-05, + "loss": 3.7296, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374528863710665e-05, + "loss": 3.7162, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366142916200145e-05, + "loss": 3.7174, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357756968689625e-05, + "loss": 3.7151, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349371021179105e-05, + "loss": 3.7194, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340985073668585e-05, + "loss": 3.7113, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332599126158065e-05, + "loss": 3.7319, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.7007, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7205, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130747404123397e-05, + "loss": 3.7116, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129908809372345e-05, + "loss": 3.7123, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129070214621293e-05, + "loss": 3.7149, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128231619870241e-05, + "loss": 3.7094, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127393025119189e-05, + "loss": 3.7269, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126554430368137e-05, + "loss": 3.7001, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7196, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.859549045562744, + "eval_runtime": 302.6413, + "eval_samples_per_second": 1260.869, + "eval_steps_per_second": 39.403, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124877240866032e-05, + "loss": 3.7145, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124041921875727e-05, + "loss": 3.7043, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123203327124675e-05, + "loss": 3.7147, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122364732373623e-05, + "loss": 3.7135, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215261376225714e-05, + "loss": 3.7188, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206875428715194e-05, + "loss": 3.7068, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1198489481204674e-05, + "loss": 3.7087, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7065, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.7156, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117334801747684e-05, + "loss": 3.7136, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116496206996632e-05, + "loss": 3.7121, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156576122455796e-05, + "loss": 3.708, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7055, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7042, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113143465872797e-05, + "loss": 3.7101, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112304871121745e-05, + "loss": 3.6974, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111466276370693e-05, + "loss": 3.7047, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110627681619641e-05, + "loss": 3.7011, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109789086868589e-05, + "loss": 3.7015, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7155, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7133, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7131, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106436345744754e-05, + "loss": 3.7071, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105597750993702e-05, + "loss": 3.7082, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.6942, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.7178, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.7021, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.6972, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101404777238442e-05, + "loss": 3.697, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.7047, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997308634970846e-05, + "loss": 3.7048, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988922687460326e-05, + "loss": 3.7159, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7131, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.6998, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963781223732495e-05, + "loss": 3.6968, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.7072, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.7061, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.6978, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.6952, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921851486179894e-05, + "loss": 3.6948, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.6985, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7109, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.7033, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088832407494155e-05, + "loss": 3.6953, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087993812743103e-05, + "loss": 3.7027, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.6947, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086318261121372e-05, + "loss": 3.7048, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08547966637032e-05, + "loss": 3.6958, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084641071619268e-05, + "loss": 3.6772, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083802476868216e-05, + "loss": 3.7049, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.6973, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082126925246485e-05, + "loss": 3.7003, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081288330495433e-05, + "loss": 3.6905, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080449735744381e-05, + "loss": 3.6901, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079611140993329e-05, + "loss": 3.6867, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078772546242277e-05, + "loss": 3.6918, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.6918, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770969946205464e-05, + "loss": 3.6931, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076258399869494e-05, + "loss": 3.7047, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075419805118442e-05, + "loss": 3.6863, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07458121036739e-05, + "loss": 3.6914, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073742615616338e-05, + "loss": 3.7075, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072904020865286e-05, + "loss": 3.6807, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072065426114234e-05, + "loss": 3.6825, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712284692435546e-05, + "loss": 3.6989, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703898744925026e-05, + "loss": 3.6972, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695512797414506e-05, + "loss": 3.6841, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068712684990399e-05, + "loss": 3.6866, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.06787572811972e-05, + "loss": 3.6813, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067037133368668e-05, + "loss": 3.6944, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066200176497989e-05, + "loss": 3.6982, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065361581746937e-05, + "loss": 3.6931, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064522986995885e-05, + "loss": 3.6966, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063684392244833e-05, + "loss": 3.7013, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062845797493781e-05, + "loss": 3.7153, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062007202742729e-05, + "loss": 3.686, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.06117024587205e-05, + "loss": 3.6942, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060331651120998e-05, + "loss": 3.6991, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059493056369946e-05, + "loss": 3.6828, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586544616188946e-05, + "loss": 3.6942, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578158668678426e-05, + "loss": 3.6984, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569772721167906e-05, + "loss": 3.6971, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561386773657386e-05, + "loss": 3.6992, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553000826146866e-05, + "loss": 3.6818, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544631257440075e-05, + "loss": 3.6833, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0536245309929555e-05, + "loss": 3.6874, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527859362419035e-05, + "loss": 3.6932, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0519473414908515e-05, + "loss": 3.6948, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0511103846201724e-05, + "loss": 3.6836, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502717898691204e-05, + "loss": 3.6893, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0494331951180684e-05, + "loss": 3.6861, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0485946003670164e-05, + "loss": 3.6797, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047757643496338e-05, + "loss": 3.6899, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046920686625659e-05, + "loss": 3.6949, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046082091874607e-05, + "loss": 3.7022, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045243497123555e-05, + "loss": 3.6919, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044404902372503e-05, + "loss": 3.6811, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043566307621451e-05, + "loss": 3.6934, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042727712870399e-05, + "loss": 3.6878, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.04189075599972e-05, + "loss": 3.6896, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041052161248668e-05, + "loss": 3.6884, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040213566497616e-05, + "loss": 3.6857, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039374971746564e-05, + "loss": 3.687, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038536376995512e-05, + "loss": 3.7, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.03769778224446e-05, + "loss": 3.6721, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036860825373781e-05, + "loss": 3.6888, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036022230622729e-05, + "loss": 3.6826, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351836358716766e-05, + "loss": 3.6922, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343450411206246e-05, + "loss": 3.6792, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335064463695726e-05, + "loss": 3.6906, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326678516185206e-05, + "loss": 3.68, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318308947478415e-05, + "loss": 3.6899, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309922999967895e-05, + "loss": 3.6915, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301537052457375e-05, + "loss": 3.6806, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293151104946855e-05, + "loss": 3.6872, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284765157436335e-05, + "loss": 3.7029, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276379209925815e-05, + "loss": 3.6906, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026800964121903e-05, + "loss": 3.6858, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025962369370851e-05, + "loss": 3.6914, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025123774619799e-05, + "loss": 3.693, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024285179868747e-05, + "loss": 3.6782, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023446585117695e-05, + "loss": 3.6883, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022607990366643e-05, + "loss": 3.6733, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021771033495964e-05, + "loss": 3.6859, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020932438744912e-05, + "loss": 3.6818, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.02009384399386e-05, + "loss": 3.6865, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019255249242808e-05, + "loss": 3.6839, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018416654491756e-05, + "loss": 3.6791, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017579697621077e-05, + "loss": 3.6778, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167411028700256e-05, + "loss": 3.6942, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159025081189736e-05, + "loss": 3.6895, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150639133679216e-05, + "loss": 3.6926, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142253186168696e-05, + "loss": 3.6699, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133883617461905e-05, + "loss": 3.7006, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125497669951385e-05, + "loss": 3.6821, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.0117111722440865e-05, + "loss": 3.687, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108725774930344e-05, + "loss": 3.6886, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100339827419824e-05, + "loss": 3.6851, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091953879909304e-05, + "loss": 3.6798, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008356793239878e-05, + "loss": 3.6986, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007518198488826e-05, + "loss": 3.6743, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006681241618147e-05, + "loss": 3.6927, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005844284747469e-05, + "loss": 3.681, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005005689996417e-05, + "loss": 3.6813, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004167095245365e-05, + "loss": 3.6814, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003328500494313e-05, + "loss": 3.6803, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.00248990574326e-05, + "loss": 3.6941, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001651310992208e-05, + "loss": 3.6741, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.00081435412153e-05, + "loss": 3.6867, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.852857828140259, + "eval_runtime": 302.1046, + "eval_samples_per_second": 1263.109, + "eval_steps_per_second": 39.473, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999975759370478e-05, + "loss": 3.6839, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999137164619425e-05, + "loss": 3.6773, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998298569868373e-05, + "loss": 3.6817, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997459975117321e-05, + "loss": 3.6812, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996621380366269e-05, + "loss": 3.6941, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995782785615218e-05, + "loss": 3.6734, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994944190864166e-05, + "loss": 3.6828, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994105596113114e-05, + "loss": 3.6781, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993268639242435e-05, + "loss": 3.6811, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924316823717556e-05, + "loss": 3.6875, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915930876207036e-05, + "loss": 3.6808, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907544928696516e-05, + "loss": 3.6748, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899158981185996e-05, + "loss": 3.6831, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890773033675476e-05, + "loss": 3.6672, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882387086164956e-05, + "loss": 3.6783, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874017517458165e-05, + "loss": 3.6705, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865631569947645e-05, + "loss": 3.6746, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985724562243713e-05, + "loss": 3.6732, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984885967492661e-05, + "loss": 3.6687, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984049010621982e-05, + "loss": 3.6867, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.98321041587093e-05, + "loss": 3.6881, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982371821119878e-05, + "loss": 3.6861, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981533226368826e-05, + "loss": 3.6756, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980694631617774e-05, + "loss": 3.6772, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979856036866722e-05, + "loss": 3.6699, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.97901744211567e-05, + "loss": 3.6838, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978178847364618e-05, + "loss": 3.6756, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977341890493939e-05, + "loss": 3.6748, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976503295742887e-05, + "loss": 3.6676, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975664700991835e-05, + "loss": 3.6719, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748277441211565e-05, + "loss": 3.6711, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739891493701045e-05, + "loss": 3.687, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731505546190525e-05, + "loss": 3.6818, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723119598680005e-05, + "loss": 3.6712, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714750029973214e-05, + "loss": 3.6672, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706364082462694e-05, + "loss": 3.6765, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697978134952174e-05, + "loss": 3.6774, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689592187441654e-05, + "loss": 3.6706, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681206239931134e-05, + "loss": 3.6704, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672820292420614e-05, + "loss": 3.6632, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966443434491009e-05, + "loss": 3.6664, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96560647762033e-05, + "loss": 3.6806, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964767882869278e-05, + "loss": 3.6805, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963929288118226e-05, + "loss": 3.6647, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963090693367174e-05, + "loss": 3.6752, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962253736496496e-05, + "loss": 3.6671, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961415141745444e-05, + "loss": 3.6746, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960576546994391e-05, + "loss": 3.6692, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959737952243339e-05, + "loss": 3.6447, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958899357492287e-05, + "loss": 3.6805, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958062400621609e-05, + "loss": 3.6676, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957223805870556e-05, + "loss": 3.6729, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956385211119504e-05, + "loss": 3.6646, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955546616368452e-05, + "loss": 3.6622, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547080216174e-05, + "loss": 3.6553, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953869426866349e-05, + "loss": 3.6632, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530324699956696e-05, + "loss": 3.6644, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521938752446176e-05, + "loss": 3.6623, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513552804935656e-05, + "loss": 3.6755, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505166857425136e-05, + "loss": 3.6601, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496797288718345e-05, + "loss": 3.6653, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488411341207825e-05, + "loss": 3.68, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480025393697305e-05, + "loss": 3.6533, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471639446186785e-05, + "loss": 3.653, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463253498676265e-05, + "loss": 3.6692, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454867551165745e-05, + "loss": 3.6682, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446497982458954e-05, + "loss": 3.6582, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943811203494844e-05, + "loss": 3.6583, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942972608743792e-05, + "loss": 3.6557, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.94213401399274e-05, + "loss": 3.6633, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941295419241688e-05, + "loss": 3.6684, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940458462371009e-05, + "loss": 3.6649, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939619867619957e-05, + "loss": 3.6714, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938781272868905e-05, + "loss": 3.6733, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937942678117853e-05, + "loss": 3.6878, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937104083366801e-05, + "loss": 3.6551, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936265488615749e-05, + "loss": 3.6716, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.93542853174507e-05, + "loss": 3.6699, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934589936994018e-05, + "loss": 3.6577, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933751342242966e-05, + "loss": 3.6631, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932912747491914e-05, + "loss": 3.6751, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320741527408625e-05, + "loss": 3.6684, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.93123555798981e-05, + "loss": 3.6732, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303986011191315e-05, + "loss": 3.6525, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295600063680794e-05, + "loss": 3.6543, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287214116170274e-05, + "loss": 3.6603, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927882816865975e-05, + "loss": 3.6658, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927044222114923e-05, + "loss": 3.6678, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926205627363871e-05, + "loss": 3.6588, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925367032612819e-05, + "loss": 3.6545, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245300757421397e-05, + "loss": 3.6615, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9236914809910877e-05, + "loss": 3.6523, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922852886240036e-05, + "loss": 3.6624, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922014291488984e-05, + "loss": 3.6697, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921177334618305e-05, + "loss": 3.6734, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920338739867253e-05, + "loss": 3.6633, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919500145116201e-05, + "loss": 3.6549, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918661550365149e-05, + "loss": 3.6645, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917822955614097e-05, + "loss": 3.6591, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916984360863045e-05, + "loss": 3.6635, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916145766111993e-05, + "loss": 3.663, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915307171360941e-05, + "loss": 3.6537, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914470214490262e-05, + "loss": 3.6675, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913633257619583e-05, + "loss": 3.6669, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912794662868532e-05, + "loss": 3.6444, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.91195606811748e-05, + "loss": 3.6602, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911117473366428e-05, + "loss": 3.6532, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910278878615376e-05, + "loss": 3.6716, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094419217446966e-05, + "loss": 3.6464, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086033269936446e-05, + "loss": 3.6655, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077647322425926e-05, + "loss": 3.6531, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069261374915406e-05, + "loss": 3.6626, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060891806208615e-05, + "loss": 3.6624, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052505858698095e-05, + "loss": 3.6568, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044119911187575e-05, + "loss": 3.6584, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035733963677055e-05, + "loss": 3.6755, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027348016166535e-05, + "loss": 3.6595, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018962068656015e-05, + "loss": 3.6632, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010576121145495e-05, + "loss": 3.6631, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900219017363498e-05, + "loss": 3.6635, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899382060492819e-05, + "loss": 3.6585, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898543465741767e-05, + "loss": 3.6591, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897704870990715e-05, + "loss": 3.6446, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896866276239663e-05, + "loss": 3.6578, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896027681488611e-05, + "loss": 3.6542, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951890867375583e-05, + "loss": 3.6592, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.89435212986688e-05, + "loss": 3.657, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893513535115828e-05, + "loss": 3.6541, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892674940364775e-05, + "loss": 3.6508, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891836345613723e-05, + "loss": 3.6708, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890999388743045e-05, + "loss": 3.6581, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901607939919935e-05, + "loss": 3.6681, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889322199240941e-05, + "loss": 3.6413, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888483604489889e-05, + "loss": 3.6749, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876466476192104e-05, + "loss": 3.6538, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886808052868158e-05, + "loss": 3.6624, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885969458117106e-05, + "loss": 3.6605, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885130863366054e-05, + "loss": 3.656, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884292268615002e-05, + "loss": 3.657, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.88345367386395e-05, + "loss": 3.6734, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826167169932706e-05, + "loss": 3.6418, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817781222422186e-05, + "loss": 3.6681, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880939527491167e-05, + "loss": 3.6575, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880100932740115e-05, + "loss": 3.6499, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879262337989063e-05, + "loss": 3.6571, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878423743238011e-05, + "loss": 3.6533, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877585148486959e-05, + "loss": 3.6699, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876746553735907e-05, + "loss": 3.6495, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875909596865228e-05, + "loss": 3.6581, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8472084999084473, + "eval_runtime": 400.0213, + "eval_samples_per_second": 953.927, + "eval_steps_per_second": 29.811, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875071002114176e-05, + "loss": 3.6539, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874234045243497e-05, + "loss": 3.6517, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873395450492445e-05, + "loss": 3.6557, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872556855741393e-05, + "loss": 3.6576, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871718260990341e-05, + "loss": 3.6688, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870879666239289e-05, + "loss": 3.6444, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870041071488237e-05, + "loss": 3.6556, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869202476737186e-05, + "loss": 3.6506, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868363881986134e-05, + "loss": 3.655, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675269251154546e-05, + "loss": 3.6624, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666883303644026e-05, + "loss": 3.6523, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658497356133506e-05, + "loss": 3.65, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650111408622986e-05, + "loss": 3.6608, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641725461112466e-05, + "loss": 3.6389, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863333951360194e-05, + "loss": 3.6515, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624969944895155e-05, + "loss": 3.6431, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616583997384635e-05, + "loss": 3.6504, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608198049874115e-05, + "loss": 3.6462, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599812102363595e-05, + "loss": 3.6466, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591442533656804e-05, + "loss": 3.6617, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858305658614629e-05, + "loss": 3.6602, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857467063863577e-05, + "loss": 3.6602, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566284691125244e-05, + "loss": 3.6509, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557898743614724e-05, + "loss": 3.6495, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854952917490794e-05, + "loss": 3.6425, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854114322739741e-05, + "loss": 3.6582, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853275727988689e-05, + "loss": 3.6541, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852437133237637e-05, + "loss": 3.6493, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851598538486585e-05, + "loss": 3.6424, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850759943735533e-05, + "loss": 3.6467, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849922986864854e-05, + "loss": 3.6438, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849084392113803e-05, + "loss": 3.6625, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848245797362751e-05, + "loss": 3.6597, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847407202611699e-05, + "loss": 3.6468, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.84657024574102e-05, + "loss": 3.6453, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845731650989968e-05, + "loss": 3.6456, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844893056238916e-05, + "loss": 3.6529, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844054461487864e-05, + "loss": 3.6457, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843215866736812e-05, + "loss": 3.6433, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.84237727198576e-05, + "loss": 3.6379, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415403151150807e-05, + "loss": 3.6449, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407017203640286e-05, + "loss": 3.6492, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398631256129766e-05, + "loss": 3.6519, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390245308619246e-05, + "loss": 3.6446, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381859361108726e-05, + "loss": 3.6456, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837348979240194e-05, + "loss": 3.6461, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836510384489142e-05, + "loss": 3.6449, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.83567178973809e-05, + "loss": 3.6463, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834833194987038e-05, + "loss": 3.6178, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833996238116359e-05, + "loss": 3.6546, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833157643365307e-05, + "loss": 3.6434, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832319048614255e-05, + "loss": 3.6493, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831480453863203e-05, + "loss": 3.6399, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830641859112151e-05, + "loss": 3.6372, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829803264361099e-05, + "loss": 3.6317, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.82896630749042e-05, + "loss": 3.6352, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828127712739368e-05, + "loss": 3.6447, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827289117988317e-05, + "loss": 3.6301, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826450523237265e-05, + "loss": 3.6502, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825611928486213e-05, + "loss": 3.6387, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.82477333373516e-05, + "loss": 3.6366, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8239363768644816e-05, + "loss": 3.6571, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230977821134296e-05, + "loss": 3.6313, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8222591873623776e-05, + "loss": 3.6278, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821420592611325e-05, + "loss": 3.646, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820581997860273e-05, + "loss": 3.6444, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197450409895945e-05, + "loss": 3.6334, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189064462385425e-05, + "loss": 3.6336, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180678514874905e-05, + "loss": 3.625, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172292567364385e-05, + "loss": 3.6404, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.81639229986576e-05, + "loss": 3.643, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155537051147074e-05, + "loss": 3.6447, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147151103636554e-05, + "loss": 3.6427, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138765156126033e-05, + "loss": 3.6461, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130379208615513e-05, + "loss": 3.6611, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812199326110499e-05, + "loss": 3.6358, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.81136236923982e-05, + "loss": 3.6489, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810523774488768e-05, + "loss": 3.64, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809685179737716e-05, + "loss": 3.6359, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808846584986664e-05, + "loss": 3.6361, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808009628115986e-05, + "loss": 3.6515, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807171033364934e-05, + "loss": 3.6408, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806332438613882e-05, + "loss": 3.6478, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.80549384386283e-05, + "loss": 3.6291, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804655249111778e-05, + "loss": 3.6304, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803816654360726e-05, + "loss": 3.6371, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802978059609674e-05, + "loss": 3.6395, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802141102738995e-05, + "loss": 3.6429, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801302507987943e-05, + "loss": 3.6395, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800463913236891e-05, + "loss": 3.6248, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996269563662116e-05, + "loss": 3.6425, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987883616151596e-05, + "loss": 3.6301, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979497668641076e-05, + "loss": 3.6349, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971111721130556e-05, + "loss": 3.6432, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796274215242377e-05, + "loss": 3.6472, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795435620491325e-05, + "loss": 3.6394, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794597025740273e-05, + "loss": 3.6328, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793758430989221e-05, + "loss": 3.638, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792919836238169e-05, + "loss": 3.6338, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.79208287936749e-05, + "loss": 3.6442, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791244284616438e-05, + "loss": 3.6362, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790405689865386e-05, + "loss": 3.6355, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789567095114334e-05, + "loss": 3.6402, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788728500363282e-05, + "loss": 3.6438, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.78788990561223e-05, + "loss": 3.6235, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787052948741551e-05, + "loss": 3.6371, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786214353990499e-05, + "loss": 3.629, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853757592394476e-05, + "loss": 3.6456, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845371644883956e-05, + "loss": 3.6235, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836985697373436e-05, + "loss": 3.6387, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7828616128666645e-05, + "loss": 3.6266, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7820230181156125e-05, + "loss": 3.6437, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811844233645605e-05, + "loss": 3.637, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803458286135085e-05, + "loss": 3.6307, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779507233862456e-05, + "loss": 3.6361, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786702769917774e-05, + "loss": 3.6494, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778316822407254e-05, + "loss": 3.6367, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769930874896734e-05, + "loss": 3.6423, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761544927386214e-05, + "loss": 3.6378, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753158979875694e-05, + "loss": 3.6362, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774478941116891e-05, + "loss": 3.6387, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773640346365838e-05, + "loss": 3.6297, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772801751614786e-05, + "loss": 3.6237, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771963156863734e-05, + "loss": 3.6368, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771126199993056e-05, + "loss": 3.6337, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770287605242003e-05, + "loss": 3.6355, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769449010490951e-05, + "loss": 3.634, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768610415739899e-05, + "loss": 3.6298, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767773458869221e-05, + "loss": 3.6267, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766934864118168e-05, + "loss": 3.6456, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766096269367117e-05, + "loss": 3.6351, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765257674616065e-05, + "loss": 3.6445, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764420717745386e-05, + "loss": 3.6183, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763582122994334e-05, + "loss": 3.6481, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762743528243282e-05, + "loss": 3.6372, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.76190493349223e-05, + "loss": 3.637, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610663387411777e-05, + "loss": 3.6338, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602293818704986e-05, + "loss": 3.6328, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593907871194466e-05, + "loss": 3.6358, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585521923683946e-05, + "loss": 3.6478, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577135976173426e-05, + "loss": 3.621, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568766407466635e-05, + "loss": 3.6405, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756038045995612e-05, + "loss": 3.6314, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.75519945124456e-05, + "loss": 3.6285, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754360856493508e-05, + "loss": 3.6346, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753522261742456e-05, + "loss": 3.63, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752683666991404e-05, + "loss": 3.6411, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751846710120725e-05, + "loss": 3.6343, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751008115369673e-05, + "loss": 3.6307, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.846785306930542, + "eval_runtime": 310.4781, + "eval_samples_per_second": 1229.043, + "eval_steps_per_second": 38.409, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750169520618621e-05, + "loss": 3.6311, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749330925867569e-05, + "loss": 3.6274, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748492331116517e-05, + "loss": 3.6299, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747653736365465e-05, + "loss": 3.635, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746816779494786e-05, + "loss": 3.6445, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745978184743734e-05, + "loss": 3.6219, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745139589992682e-05, + "loss": 3.6312, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443009952416306e-05, + "loss": 3.632, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434624004905786e-05, + "loss": 3.6297, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426254436198995e-05, + "loss": 3.6342, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417868488688475e-05, + "loss": 3.6275, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409482541177955e-05, + "loss": 3.6299, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401096593667435e-05, + "loss": 3.636, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392710646156915e-05, + "loss": 3.6171, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384324698646395e-05, + "loss": 3.6292, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375955129939604e-05, + "loss": 3.6168, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367569182429084e-05, + "loss": 3.6298, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359183234918564e-05, + "loss": 3.6246, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350797287408044e-05, + "loss": 3.6212, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734242771870125e-05, + "loss": 3.6363, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733404177119074e-05, + "loss": 3.6349, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732565582368022e-05, + "loss": 3.6374, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731726987616969e-05, + "loss": 3.6311, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730888392865917e-05, + "loss": 3.6268, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730051435995239e-05, + "loss": 3.6259, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729212841244187e-05, + "loss": 3.6316, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728374246493134e-05, + "loss": 3.6279, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727535651742082e-05, + "loss": 3.6289, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.72669705699103e-05, + "loss": 3.6218, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725858462239978e-05, + "loss": 3.6216, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250215053693e-05, + "loss": 3.6239, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724182910618248e-05, + "loss": 3.6314, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723344315867196e-05, + "loss": 3.6393, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722505721116144e-05, + "loss": 3.6251, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216687642454646e-05, + "loss": 3.6235, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208301694944126e-05, + "loss": 3.6209, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199915747433606e-05, + "loss": 3.633, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191529799923086e-05, + "loss": 3.6242, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183143852412566e-05, + "loss": 3.6204, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174757904902046e-05, + "loss": 3.6144, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166388336195255e-05, + "loss": 3.6239, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158002388684735e-05, + "loss": 3.623, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149616441174215e-05, + "loss": 3.6309, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141230493663695e-05, + "loss": 3.6254, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132844546153175e-05, + "loss": 3.6224, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712447497744639e-05, + "loss": 3.623, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711608902993587e-05, + "loss": 3.6243, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710770308242535e-05, + "loss": 3.6232, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709931713491483e-05, + "loss": 3.5954, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709094756620804e-05, + "loss": 3.6299, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708256161869752e-05, + "loss": 3.6201, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074175671187e-05, + "loss": 3.6283, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706578972367648e-05, + "loss": 3.6175, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705740377616596e-05, + "loss": 3.6139, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704901782865544e-05, + "loss": 3.608, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704063188114492e-05, + "loss": 3.6125, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703226231243813e-05, + "loss": 3.6243, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023876364927615e-05, + "loss": 3.606, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015490417417095e-05, + "loss": 3.629, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007104469906575e-05, + "loss": 3.6141, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998718522396055e-05, + "loss": 3.6099, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990348953689264e-05, + "loss": 3.6359, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981963006178744e-05, + "loss": 3.612, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973577058668224e-05, + "loss": 3.6052, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.69651911111577e-05, + "loss": 3.6219, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695680516364718e-05, + "loss": 3.6211, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694843559494039e-05, + "loss": 3.6089, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694004964742987e-05, + "loss": 3.6128, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693166369991935e-05, + "loss": 3.6042, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692327775240883e-05, + "loss": 3.6167, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691490818370205e-05, + "loss": 3.6233, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690652223619153e-05, + "loss": 3.6217, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898136288681e-05, + "loss": 3.6202, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688975034117048e-05, + "loss": 3.6223, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688136439365996e-05, + "loss": 3.6395, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687297844614944e-05, + "loss": 3.6176, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686460887744265e-05, + "loss": 3.6248, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685622292993213e-05, + "loss": 3.6164, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684783698242161e-05, + "loss": 3.6157, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683945103491109e-05, + "loss": 3.6095, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683108146620431e-05, + "loss": 3.6327, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682269551869379e-05, + "loss": 3.6198, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681430957118327e-05, + "loss": 3.6261, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680592362367275e-05, + "loss": 3.6057, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679753767616223e-05, + "loss": 3.6086, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789168107455436e-05, + "loss": 3.6142, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780782159944916e-05, + "loss": 3.617, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772396212434396e-05, + "loss": 3.6202, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764010264923876e-05, + "loss": 3.6189, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755624317413356e-05, + "loss": 3.605, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747254748706565e-05, + "loss": 3.6163, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738868801196045e-05, + "loss": 3.6091, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730482853685525e-05, + "loss": 3.6104, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722096906175005e-05, + "loss": 3.622, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671372733746822e-05, + "loss": 3.628, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.67053413899577e-05, + "loss": 3.6166, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669695544244718e-05, + "loss": 3.6113, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668856949493666e-05, + "loss": 3.6169, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668018354742614e-05, + "loss": 3.608, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667181397871935e-05, + "loss": 3.6229, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666342803120883e-05, + "loss": 3.6121, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665504208369831e-05, + "loss": 3.6166, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664665613618779e-05, + "loss": 3.6193, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638286567481e-05, + "loss": 3.6154, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662990061997048e-05, + "loss": 3.6088, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662151467245996e-05, + "loss": 3.6116, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661312872494944e-05, + "loss": 3.6043, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604759156242654e-05, + "loss": 3.6231, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596373208732134e-05, + "loss": 3.6115, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587987261221614e-05, + "loss": 3.6113, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579601313711094e-05, + "loss": 3.6033, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571215366200574e-05, + "loss": 3.6185, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656284579749378e-05, + "loss": 3.6217, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655445984998326e-05, + "loss": 3.6089, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654607390247274e-05, + "loss": 3.6167, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653768795496222e-05, + "loss": 3.627, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652931838625543e-05, + "loss": 3.6118, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652093243874491e-05, + "loss": 3.6232, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651254649123439e-05, + "loss": 3.6157, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650416054372388e-05, + "loss": 3.6148, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649577459621336e-05, + "loss": 3.6168, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648740502750657e-05, + "loss": 3.6058, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647901907999605e-05, + "loss": 3.606, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647063313248553e-05, + "loss": 3.6121, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646224718497501e-05, + "loss": 3.6137, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453877616268217e-05, + "loss": 3.6139, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445491668757697e-05, + "loss": 3.6081, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437105721247176e-05, + "loss": 3.6092, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428719773736656e-05, + "loss": 3.6023, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642033382622613e-05, + "loss": 3.6256, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411964257519345e-05, + "loss": 3.612, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640357831000883e-05, + "loss": 3.6238, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395192362498305e-05, + "loss": 3.6008, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386806414987785e-05, + "loss": 3.6226, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378436846281e-05, + "loss": 3.6149, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637005089877048e-05, + "loss": 3.6127, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361664951259954e-05, + "loss": 3.614, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6353279003749434e-05, + "loss": 3.6113, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344893056238914e-05, + "loss": 3.6123, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336507108728394e-05, + "loss": 3.6282, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328121161217874e-05, + "loss": 3.6021, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631975159251108e-05, + "loss": 3.6194, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631136564500057e-05, + "loss": 3.6092, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630297969749005e-05, + "loss": 3.6092, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629459374997953e-05, + "loss": 3.6138, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628620780246901e-05, + "loss": 3.6084, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627782185495849e-05, + "loss": 3.6202, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.62694522862517e-05, + "loss": 3.6151, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626106633874118e-05, + "loss": 3.6102, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8451502323150635, + "eval_runtime": 302.7027, + "eval_samples_per_second": 1260.613, + "eval_steps_per_second": 39.395, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625268039123066e-05, + "loss": 3.6064, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624429444372014e-05, + "loss": 3.6045, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623590849620962e-05, + "loss": 3.6124, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622753892750283e-05, + "loss": 3.6128, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621915297999231e-05, + "loss": 3.6227, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621076703248179e-05, + "loss": 3.6033, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620238108497127e-05, + "loss": 3.6122, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6193995137460754e-05, + "loss": 3.6094, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185609189950234e-05, + "loss": 3.6111, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177239621243443e-05, + "loss": 3.6109, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6168853673732923e-05, + "loss": 3.6138, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160467726222403e-05, + "loss": 3.6053, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615208177871188e-05, + "loss": 3.6131, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614369583120136e-05, + "loss": 3.5955, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613530988369084e-05, + "loss": 3.6057, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612694031498405e-05, + "loss": 3.5972, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611855436747353e-05, + "loss": 3.6132, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611016841996301e-05, + "loss": 3.6045, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610178247245249e-05, + "loss": 3.6, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609341290374571e-05, + "loss": 3.614, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608502695623519e-05, + "loss": 3.615, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607664100872467e-05, + "loss": 3.6118, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606825506121414e-05, + "loss": 3.6118, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605986911370362e-05, + "loss": 3.6062, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605149954499684e-05, + "loss": 3.607, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604311359748632e-05, + "loss": 3.6134, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603472764997579e-05, + "loss": 3.6007, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602634170246527e-05, + "loss": 3.6082, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601795575495475e-05, + "loss": 3.6027, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009586186247966e-05, + "loss": 3.599, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001200238737446e-05, + "loss": 3.6039, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992814291226926e-05, + "loss": 3.613, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984428343716406e-05, + "loss": 3.612, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976042396205886e-05, + "loss": 3.6123, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967672827499095e-05, + "loss": 3.6002, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5959286879988575e-05, + "loss": 3.5989, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5950900932478055e-05, + "loss": 3.6142, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942514984967535e-05, + "loss": 3.6023, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934129037457015e-05, + "loss": 3.6021, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925759468750224e-05, + "loss": 3.5958, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917373521239704e-05, + "loss": 3.6029, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908987573729184e-05, + "loss": 3.6012, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900601626218664e-05, + "loss": 3.6113, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892215678708144e-05, + "loss": 3.6052, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883829731197624e-05, + "loss": 3.5987, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587546016249084e-05, + "loss": 3.6056, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586707421498032e-05, + "loss": 3.6013, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.58586882674698e-05, + "loss": 3.6042, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585030231995928e-05, + "loss": 3.5803, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584193275125249e-05, + "loss": 3.6061, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583354680374197e-05, + "loss": 3.599, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582516085623145e-05, + "loss": 3.6083, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581677490872093e-05, + "loss": 3.5977, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580838896121041e-05, + "loss": 3.5926, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580000301369989e-05, + "loss": 3.5902, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.57916334449931e-05, + "loss": 3.5912, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578324749748258e-05, + "loss": 3.6047, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5774861549972064e-05, + "loss": 3.5838, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766475602461544e-05, + "loss": 3.6099, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575810603375475e-05, + "loss": 3.596, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574972008624423e-05, + "loss": 3.5893, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574133413873371e-05, + "loss": 3.6154, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573294819122319e-05, + "loss": 3.5922, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572456224371267e-05, + "loss": 3.5867, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571619267500588e-05, + "loss": 3.6021, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570780672749536e-05, + "loss": 3.5999, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569942077998484e-05, + "loss": 3.5865, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569103483247432e-05, + "loss": 3.5978, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568266526376753e-05, + "loss": 3.5819, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567427931625702e-05, + "loss": 3.5933, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.56658933687465e-05, + "loss": 3.6053, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565750742123598e-05, + "loss": 3.6013, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564913785252919e-05, + "loss": 3.6004, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640751905018667e-05, + "loss": 3.6014, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632365957508147e-05, + "loss": 3.6195, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5623980009997627e-05, + "loss": 3.5974, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.56155940624871e-05, + "loss": 3.6055, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607224493780316e-05, + "loss": 3.5939, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598838546269796e-05, + "loss": 3.5959, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559045259875927e-05, + "loss": 3.593, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582066651248755e-05, + "loss": 3.6087, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573680703738235e-05, + "loss": 3.6012, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556531113503145e-05, + "loss": 3.6075, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556925187520924e-05, + "loss": 3.5883, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548539240010404e-05, + "loss": 3.5881, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540153292499884e-05, + "loss": 3.5948, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531767344989364e-05, + "loss": 3.5936, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523397776282573e-05, + "loss": 3.597, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551501182877205e-05, + "loss": 3.5997, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550662588126153e-05, + "loss": 3.5893, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549823993375101e-05, + "loss": 3.5958, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548987036504422e-05, + "loss": 3.5914, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548148441753371e-05, + "loss": 3.5886, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547309847002319e-05, + "loss": 3.6011, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546471252251267e-05, + "loss": 3.6084, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545632657500215e-05, + "loss": 3.6, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544795700629536e-05, + "loss": 3.5869, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543957105878484e-05, + "loss": 3.6004, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543118511127432e-05, + "loss": 3.5894, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.54227991637638e-05, + "loss": 3.599, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541441321625328e-05, + "loss": 3.5974, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540602726874276e-05, + "loss": 3.5921, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539764132123224e-05, + "loss": 3.6014, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538927175252545e-05, + "loss": 3.5937, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538088580501493e-05, + "loss": 3.5917, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537249985750441e-05, + "loss": 3.5898, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536411390999389e-05, + "loss": 3.5865, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355727962483373e-05, + "loss": 3.6011, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534735839377658e-05, + "loss": 3.5944, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533897244626606e-05, + "loss": 3.5894, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533058649875554e-05, + "loss": 3.5838, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532220055124502e-05, + "loss": 3.5937, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531383098253823e-05, + "loss": 3.6023, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530544503502771e-05, + "loss": 3.5879, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529705908751719e-05, + "loss": 3.5987, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528867314000667e-05, + "loss": 3.6057, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528030357129988e-05, + "loss": 3.5968, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527191762378936e-05, + "loss": 3.5992, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526353167627884e-05, + "loss": 3.5999, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525514572876833e-05, + "loss": 3.5965, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5246776160061536e-05, + "loss": 3.5979, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238390212551016e-05, + "loss": 3.5867, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230004265040496e-05, + "loss": 3.5864, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221618317529976e-05, + "loss": 3.5954, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213232370019456e-05, + "loss": 3.595, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520484642250893e-05, + "loss": 3.5935, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519646047499841e-05, + "loss": 3.5944, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518807452748789e-05, + "loss": 3.5849, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5179704958781105e-05, + "loss": 3.5851, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171335390074314e-05, + "loss": 3.6045, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162949442563794e-05, + "loss": 3.5922, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515456349505328e-05, + "loss": 3.6073, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514617754754276e-05, + "loss": 3.5813, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513780797883597e-05, + "loss": 3.6033, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512942203132545e-05, + "loss": 3.597, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512103608381493e-05, + "loss": 3.594, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.51126501363044e-05, + "loss": 3.5908, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510428056759762e-05, + "loss": 3.594, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.50958946200871e-05, + "loss": 3.5955, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508750867257658e-05, + "loss": 3.6035, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507912272506605e-05, + "loss": 3.5865, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507073677755553e-05, + "loss": 3.5947, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506236720884875e-05, + "loss": 3.5923, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053981261338234e-05, + "loss": 3.5906, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504559531382771e-05, + "loss": 3.5894, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503720936631719e-05, + "loss": 3.5954, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028839797610403e-05, + "loss": 3.5973, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502045385009988e-05, + "loss": 3.5954, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501206790258936e-05, + "loss": 3.5881, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8435444831848145, + "eval_runtime": 302.4931, + "eval_samples_per_second": 1261.487, + "eval_steps_per_second": 39.422, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003681955078837e-05, + "loss": 3.6019, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995296007568317e-05, + "loss": 3.582, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4986910060057796e-05, + "loss": 3.595, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978524112547276e-05, + "loss": 3.5948, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970154543840486e-05, + "loss": 3.5985, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496176859632997e-05, + "loss": 3.59, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495338264881945e-05, + "loss": 3.5941, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494499670130893e-05, + "loss": 3.5898, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493661075379841e-05, + "loss": 3.5867, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492824118509162e-05, + "loss": 3.5913, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.49198552375811e-05, + "loss": 3.5966, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491146929007058e-05, + "loss": 3.5853, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490308334256006e-05, + "loss": 3.6, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489469739504954e-05, + "loss": 3.5733, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488631144753902e-05, + "loss": 3.5835, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487794187883223e-05, + "loss": 3.5798, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486955593132171e-05, + "loss": 3.5945, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486116998381119e-05, + "loss": 3.583, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485278403630067e-05, + "loss": 3.5802, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844414467593886e-05, + "loss": 3.5931, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836028520083366e-05, + "loss": 3.597, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827642572572846e-05, + "loss": 3.5938, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819256625062326e-05, + "loss": 3.5917, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810870677551806e-05, + "loss": 3.586, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802501108845015e-05, + "loss": 3.5927, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794115161334495e-05, + "loss": 3.592, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785729213823975e-05, + "loss": 3.5818, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777343266313455e-05, + "loss": 3.5897, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4768957318802935e-05, + "loss": 3.5821, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760571371292415e-05, + "loss": 3.5799, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752201802585624e-05, + "loss": 3.5881, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743815855075104e-05, + "loss": 3.5913, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473542990756459e-05, + "loss": 3.5935, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472704396005407e-05, + "loss": 3.5941, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471867439134728e-05, + "loss": 3.5834, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471028844383676e-05, + "loss": 3.5794, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470190249632624e-05, + "loss": 3.5951, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469351654881571e-05, + "loss": 3.5801, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468513060130519e-05, + "loss": 3.5831, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467676103259841e-05, + "loss": 3.5821, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466837508508789e-05, + "loss": 3.5795, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465998913757736e-05, + "loss": 3.5847, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465160319006684e-05, + "loss": 3.5942, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464321724255633e-05, + "loss": 3.5836, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463483129504581e-05, + "loss": 3.5822, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462646172633902e-05, + "loss": 3.587, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.46180757788285e-05, + "loss": 3.5822, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460968983131798e-05, + "loss": 3.5864, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460130388380746e-05, + "loss": 3.5651, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592934315100666e-05, + "loss": 3.5879, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584548367590146e-05, + "loss": 3.5784, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576162420079626e-05, + "loss": 3.5917, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567776472569106e-05, + "loss": 3.5779, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559406903862315e-05, + "loss": 3.5754, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551020956351795e-05, + "loss": 3.5703, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454263500884128e-05, + "loss": 3.5735, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453424906133076e-05, + "loss": 3.5868, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452587949262397e-05, + "loss": 3.5651, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451749354511345e-05, + "loss": 3.5912, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450910759760293e-05, + "loss": 3.5776, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450072165009241e-05, + "loss": 3.569, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449235208138562e-05, + "loss": 3.5969, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.44839661338751e-05, + "loss": 3.5686, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447558018636458e-05, + "loss": 3.5686, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446719423885406e-05, + "loss": 3.5799, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445880829134354e-05, + "loss": 3.5825, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445043872263675e-05, + "loss": 3.5701, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442052775126235e-05, + "loss": 3.5805, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433666827615715e-05, + "loss": 3.5618, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425280880105195e-05, + "loss": 3.5783, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416911311398404e-05, + "loss": 3.5856, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408525363887884e-05, + "loss": 3.5845, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400139416377364e-05, + "loss": 3.5793, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391753468866844e-05, + "loss": 3.5824, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383367521356324e-05, + "loss": 3.6018, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4374981573845804e-05, + "loss": 3.5801, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436661200513901e-05, + "loss": 3.5898, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435822605762849e-05, + "loss": 3.5751, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434984011011797e-05, + "loss": 3.5785, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434145416260745e-05, + "loss": 3.5722, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433308459390067e-05, + "loss": 3.5892, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432469864639015e-05, + "loss": 3.5818, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431631269887963e-05, + "loss": 3.5911, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430792675136911e-05, + "loss": 3.5698, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429954080385859e-05, + "loss": 3.5674, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.42911712351518e-05, + "loss": 3.5732, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428278528764128e-05, + "loss": 3.5822, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427439934013076e-05, + "loss": 3.5759, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426601339262024e-05, + "loss": 3.5814, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425762744510972e-05, + "loss": 3.5735, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424925787640293e-05, + "loss": 3.5753, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424087192889241e-05, + "loss": 3.5726, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423248598138189e-05, + "loss": 3.5704, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224100033871374e-05, + "loss": 3.5804, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421573046516458e-05, + "loss": 3.5904, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420734451765406e-05, + "loss": 3.5816, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419895857014354e-05, + "loss": 3.5701, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419057262263302e-05, + "loss": 3.5783, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182186675122496e-05, + "loss": 3.5737, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417381710641571e-05, + "loss": 3.5805, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416543115890519e-05, + "loss": 3.5781, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415704521139467e-05, + "loss": 3.5725, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148659263884145e-05, + "loss": 3.5821, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414028969517736e-05, + "loss": 3.5788, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413190374766684e-05, + "loss": 3.5734, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412351780015632e-05, + "loss": 3.5697, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.41151318526458e-05, + "loss": 3.5718, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106762283939016e-05, + "loss": 3.5772, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098376336428496e-05, + "loss": 3.578, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408999038891797e-05, + "loss": 3.5701, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408160444140745e-05, + "loss": 3.5672, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407321849389693e-05, + "loss": 3.5739, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064848925190145e-05, + "loss": 3.5871, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405646297767962e-05, + "loss": 3.5735, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.40480770301691e-05, + "loss": 3.5763, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403969108265858e-05, + "loss": 3.586, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031321513951794e-05, + "loss": 3.5797, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022935566441274e-05, + "loss": 3.5813, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014549618930754e-05, + "loss": 3.5829, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006163671420234e-05, + "loss": 3.5793, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3997777723909714e-05, + "loss": 3.5826, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398940815520292e-05, + "loss": 3.5646, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39810222076924e-05, + "loss": 3.5704, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397263626018188e-05, + "loss": 3.5731, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396426669147509e-05, + "loss": 3.5769, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395588074396457e-05, + "loss": 3.5776, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394749479645405e-05, + "loss": 3.5739, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393910884894353e-05, + "loss": 3.5636, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393072290143301e-05, + "loss": 3.5709, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392235333272623e-05, + "loss": 3.5854, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391396738521571e-05, + "loss": 3.5779, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390558143770519e-05, + "loss": 3.5839, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389719549019467e-05, + "loss": 3.5678, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388882592148788e-05, + "loss": 3.5819, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388043997397736e-05, + "loss": 3.5831, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387205402646684e-05, + "loss": 3.5741, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386366807895632e-05, + "loss": 3.5711, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855298510249526e-05, + "loss": 3.5763, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846912562739006e-05, + "loss": 3.5803, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838526615228486e-05, + "loss": 3.5854, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830140667717966e-05, + "loss": 3.5697, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382175472020745e-05, + "loss": 3.573, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381338515150066e-05, + "loss": 3.5748, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380499920399014e-05, + "loss": 3.5759, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379661325647962e-05, + "loss": 3.5694, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.37882273089691e-05, + "loss": 3.5799, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377985774026231e-05, + "loss": 3.5749, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377147179275179e-05, + "loss": 3.583, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376308584524127e-05, + "loss": 3.5698, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8436408042907715, + "eval_runtime": 385.3098, + "eval_samples_per_second": 990.349, + "eval_steps_per_second": 30.949, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375469989773075e-05, + "loss": 3.5734, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374631395022023e-05, + "loss": 3.5647, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373794438151344e-05, + "loss": 3.5756, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372955843400292e-05, + "loss": 3.5806, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721172486492406e-05, + "loss": 3.5775, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3712786538981886e-05, + "loss": 3.574, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704416970275095e-05, + "loss": 3.5731, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696031022764575e-05, + "loss": 3.5718, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687645075254055e-05, + "loss": 3.5681, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679259127743535e-05, + "loss": 3.5794, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3670873180233015e-05, + "loss": 3.5719, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662487232722495e-05, + "loss": 3.573, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654117664015704e-05, + "loss": 3.5808, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3645731716505184e-05, + "loss": 3.5571, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637345768994664e-05, + "loss": 3.5676, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3628959821484144e-05, + "loss": 3.5611, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620573873973624e-05, + "loss": 3.5787, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361220430526684e-05, + "loss": 3.5652, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360381835775632e-05, + "loss": 3.566, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.35954324102458e-05, + "loss": 3.5729, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358704646273528e-05, + "loss": 3.5831, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357866051522475e-05, + "loss": 3.5761, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357029094651797e-05, + "loss": 3.5759, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356190499900745e-05, + "loss": 3.5682, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355351905149692e-05, + "loss": 3.5784, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.35451331039864e-05, + "loss": 3.5702, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353674715647588e-05, + "loss": 3.5693, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352836120896536e-05, + "loss": 3.5726, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351997526145484e-05, + "loss": 3.566, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351160569274806e-05, + "loss": 3.5604, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350321974523754e-05, + "loss": 3.5681, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349483379772702e-05, + "loss": 3.5738, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.34864478502165e-05, + "loss": 3.579, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347806190270598e-05, + "loss": 3.5737, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469692333999186e-05, + "loss": 3.566, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461306386488666e-05, + "loss": 3.5632, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452920438978146e-05, + "loss": 3.5822, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444534491467626e-05, + "loss": 3.5559, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436164922760835e-05, + "loss": 3.5699, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3427778975250315e-05, + "loss": 3.5648, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419393027739795e-05, + "loss": 3.559, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341100708022928e-05, + "loss": 3.567, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340263751152249e-05, + "loss": 3.5781, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339425156401197e-05, + "loss": 3.5685, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338586561650145e-05, + "loss": 3.5625, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337747966899093e-05, + "loss": 3.5689, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336909372148041e-05, + "loss": 3.5637, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336070777396989e-05, + "loss": 3.572, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.33523382052631e-05, + "loss": 3.549, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334395225775258e-05, + "loss": 3.5646, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333556631024206e-05, + "loss": 3.563, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332718036273154e-05, + "loss": 3.576, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331881079402475e-05, + "loss": 3.5566, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331042484651423e-05, + "loss": 3.5617, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302038899003715e-05, + "loss": 3.5461, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3293652951493195e-05, + "loss": 3.5589, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285283382786405e-05, + "loss": 3.5725, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3276897435275885e-05, + "loss": 3.5481, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268511487765364e-05, + "loss": 3.5732, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260125540254844e-05, + "loss": 3.5623, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3251739592744324e-05, + "loss": 3.5571, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243370024037533e-05, + "loss": 3.5782, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234984076527013e-05, + "loss": 3.5502, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322659812901649e-05, + "loss": 3.5532, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321821218150597e-05, + "loss": 3.5603, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320984261279918e-05, + "loss": 3.5715, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320145666528867e-05, + "loss": 3.5537, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319307071777815e-05, + "loss": 3.5584, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318468477026763e-05, + "loss": 3.5457, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317631520156084e-05, + "loss": 3.5597, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316792925405032e-05, + "loss": 3.5662, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.31595433065398e-05, + "loss": 3.5711, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315115735902928e-05, + "loss": 3.5622, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314278779032249e-05, + "loss": 3.5663, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313440184281197e-05, + "loss": 3.5821, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312601589530145e-05, + "loss": 3.5627, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311762994779093e-05, + "loss": 3.5686, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310924400028041e-05, + "loss": 3.5634, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310087443157362e-05, + "loss": 3.5634, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.30924884840631e-05, + "loss": 3.5558, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308410253655258e-05, + "loss": 3.5697, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3075716589042056e-05, + "loss": 3.5615, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067330641531536e-05, + "loss": 3.5755, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305896107282475e-05, + "loss": 3.5606, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305057512531423e-05, + "loss": 3.5487, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042189177803705e-05, + "loss": 3.5554, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3033803230293185e-05, + "loss": 3.5677, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.30254336615864e-05, + "loss": 3.5552, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301704771407588e-05, + "loss": 3.5647, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300866176656536e-05, + "loss": 3.559, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300027581905484e-05, + "loss": 3.5551, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2991906250348056e-05, + "loss": 3.5568, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298352030283753e-05, + "loss": 3.5573, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297513435532701e-05, + "loss": 3.5628, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296674840781649e-05, + "loss": 3.5722, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295836246030597e-05, + "loss": 3.5691, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294999289159918e-05, + "loss": 3.5501, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294160694408866e-05, + "loss": 3.564, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293322099657814e-05, + "loss": 3.5539, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292483504906762e-05, + "loss": 3.5651, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.29164491015571e-05, + "loss": 3.5639, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908079532850314e-05, + "loss": 3.5534, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2899693585339794e-05, + "loss": 3.5633, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891307637829274e-05, + "loss": 3.5602, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2882921690318754e-05, + "loss": 3.5571, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874535742808234e-05, + "loss": 3.5542, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866149795297714e-05, + "loss": 3.5544, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285778022659092e-05, + "loss": 3.5644, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.28493942790804e-05, + "loss": 3.5629, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284100833156988e-05, + "loss": 3.5506, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283262238405936e-05, + "loss": 3.55, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282425281535257e-05, + "loss": 3.5569, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281586686784205e-05, + "loss": 3.5697, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280748092033153e-05, + "loss": 3.555, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279909497282101e-05, + "loss": 3.5587, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279072540411423e-05, + "loss": 3.5645, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278233945660371e-05, + "loss": 3.5706, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277395350909319e-05, + "loss": 3.5644, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276556756158267e-05, + "loss": 3.5623, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275719799287588e-05, + "loss": 3.5651, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274881204536536e-05, + "loss": 3.5649, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274042609785484e-05, + "loss": 3.5514, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273204015034432e-05, + "loss": 3.5561, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723670581637526e-05, + "loss": 3.551, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715284634127006e-05, + "loss": 3.5638, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2706898686616486e-05, + "loss": 3.5624, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698512739105966e-05, + "loss": 3.5555, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690126791595446e-05, + "loss": 3.5477, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268175722288866e-05, + "loss": 3.5568, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267337127537814e-05, + "loss": 3.5688, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266498532786762e-05, + "loss": 3.5632, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.26565993803571e-05, + "loss": 3.5656, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264822981165031e-05, + "loss": 3.5522, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263984386413979e-05, + "loss": 3.5655, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263145791662927e-05, + "loss": 3.566, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262307196911875e-05, + "loss": 3.5612, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261470240041196e-05, + "loss": 3.5542, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260631645290144e-05, + "loss": 3.56, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259793050539092e-05, + "loss": 3.5652, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.25895445578804e-05, + "loss": 3.5667, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581158610369886e-05, + "loss": 3.5541, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2572789041663095e-05, + "loss": 3.5546, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564403094152575e-05, + "loss": 3.5627, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556017146642055e-05, + "loss": 3.5588, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2547631199131535e-05, + "loss": 3.5509, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539245251621015e-05, + "loss": 3.5677, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2530875682914224e-05, + "loss": 3.5577, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522489735403704e-05, + "loss": 3.57, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514103787893184e-05, + "loss": 3.5469, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8441765308380127, + "eval_runtime": 370.5749, + "eval_samples_per_second": 1029.727, + "eval_steps_per_second": 32.18, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250571784038266e-05, + "loss": 3.5766, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249733189287214e-05, + "loss": 3.5499, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2488945945361624e-05, + "loss": 3.5565, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480559997851104e-05, + "loss": 3.5637, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247219042914431e-05, + "loss": 3.5616, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246380448163379e-05, + "loss": 3.561, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245541853412327e-05, + "loss": 3.5532, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244703258661275e-05, + "loss": 3.5563, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243864663910223e-05, + "loss": 3.5527, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243027707039544e-05, + "loss": 3.5612, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242189112288492e-05, + "loss": 3.5583, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.24135051753744e-05, + "loss": 3.5592, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240511922786388e-05, + "loss": 3.5642, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239673328035336e-05, + "loss": 3.5425, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238836371164658e-05, + "loss": 3.5486, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237997776413606e-05, + "loss": 3.5432, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237159181662554e-05, + "loss": 3.5638, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236320586911502e-05, + "loss": 3.546, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2354836300408226e-05, + "loss": 3.5517, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346450352897706e-05, + "loss": 3.559, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338064405387186e-05, + "loss": 3.5645, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329678457876666e-05, + "loss": 3.56, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321308889169875e-05, + "loss": 3.5552, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2312922941659355e-05, + "loss": 3.5562, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304536994148835e-05, + "loss": 3.565, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296151046638315e-05, + "loss": 3.5501, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2287765099127795e-05, + "loss": 3.5552, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227939553042101e-05, + "loss": 3.5569, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227100958291049e-05, + "loss": 3.5475, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226262363539997e-05, + "loss": 3.5441, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225423768788945e-05, + "loss": 3.5507, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224585174037893e-05, + "loss": 3.5556, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223748217167214e-05, + "loss": 3.565, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222909622416162e-05, + "loss": 3.557, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.22207102766511e-05, + "loss": 3.5474, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221232432914058e-05, + "loss": 3.5497, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220393838163006e-05, + "loss": 3.5628, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219556881292327e-05, + "loss": 3.5416, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218718286541275e-05, + "loss": 3.5564, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217879691790223e-05, + "loss": 3.5437, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170410970391716e-05, + "loss": 3.5455, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162025022881196e-05, + "loss": 3.5491, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153655454174405e-05, + "loss": 3.5667, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145269506663885e-05, + "loss": 3.5482, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2136883559153365e-05, + "loss": 3.5486, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128497611642845e-05, + "loss": 3.5523, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120128042936054e-05, + "loss": 3.5477, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2111742095425534e-05, + "loss": 3.5529, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103356147915014e-05, + "loss": 3.535, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2094970200404493e-05, + "loss": 3.5512, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.20866006316977e-05, + "loss": 3.5497, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207821468418718e-05, + "loss": 3.5565, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206982873667667e-05, + "loss": 3.5398, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206144278916615e-05, + "loss": 3.5423, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205305684165562e-05, + "loss": 3.5394, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204468727294884e-05, + "loss": 3.5347, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203630132543832e-05, + "loss": 3.5594, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202791537792779e-05, + "loss": 3.5323, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201952943041727e-05, + "loss": 3.5547, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201115986171049e-05, + "loss": 3.5486, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200277391419997e-05, + "loss": 3.5422, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199438796668944e-05, + "loss": 3.5611, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198600201917892e-05, + "loss": 3.5384, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977632450472136e-05, + "loss": 3.5405, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969246502961616e-05, + "loss": 3.5368, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1960860555451096e-05, + "loss": 3.558, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952474607940576e-05, + "loss": 3.5383, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194410503923379e-05, + "loss": 3.5376, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1935719091723265e-05, + "loss": 3.5338, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927333144212745e-05, + "loss": 3.5417, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1918947196702225e-05, + "loss": 3.5518, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910561249191705e-05, + "loss": 3.5542, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902191680484914e-05, + "loss": 3.545, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1893805732974394e-05, + "loss": 3.5548, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885419785463874e-05, + "loss": 3.564, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877033837953354e-05, + "loss": 3.5482, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186866426924657e-05, + "loss": 3.5522, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186027832173605e-05, + "loss": 3.5476, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185189237422553e-05, + "loss": 3.5479, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184350642671501e-05, + "loss": 3.5423, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183513685800822e-05, + "loss": 3.5513, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.18267509104977e-05, + "loss": 3.5481, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181836496298718e-05, + "loss": 3.5578, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180997901547666e-05, + "loss": 3.5464, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180159306796614e-05, + "loss": 3.5314, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179320712045562e-05, + "loss": 3.5403, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178483755174883e-05, + "loss": 3.5496, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177645160423831e-05, + "loss": 3.5399, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768065656727794e-05, + "loss": 3.5501, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759679709217274e-05, + "loss": 3.5456, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175131014051048e-05, + "loss": 3.5378, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174292419299996e-05, + "loss": 3.5372, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173453824548944e-05, + "loss": 3.5451, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172615229797892e-05, + "loss": 3.5477, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171778272927213e-05, + "loss": 3.5539, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170939678176161e-05, + "loss": 3.5513, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170101083425109e-05, + "loss": 3.5362, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169262488674057e-05, + "loss": 3.547, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168425531803378e-05, + "loss": 3.5438, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167586937052326e-05, + "loss": 3.5451, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166748342301275e-05, + "loss": 3.5482, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165909747550223e-05, + "loss": 3.5363, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165071152799171e-05, + "loss": 3.5498, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164234195928492e-05, + "loss": 3.5463, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.16339560117744e-05, + "loss": 3.5408, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162557006426388e-05, + "loss": 3.5385, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161718411675336e-05, + "loss": 3.5419, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608814548046566e-05, + "loss": 3.548, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600428600536046e-05, + "loss": 3.5494, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592042653025526e-05, + "loss": 3.5343, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1583656705515006e-05, + "loss": 3.5335, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575270758004486e-05, + "loss": 3.5374, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.15669011892977e-05, + "loss": 3.555, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155851524178718e-05, + "loss": 3.5427, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155012929427666e-05, + "loss": 3.5415, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154174334676614e-05, + "loss": 3.5501, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153335739925562e-05, + "loss": 3.5545, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152498783054883e-05, + "loss": 3.5484, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151660188303831e-05, + "loss": 3.5499, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150821593552779e-05, + "loss": 3.5512, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149982998801727e-05, + "loss": 3.5484, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149146041931048e-05, + "loss": 3.5327, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148307447179996e-05, + "loss": 3.5394, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147468852428944e-05, + "loss": 3.54, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146630257677892e-05, + "loss": 3.5425, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.14579166292684e-05, + "loss": 3.5432, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449547060561615e-05, + "loss": 3.5412, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441161113051095e-05, + "loss": 3.5364, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1432775165540575e-05, + "loss": 3.5421, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142438921803005e-05, + "loss": 3.5446, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416019649323264e-05, + "loss": 3.5512, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407633701812744e-05, + "loss": 3.5527, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399247754302224e-05, + "loss": 3.5346, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.13908618067917e-05, + "loss": 3.5468, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138249223808491e-05, + "loss": 3.548, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137410629057439e-05, + "loss": 3.5471, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136572034306387e-05, + "loss": 3.5391, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135733439555335e-05, + "loss": 3.5462, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134896482684657e-05, + "loss": 3.5498, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134057887933605e-05, + "loss": 3.5493, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133219293182552e-05, + "loss": 3.5383, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1323806984315e-05, + "loss": 3.5417, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131543741560822e-05, + "loss": 3.5456, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.13070514680977e-05, + "loss": 3.54, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129866552058717e-05, + "loss": 3.5334, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129027957307665e-05, + "loss": 3.5508, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128191000436987e-05, + "loss": 3.5409, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127352405685935e-05, + "loss": 3.5557, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126513810934883e-05, + "loss": 3.534, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8448638916015625, + "eval_runtime": 302.332, + "eval_samples_per_second": 1262.159, + "eval_steps_per_second": 39.443, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125675216183831e-05, + "loss": 3.5419, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124836621432779e-05, + "loss": 3.5378, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1239996645620996e-05, + "loss": 3.5399, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231610698110476e-05, + "loss": 3.5502, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223224750599956e-05, + "loss": 3.5442, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1214838803089436e-05, + "loss": 3.5475, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1206469234382645e-05, + "loss": 3.5363, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1198083286872125e-05, + "loss": 3.539, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1189697339361605e-05, + "loss": 3.5398, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181311391851085e-05, + "loss": 3.5448, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1172925444340565e-05, + "loss": 3.5379, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116455587563378e-05, + "loss": 3.5488, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115616992812326e-05, + "loss": 3.5479, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114778398061274e-05, + "loss": 3.5278, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113939803310222e-05, + "loss": 3.5309, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113102846439543e-05, + "loss": 3.5319, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112264251688491e-05, + "loss": 3.5427, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111425656937439e-05, + "loss": 3.5382, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110587062186387e-05, + "loss": 3.5337, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109750105315708e-05, + "loss": 3.5401, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108911510564656e-05, + "loss": 3.548, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108072915813604e-05, + "loss": 3.5441, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107234321062552e-05, + "loss": 3.5399, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1063973641918734e-05, + "loss": 3.5398, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055587694408214e-05, + "loss": 3.5531, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047201746897694e-05, + "loss": 3.533, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1038815799387174e-05, + "loss": 3.5405, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1030429851876654e-05, + "loss": 3.5433, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102206028316986e-05, + "loss": 3.5299, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101367433565934e-05, + "loss": 3.532, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100528838814882e-05, + "loss": 3.5317, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.09969024406383e-05, + "loss": 3.5415, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098851649312778e-05, + "loss": 3.5483, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098014692442099e-05, + "loss": 3.5406, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097176097691047e-05, + "loss": 3.5369, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096337502939995e-05, + "loss": 3.5327, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095498908188943e-05, + "loss": 3.5467, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094661951318265e-05, + "loss": 3.5296, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093823356567213e-05, + "loss": 3.5393, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092984761816161e-05, + "loss": 3.5297, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092146167065109e-05, + "loss": 3.5314, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.09130921019443e-05, + "loss": 3.5333, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0904706154433777e-05, + "loss": 3.5508, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896320206923257e-05, + "loss": 3.5296, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0887934259412736e-05, + "loss": 3.5373, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879548311902216e-05, + "loss": 3.5379, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871178743195426e-05, + "loss": 3.534, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0862792795684905e-05, + "loss": 3.5395, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854406848174385e-05, + "loss": 3.5163, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084602090066387e-05, + "loss": 3.5356, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083765133195708e-05, + "loss": 3.5399, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082926538444656e-05, + "loss": 3.5396, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082087943693604e-05, + "loss": 3.5282, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081249348942552e-05, + "loss": 3.5233, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080412392071873e-05, + "loss": 3.5289, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079573797320821e-05, + "loss": 3.5207, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078735202569769e-05, + "loss": 3.5476, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077896607818717e-05, + "loss": 3.5167, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077059650948038e-05, + "loss": 3.5357, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076221056196986e-05, + "loss": 3.5345, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075382461445934e-05, + "loss": 3.5277, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0745438666948826e-05, + "loss": 3.5428, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737052719438306e-05, + "loss": 3.5247, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0728683150731515e-05, + "loss": 3.5259, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720297203220995e-05, + "loss": 3.5238, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0711911255710475e-05, + "loss": 3.5449, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070352530819995e-05, + "loss": 3.5228, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695155739493164e-05, + "loss": 3.5238, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0686769791982644e-05, + "loss": 3.5204, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678383844472124e-05, + "loss": 3.5274, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.06699978969616e-05, + "loss": 3.5376, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066161194945108e-05, + "loss": 3.5387, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065324238074429e-05, + "loss": 3.5284, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064485643323378e-05, + "loss": 3.5364, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063647048572325e-05, + "loss": 3.5503, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062808453821273e-05, + "loss": 3.5363, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061971496950595e-05, + "loss": 3.5311, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061132902199542e-05, + "loss": 3.5343, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.06029430744849e-05, + "loss": 3.5346, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059455712697438e-05, + "loss": 3.5306, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.05861875582676e-05, + "loss": 3.5306, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057780161075707e-05, + "loss": 3.5401, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056941566324655e-05, + "loss": 3.5423, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056102971573603e-05, + "loss": 3.5363, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055264376822552e-05, + "loss": 3.5146, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544257820715e-05, + "loss": 3.5251, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0535888252008206e-05, + "loss": 3.5369, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527502304497686e-05, + "loss": 3.5259, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0519116356987166e-05, + "loss": 3.5355, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510730409476646e-05, + "loss": 3.5294, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502360840769855e-05, + "loss": 3.5259, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0493974893259335e-05, + "loss": 3.5208, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485588945748815e-05, + "loss": 3.533, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477202998238295e-05, + "loss": 3.5316, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468833429531508e-05, + "loss": 3.5392, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460447482020988e-05, + "loss": 3.5379, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452061534510468e-05, + "loss": 3.5183, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443675586999948e-05, + "loss": 3.5336, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435306018293157e-05, + "loss": 3.5278, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042692007078264e-05, + "loss": 3.5328, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041853412327212e-05, + "loss": 3.5332, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.04101481757616e-05, + "loss": 3.5233, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040176222825108e-05, + "loss": 3.531, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039339265954429e-05, + "loss": 3.5349, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038500671203377e-05, + "loss": 3.5296, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037662076452325e-05, + "loss": 3.5216, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368234817012732e-05, + "loss": 3.5264, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035986524830594e-05, + "loss": 3.5339, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035147930079542e-05, + "loss": 3.5335, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.03430933532849e-05, + "loss": 3.518, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033470740577438e-05, + "loss": 3.5225, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326337837067594e-05, + "loss": 3.5199, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0317951889557074e-05, + "loss": 3.5431, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309565942046554e-05, + "loss": 3.5273, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301179994536034e-05, + "loss": 3.5285, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0292810425829243e-05, + "loss": 3.5369, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284424478318723e-05, + "loss": 3.5407, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276038530808203e-05, + "loss": 3.5307, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267652583297686e-05, + "loss": 3.5335, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259283014590895e-05, + "loss": 3.5373, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0250897067080375e-05, + "loss": 3.5304, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242511119569855e-05, + "loss": 3.5219, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234125172059335e-05, + "loss": 3.5271, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225755603352547e-05, + "loss": 3.5215, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217369655842027e-05, + "loss": 3.528, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0208983708331507e-05, + "loss": 3.5269, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200597760820987e-05, + "loss": 3.5302, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192211813310467e-05, + "loss": 3.5227, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0183842244603676e-05, + "loss": 3.5252, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175456297093156e-05, + "loss": 3.529, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016707034958264e-05, + "loss": 3.5371, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015868440207212e-05, + "loss": 3.5387, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015031483336533e-05, + "loss": 3.5264, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014192888585481e-05, + "loss": 3.5263, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013354293834429e-05, + "loss": 3.5328, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012515699083377e-05, + "loss": 3.5314, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011677104332325e-05, + "loss": 3.5309, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010840147461646e-05, + "loss": 3.5304, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010001552710594e-05, + "loss": 3.5361, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009162957959542e-05, + "loss": 3.5319, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.00832436320849e-05, + "loss": 3.5273, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007487406337811e-05, + "loss": 3.5283, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006648811586759e-05, + "loss": 3.5307, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058102168357073e-05, + "loss": 3.5275, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049716220846553e-05, + "loss": 3.5183, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041330273336026e-05, + "loss": 3.5383, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0032960704629242e-05, + "loss": 3.5307, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024574757118722e-05, + "loss": 3.5359, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016188809608202e-05, + "loss": 3.5216, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000780286209768e-05, + "loss": 3.5276, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.846639394760132, + "eval_runtime": 302.2792, + "eval_samples_per_second": 1262.379, + "eval_steps_per_second": 39.45, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999941691458716e-05, + "loss": 3.5266, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999103096707664e-05, + "loss": 3.5232, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998264501956612e-05, + "loss": 3.5373, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997427545085933e-05, + "loss": 3.5296, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996588950334881e-05, + "loss": 3.5346, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995750355583829e-05, + "loss": 3.521, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994911760832777e-05, + "loss": 3.5297, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994074803962098e-05, + "loss": 3.5198, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993236209211046e-05, + "loss": 3.532, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992397614459994e-05, + "loss": 3.5268, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991559019708942e-05, + "loss": 3.5333, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907204249578903e-05, + "loss": 3.5301, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9898834680872112e-05, + "loss": 3.5176, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890448733361592e-05, + "loss": 3.5208, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882062785851072e-05, + "loss": 3.5124, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873676838340552e-05, + "loss": 3.5266, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865290890830032e-05, + "loss": 3.5225, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9856921322123245e-05, + "loss": 3.5242, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848535374612725e-05, + "loss": 3.521, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840149427102204e-05, + "loss": 3.5382, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831763479591684e-05, + "loss": 3.5278, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823393910884894e-05, + "loss": 3.527, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815007963374373e-05, + "loss": 3.5284, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806622015863857e-05, + "loss": 3.5349, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798236068353337e-05, + "loss": 3.5197, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9789866499646546e-05, + "loss": 3.5283, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781480552136026e-05, + "loss": 3.5239, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773094604625506e-05, + "loss": 3.5181, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764708657114986e-05, + "loss": 3.5179, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756339088408198e-05, + "loss": 3.5208, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9747953140897678e-05, + "loss": 3.5261, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739567193387158e-05, + "loss": 3.5347, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731181245876638e-05, + "loss": 3.5261, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722811677169847e-05, + "loss": 3.523, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714425729659327e-05, + "loss": 3.5213, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970603978214881e-05, + "loss": 3.5312, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969765383463829e-05, + "loss": 3.5194, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968926788712777e-05, + "loss": 3.5256, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968088193961725e-05, + "loss": 3.5117, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967251237091046e-05, + "loss": 3.5212, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966412642339994e-05, + "loss": 3.5197, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965574047588942e-05, + "loss": 3.5343, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647354528378903e-05, + "loss": 3.5172, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9638984959672112e-05, + "loss": 3.5197, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630599012161592e-05, + "loss": 3.5231, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622213064651072e-05, + "loss": 3.5182, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961382711714055e-05, + "loss": 3.5279, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605457548433764e-05, + "loss": 3.5013, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597071600923244e-05, + "loss": 3.5185, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588685653412724e-05, + "loss": 3.5263, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580299705902204e-05, + "loss": 3.5284, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9571930137195413e-05, + "loss": 3.5145, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563544189684893e-05, + "loss": 3.5052, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555158242174373e-05, + "loss": 3.5175, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546772294663856e-05, + "loss": 3.5022, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538402725957065e-05, + "loss": 3.5337, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530016778446545e-05, + "loss": 3.5055, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521630830936025e-05, + "loss": 3.5244, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513244883425505e-05, + "loss": 3.5185, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9504858935914985e-05, + "loss": 3.5139, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496489367208198e-05, + "loss": 3.5255, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488103419697678e-05, + "loss": 3.5129, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479717472187158e-05, + "loss": 3.5105, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947133152467663e-05, + "loss": 3.5092, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9462961955969847e-05, + "loss": 3.5284, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454576008459327e-05, + "loss": 3.5126, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944619006094881e-05, + "loss": 3.5115, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9437804113438283e-05, + "loss": 3.5039, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.94294345447315e-05, + "loss": 3.5113, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942104859722098e-05, + "loss": 3.524, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941266264971046e-05, + "loss": 3.5263, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404276702199936e-05, + "loss": 3.5123, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9395890754689416e-05, + "loss": 3.525, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938752118598263e-05, + "loss": 3.5356, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379135238472105e-05, + "loss": 3.5234, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370749290961585e-05, + "loss": 3.515, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362363343451065e-05, + "loss": 3.5215, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935399377474428e-05, + "loss": 3.521, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345607827233757e-05, + "loss": 3.5161, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337221879723237e-05, + "loss": 3.5194, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9328835932212717e-05, + "loss": 3.5218, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320449984702197e-05, + "loss": 3.527, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931208041599541e-05, + "loss": 3.5235, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930369446848489e-05, + "loss": 3.5003, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929530852097437e-05, + "loss": 3.5138, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928692257346385e-05, + "loss": 3.5176, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927853662595333e-05, + "loss": 3.5187, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270167057246538e-05, + "loss": 3.5178, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9261781109736018e-05, + "loss": 3.5178, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253395162225498e-05, + "loss": 3.5135, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924500921471498e-05, + "loss": 3.5039, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923662326720446e-05, + "loss": 3.5196, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922825369849767e-05, + "loss": 3.5166, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.921986775098715e-05, + "loss": 3.5236, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921148180347663e-05, + "loss": 3.5233, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920309585596611e-05, + "loss": 3.5079, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919470990845559e-05, + "loss": 3.5176, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186340339748803e-05, + "loss": 3.5187, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9177954392238283e-05, + "loss": 3.5165, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169568444727763e-05, + "loss": 3.5204, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161182497217243e-05, + "loss": 3.5116, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9152796549706723e-05, + "loss": 3.5154, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144426980999935e-05, + "loss": 3.5216, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136041033489415e-05, + "loss": 3.5157, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127655085978895e-05, + "loss": 3.5068, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119269138468375e-05, + "loss": 3.5103, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9110883190957855e-05, + "loss": 3.5233, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102513622251064e-05, + "loss": 3.515, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094127674740544e-05, + "loss": 3.5069, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085741727230027e-05, + "loss": 3.5075, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077355779719507e-05, + "loss": 3.5066, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9068986211012716e-05, + "loss": 3.5304, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060600263502196e-05, + "loss": 3.5122, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052214315991676e-05, + "loss": 3.5167, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9043828368481156e-05, + "loss": 3.5207, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903545879977437e-05, + "loss": 3.5277, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902707285226385e-05, + "loss": 3.5154, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901868690475333e-05, + "loss": 3.5202, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901030095724281e-05, + "loss": 3.5265, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900191500973229e-05, + "loss": 3.5163, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993545441025498e-05, + "loss": 3.5067, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898515949351498e-05, + "loss": 3.5109, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897677354600446e-05, + "loss": 3.5108, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896838759849394e-05, + "loss": 3.515, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896001802978715e-05, + "loss": 3.5127, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895163208227663e-05, + "loss": 3.5189, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894324613476611e-05, + "loss": 3.5069, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893486018725559e-05, + "loss": 3.5115, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926490618548802e-05, + "loss": 3.512, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918104671038282e-05, + "loss": 3.53, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909718723527762e-05, + "loss": 3.5263, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901332776017235e-05, + "loss": 3.5113, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889296320731045e-05, + "loss": 3.5118, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884577259799935e-05, + "loss": 3.517, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876191312289415e-05, + "loss": 3.5223, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8867805364778888e-05, + "loss": 3.5167, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859435796072104e-05, + "loss": 3.5181, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851049848561584e-05, + "loss": 3.5229, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842663901051064e-05, + "loss": 3.5164, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883427795354054e-05, + "loss": 3.517, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8825908384833756e-05, + "loss": 3.5141, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817522437323236e-05, + "loss": 3.5205, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880913648981271e-05, + "loss": 3.5133, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880075054230219e-05, + "loss": 3.5038, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792364594791672e-05, + "loss": 3.5217, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878399502608489e-05, + "loss": 3.519, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877560907857436e-05, + "loss": 3.5224, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876722313106384e-05, + "loss": 3.5074, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875883718355332e-05, + "loss": 3.5109, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8462326526641846, + "eval_runtime": 302.9993, + "eval_samples_per_second": 1259.379, + "eval_steps_per_second": 39.357, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750467614846537e-05, + "loss": 3.5124, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742081667336014e-05, + "loss": 3.5117, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733695719825494e-05, + "loss": 3.522, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725309772314974e-05, + "loss": 3.5135, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8716940203608183e-05, + "loss": 3.5225, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708554256097663e-05, + "loss": 3.5055, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700168308587143e-05, + "loss": 3.5153, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8691782361076626e-05, + "loss": 3.5085, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683412792369835e-05, + "loss": 3.5164, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675026844859315e-05, + "loss": 3.5158, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666640897348795e-05, + "loss": 3.5191, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658254949838275e-05, + "loss": 3.5153, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8649885381131488e-05, + "loss": 3.5049, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641499433620968e-05, + "loss": 3.5078, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633113486110448e-05, + "loss": 3.5078, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8624727538599927e-05, + "loss": 3.5043, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616341591089407e-05, + "loss": 3.5102, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8607972022382617e-05, + "loss": 3.5092, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599586074872096e-05, + "loss": 3.5098, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859120012736158e-05, + "loss": 3.526, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858281417985106e-05, + "loss": 3.5126, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857444461114427e-05, + "loss": 3.5154, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856605866363375e-05, + "loss": 3.5101, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855767271612323e-05, + "loss": 3.5262, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854928676861271e-05, + "loss": 3.4981, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.854090082110219e-05, + "loss": 3.5189, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.85325312523954e-05, + "loss": 3.5077, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852414530488488e-05, + "loss": 3.5084, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851575935737436e-05, + "loss": 3.5033, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850737340986384e-05, + "loss": 3.5027, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849900384115705e-05, + "loss": 3.5155, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849061789364653e-05, + "loss": 3.5215, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482231946136013e-05, + "loss": 3.5091, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8473845998625493e-05, + "loss": 3.5138, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465476429918702e-05, + "loss": 3.5041, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457090482408182e-05, + "loss": 3.5139, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448704534897662e-05, + "loss": 3.5069, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440318587387142e-05, + "loss": 3.5132, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8431932639876622e-05, + "loss": 3.4979, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423546692366106e-05, + "loss": 3.5091, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415177123659315e-05, + "loss": 3.5037, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8406791176148795e-05, + "loss": 3.5221, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398405228638275e-05, + "loss": 3.5016, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390019281127755e-05, + "loss": 3.5088, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381649712420967e-05, + "loss": 3.5106, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373263764910447e-05, + "loss": 3.504, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8364877817399927e-05, + "loss": 3.5143, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356491869889407e-05, + "loss": 3.4919, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348122301182616e-05, + "loss": 3.5038, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339736353672096e-05, + "loss": 3.5139, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331350406161576e-05, + "loss": 3.5108, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832296445865106e-05, + "loss": 3.5013, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831459488994427e-05, + "loss": 3.4985, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830620894243375e-05, + "loss": 3.5026, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829782299492323e-05, + "loss": 3.4923, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289437047412708e-05, + "loss": 3.515, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.828106747870592e-05, + "loss": 3.4946, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.82726815311954e-05, + "loss": 3.5052, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826429558368488e-05, + "loss": 3.5055, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825590963617436e-05, + "loss": 3.5029, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824754006746757e-05, + "loss": 3.5119, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823915411995705e-05, + "loss": 3.5037, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823076817244653e-05, + "loss": 3.496, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222382224936013e-05, + "loss": 3.4902, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8213996277425493e-05, + "loss": 3.5182, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205610329914966e-05, + "loss": 3.4995, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197224382404446e-05, + "loss": 3.4985, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8188854813697662e-05, + "loss": 3.4927, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180468866187142e-05, + "loss": 3.498, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817208291867662e-05, + "loss": 3.5059, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.81636969711661e-05, + "loss": 3.5134, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155327402459314e-05, + "loss": 3.5031, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8146941454948787e-05, + "loss": 3.5123, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138555507438267e-05, + "loss": 3.516, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813016955992775e-05, + "loss": 3.5157, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121799991220967e-05, + "loss": 3.4982, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811341404371044e-05, + "loss": 3.5118, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810502809619992e-05, + "loss": 3.5068, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.80966421486894e-05, + "loss": 3.5053, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808825620117888e-05, + "loss": 3.5036, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8079886632472092e-05, + "loss": 3.5077, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071500684961572e-05, + "loss": 3.5125, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063114737451052e-05, + "loss": 3.51, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8054728789940532e-05, + "loss": 3.4891, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804635922123374e-05, + "loss": 3.4969, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803797327372322e-05, + "loss": 3.5024, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029587326212704e-05, + "loss": 3.5086, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021201378702184e-05, + "loss": 3.5081, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8012831809995394e-05, + "loss": 3.5009, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004445862484873e-05, + "loss": 3.5073, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996059914974353e-05, + "loss": 3.4888, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7987673967463833e-05, + "loss": 3.5022, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979304398757046e-05, + "loss": 3.5063, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7970918451246526e-05, + "loss": 3.5068, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962532503736006e-05, + "loss": 3.5107, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954146556225486e-05, + "loss": 3.4984, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7945760608714966e-05, + "loss": 3.5015, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937391040008175e-05, + "loss": 3.5076, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929005092497658e-05, + "loss": 3.5061, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920619144987138e-05, + "loss": 3.5017, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912233197476618e-05, + "loss": 3.5027, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7903847249966098e-05, + "loss": 3.5, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895477681259307e-05, + "loss": 3.5092, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887091733748787e-05, + "loss": 3.506, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7878705786238267e-05, + "loss": 3.4868, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787031983872775e-05, + "loss": 3.5003, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786195027002096e-05, + "loss": 3.5097, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785356432251044e-05, + "loss": 3.5042, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784517837499992e-05, + "loss": 3.4916, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.78367924274894e-05, + "loss": 3.4968, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828422858782612e-05, + "loss": 3.4936, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820036911272092e-05, + "loss": 3.5149, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811650963761572e-05, + "loss": 3.5003, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780326501625105e-05, + "loss": 3.5042, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779489544754426e-05, + "loss": 3.505, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778650950003374e-05, + "loss": 3.518, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777812355252322e-05, + "loss": 3.5009, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.77697376050127e-05, + "loss": 3.5084, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761368036305913e-05, + "loss": 3.5116, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7752982088795393e-05, + "loss": 3.5, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744596141284873e-05, + "loss": 3.4974, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736210193774353e-05, + "loss": 3.4993, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7727824246263833e-05, + "loss": 3.4959, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719454677557045e-05, + "loss": 3.5005, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711068730046525e-05, + "loss": 3.5047, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7702682782536005e-05, + "loss": 3.5038, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694296835025485e-05, + "loss": 3.4947, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7685927266318694e-05, + "loss": 3.4975, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677541318808174e-05, + "loss": 3.4986, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669155371297654e-05, + "loss": 3.5124, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7660769423787138e-05, + "loss": 3.5147, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652399855080347e-05, + "loss": 3.5034, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644013907569827e-05, + "loss": 3.4952, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635627960059307e-05, + "loss": 3.5072, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627242012548787e-05, + "loss": 3.5051, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7618856065038267e-05, + "loss": 3.5069, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761048649633148e-05, + "loss": 3.5002, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760210054882096e-05, + "loss": 3.5096, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759371460131044e-05, + "loss": 3.5018, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758532865379992e-05, + "loss": 3.504, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7576959085093128e-05, + "loss": 3.503, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568573137582608e-05, + "loss": 3.5061, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.756018719007209e-05, + "loss": 3.5011, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755180124256157e-05, + "loss": 3.4911, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754343167385478e-05, + "loss": 3.5077, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753504572634426e-05, + "loss": 3.5082, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752665977883374e-05, + "loss": 3.5098, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751827383132322e-05, + "loss": 3.4946, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7509904262616433e-05, + "loss": 3.4955, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8490655422210693, + "eval_runtime": 302.8715, + "eval_samples_per_second": 1259.911, + "eval_steps_per_second": 39.373, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501518315105913e-05, + "loss": 3.4987, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493132367595393e-05, + "loss": 3.5, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7484746420084866e-05, + "loss": 3.5096, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476360472574346e-05, + "loss": 3.4988, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746799090386756e-05, + "loss": 3.5118, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459604956357045e-05, + "loss": 3.492, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451219008846518e-05, + "loss": 3.5031, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7442833061335998e-05, + "loss": 3.4936, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434463492629214e-05, + "loss": 3.5051, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426077545118694e-05, + "loss": 3.5026, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741769159760817e-05, + "loss": 3.5066, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740930565009765e-05, + "loss": 3.4997, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740091970258713e-05, + "loss": 3.4911, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739255013388034e-05, + "loss": 3.4954, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738416418636982e-05, + "loss": 3.4955, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.73757782388593e-05, + "loss": 3.4944, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367392291348783e-05, + "loss": 3.4954, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359022722641992e-05, + "loss": 3.4958, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350636775131472e-05, + "loss": 3.4936, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342250827620952e-05, + "loss": 3.5156, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7333864880110432e-05, + "loss": 3.5025, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325495311403644e-05, + "loss": 3.5012, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317109363893124e-05, + "loss": 3.5019, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7308723416382604e-05, + "loss": 3.5086, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300337468872084e-05, + "loss": 3.4869, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7291967900165293e-05, + "loss": 3.5021, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283581952654773e-05, + "loss": 3.5002, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275196005144253e-05, + "loss": 3.4935, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7266810057633736e-05, + "loss": 3.4887, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258440488926946e-05, + "loss": 3.4902, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250054541416425e-05, + "loss": 3.5039, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241668593905905e-05, + "loss": 3.5114, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233282646395385e-05, + "loss": 3.4971, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7224913077688598e-05, + "loss": 3.5015, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216527130178078e-05, + "loss": 3.493, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208141182667558e-05, + "loss": 3.4994, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199755235157038e-05, + "loss": 3.4918, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191385666450247e-05, + "loss": 3.5039, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7182999718939727e-05, + "loss": 3.4835, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174613771429207e-05, + "loss": 3.4963, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716622782391869e-05, + "loss": 3.4908, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.71578582552119e-05, + "loss": 3.5094, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714947230770138e-05, + "loss": 3.4938, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714108636019086e-05, + "loss": 3.4944, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713270041268034e-05, + "loss": 3.4999, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712433084397355e-05, + "loss": 3.4945, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711594489646303e-05, + "loss": 3.4993, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710755894895251e-05, + "loss": 3.4817, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709917300144199e-05, + "loss": 3.4909, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.70908034327352e-05, + "loss": 3.5009, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708241748522468e-05, + "loss": 3.4955, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707403153771416e-05, + "loss": 3.4904, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065645590203644e-05, + "loss": 3.486, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057259642693124e-05, + "loss": 3.4929, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7048890073986333e-05, + "loss": 3.4797, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040504126475813e-05, + "loss": 3.499, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032118178965293e-05, + "loss": 3.481, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7023732231454773e-05, + "loss": 3.4959, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015346283944253e-05, + "loss": 3.4973, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7006960336433733e-05, + "loss": 3.487, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998590767726945e-05, + "loss": 3.4948, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990204820216425e-05, + "loss": 3.4945, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6981818872705905e-05, + "loss": 3.4801, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973432925195385e-05, + "loss": 3.4848, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965046977684865e-05, + "loss": 3.4973, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956677408978077e-05, + "loss": 3.493, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948291461467557e-05, + "loss": 3.4888, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6939905513957037e-05, + "loss": 3.4762, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931519566446517e-05, + "loss": 3.4849, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923149997739726e-05, + "loss": 3.4965, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914764050229206e-05, + "loss": 3.5003, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906378102718686e-05, + "loss": 3.4887, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689799215520817e-05, + "loss": 3.5023, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688960620769765e-05, + "loss": 3.5037, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881220260187123e-05, + "loss": 3.5069, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687285069148034e-05, + "loss": 3.4812, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686446474396982e-05, + "loss": 3.5007, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.68560787964593e-05, + "loss": 3.4899, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6847692848948775e-05, + "loss": 3.4905, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683932328024199e-05, + "loss": 3.4952, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683093733273147e-05, + "loss": 3.4961, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822551385220944e-05, + "loss": 3.4981, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814165437710424e-05, + "loss": 3.4999, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680579586900364e-05, + "loss": 3.4764, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797409921493123e-05, + "loss": 3.4877, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789023973982596e-05, + "loss": 3.4907, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780638026472076e-05, + "loss": 3.4958, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772252078961556e-05, + "loss": 3.4975, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6763882510254772e-05, + "loss": 3.4864, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675549656274425e-05, + "loss": 3.493, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674711061523373e-05, + "loss": 3.4781, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673872466772321e-05, + "loss": 3.4906, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730355099016418e-05, + "loss": 3.4917, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6721969151505898e-05, + "loss": 3.4912, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713583203995378e-05, + "loss": 3.4955, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670519725648486e-05, + "loss": 3.4933, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669681130897434e-05, + "loss": 3.4838, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668842536146382e-05, + "loss": 3.4985, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668005579275703e-05, + "loss": 3.4916, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667166984524651e-05, + "loss": 3.4904, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666328389773599e-05, + "loss": 3.4882, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665489795022547e-05, + "loss": 3.4891, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646528381518682e-05, + "loss": 3.4957, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638142434008162e-05, + "loss": 3.4958, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6629756486497642e-05, + "loss": 3.4739, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621370538987122e-05, + "loss": 3.4862, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6612984591476602e-05, + "loss": 3.5018, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604598643966082e-05, + "loss": 3.4916, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596229075259295e-05, + "loss": 3.4785, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6587843127748775e-05, + "loss": 3.4867, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579457180238255e-05, + "loss": 3.4821, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571071232727735e-05, + "loss": 3.5006, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6562685285217215e-05, + "loss": 3.4863, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554315716510424e-05, + "loss": 3.493, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6545929768999907e-05, + "loss": 3.4964, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537543821489387e-05, + "loss": 3.5022, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529157873978867e-05, + "loss": 3.4887, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6520788305272076e-05, + "loss": 3.4993, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512402357761556e-05, + "loss": 3.5004, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504016410251036e-05, + "loss": 3.4904, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495630462740516e-05, + "loss": 3.4818, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648724451523e-05, + "loss": 3.4864, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647885856771948e-05, + "loss": 3.4842, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470488999012688e-05, + "loss": 3.489, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462103051502168e-05, + "loss": 3.49, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6453717103991648e-05, + "loss": 3.4947, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445331156481128e-05, + "loss": 3.4827, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643696158777434e-05, + "loss": 3.4829, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642857564026382e-05, + "loss": 3.4867, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.64201896927533e-05, + "loss": 3.5018, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641180374524278e-05, + "loss": 3.5022, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403417797732254e-05, + "loss": 3.4939, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639504822902547e-05, + "loss": 3.4839, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638666228151495e-05, + "loss": 3.4926, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378276334004433e-05, + "loss": 3.4965, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6369890386493906e-05, + "loss": 3.4903, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361520817787122e-05, + "loss": 3.488, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353134870276602e-05, + "loss": 3.4972, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634474892276608e-05, + "loss": 3.4909, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633636297525556e-05, + "loss": 3.4966, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6327993406548774e-05, + "loss": 3.4858, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319607459038254e-05, + "loss": 3.4957, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311221511527727e-05, + "loss": 3.4892, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6302835564017207e-05, + "loss": 3.4779, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294465995310423e-05, + "loss": 3.4941, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286080047799903e-05, + "loss": 3.497, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627769410028938e-05, + "loss": 3.4945, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626930815277886e-05, + "loss": 3.4851, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626092220526834e-05, + "loss": 3.4793, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8501148223876953, + "eval_runtime": 303.1476, + "eval_samples_per_second": 1258.763, + "eval_steps_per_second": 39.337, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252552636561552e-05, + "loss": 3.4944, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244166689051032e-05, + "loss": 3.4875, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6235780741540512e-05, + "loss": 3.4961, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227394794029992e-05, + "loss": 3.4827, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.62190252253232e-05, + "loss": 3.5065, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621063927781268e-05, + "loss": 3.4762, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620225333030216e-05, + "loss": 3.4942, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619386738279164e-05, + "loss": 3.4805, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185497814084853e-05, + "loss": 3.4962, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177111866574333e-05, + "loss": 3.4916, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6168725919063813e-05, + "loss": 3.4876, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160339971553293e-05, + "loss": 3.4917, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6151970402846502e-05, + "loss": 3.4773, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143584455335986e-05, + "loss": 3.4819, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135198507825466e-05, + "loss": 3.4847, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6126812560314946e-05, + "loss": 3.4822, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118426612804426e-05, + "loss": 3.4841, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110057044097635e-05, + "loss": 3.4825, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101671096587115e-05, + "loss": 3.4864, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093285149076595e-05, + "loss": 3.5018, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6084899201566078e-05, + "loss": 3.4895, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076529632859287e-05, + "loss": 3.4894, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068143685348767e-05, + "loss": 3.4921, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6059757737838247e-05, + "loss": 3.495, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051371790327727e-05, + "loss": 3.4763, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6042985842817207e-05, + "loss": 3.4978, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603461627411042e-05, + "loss": 3.4827, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.60262303265999e-05, + "loss": 3.4827, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601784437908938e-05, + "loss": 3.4758, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600945843157886e-05, + "loss": 3.4815, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001088862872068e-05, + "loss": 3.4875, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5992702915361548e-05, + "loss": 3.4975, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598431696785103e-05, + "loss": 3.4881, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597593102034051e-05, + "loss": 3.4895, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596756145163372e-05, + "loss": 3.4759, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.59591755041232e-05, + "loss": 3.4897, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595078955661268e-05, + "loss": 3.4751, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594240360910216e-05, + "loss": 3.4935, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593401766159164e-05, + "loss": 3.4709, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925648092884853e-05, + "loss": 3.4837, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917262145374333e-05, + "loss": 3.4794, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5908876197863813e-05, + "loss": 3.4977, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900490250353293e-05, + "loss": 3.4844, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892120681646502e-05, + "loss": 3.4805, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5883734734135985e-05, + "loss": 3.4851, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875348786625465e-05, + "loss": 3.484, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5866962839114945e-05, + "loss": 3.486, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858593270408154e-05, + "loss": 3.4738, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850207322897634e-05, + "loss": 3.4722, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5841821375387114e-05, + "loss": 3.4899, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833435427876594e-05, + "loss": 3.4812, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825065859169807e-05, + "loss": 3.4766, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5816679911659287e-05, + "loss": 3.4762, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808293964148767e-05, + "loss": 3.48, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5799908016638246e-05, + "loss": 3.4667, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791538447931456e-05, + "loss": 3.4879, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578315250042094e-05, + "loss": 3.4683, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577476655291042e-05, + "loss": 3.4844, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.57663806053999e-05, + "loss": 3.4809, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575799465788938e-05, + "loss": 3.4836, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5749625089182588e-05, + "loss": 3.4778, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741239141672068e-05, + "loss": 3.487, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5732853194161548e-05, + "loss": 3.4678, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572446724665103e-05, + "loss": 3.4742, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571609767794424e-05, + "loss": 3.4846, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570771173043372e-05, + "loss": 3.482, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.56993257829232e-05, + "loss": 3.4719, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569093983541268e-05, + "loss": 3.4686, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682570266705893e-05, + "loss": 3.472, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674184319195373e-05, + "loss": 3.48, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5665798371684852e-05, + "loss": 3.489, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657412424174332e-05, + "loss": 3.4762, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564904285546754e-05, + "loss": 3.4913, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564065690795702e-05, + "loss": 3.4909, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.56322709604465e-05, + "loss": 3.4993, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.562388501293598e-05, + "loss": 3.467, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615515444229194e-05, + "loss": 3.4867, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607129496718674e-05, + "loss": 3.4859, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5598743549208154e-05, + "loss": 3.4741, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559035760169763e-05, + "loss": 3.4851, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5581988032990846e-05, + "loss": 3.4876, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573602085480326e-05, + "loss": 3.4888, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565216137969806e-05, + "loss": 3.4819, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555683019045928e-05, + "loss": 3.4704, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548460621752495e-05, + "loss": 3.4727, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540074674241975e-05, + "loss": 3.4781, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5531688726731455e-05, + "loss": 3.4843, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552330277922093e-05, + "loss": 3.4872, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551491683171041e-05, + "loss": 3.4724, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5506547263003628e-05, + "loss": 3.4819, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.54981613154931e-05, + "loss": 3.4677, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5489775367982584e-05, + "loss": 3.4765, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481389420472064e-05, + "loss": 3.4792, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547301985176528e-05, + "loss": 3.4774, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464633904254753e-05, + "loss": 3.4882, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456247956744233e-05, + "loss": 3.4805, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5447862009233713e-05, + "loss": 3.4742, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543949244052693e-05, + "loss": 3.4856, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431106493016405e-05, + "loss": 3.4809, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5422720545505885e-05, + "loss": 3.4819, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414334597995365e-05, + "loss": 3.4715, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5405965029288574e-05, + "loss": 3.4771, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397579081778054e-05, + "loss": 3.4819, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389193134267534e-05, + "loss": 3.4846, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5380807186757018e-05, + "loss": 3.4646, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372437618050227e-05, + "loss": 3.47, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364051670539707e-05, + "loss": 3.4875, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5355665723029187e-05, + "loss": 3.4803, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347279775518667e-05, + "loss": 3.467, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533891020681188e-05, + "loss": 3.4704, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533052425930136e-05, + "loss": 3.4751, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532213831179084e-05, + "loss": 3.4845, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531375236428032e-05, + "loss": 3.4759, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.53053664167698e-05, + "loss": 3.4761, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5296996848063008e-05, + "loss": 3.483, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288610900552488e-05, + "loss": 3.4904, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528022495304197e-05, + "loss": 3.484, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527183900553145e-05, + "loss": 3.4797, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526346943682466e-05, + "loss": 3.4918, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525508348931414e-05, + "loss": 3.4775, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524669754180362e-05, + "loss": 3.4679, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238327973096833e-05, + "loss": 3.4753, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5229942025586313e-05, + "loss": 3.4734, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221556078075793e-05, + "loss": 3.4791, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213170130565273e-05, + "loss": 3.4739, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5204784183054753e-05, + "loss": 3.4834, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196414614347962e-05, + "loss": 3.4707, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518802866683744e-05, + "loss": 3.4706, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179642719326925e-05, + "loss": 3.4733, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171273150620134e-05, + "loss": 3.4922, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5162887203109614e-05, + "loss": 3.4837, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154501255599094e-05, + "loss": 3.4851, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146115308088574e-05, + "loss": 3.4722, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5137729360578054e-05, + "loss": 3.4846, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129359791871266e-05, + "loss": 3.4852, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5120973844360746e-05, + "loss": 3.4765, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5112587896850226e-05, + "loss": 3.4739, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104201949339706e-05, + "loss": 3.4837, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5095832380632915e-05, + "loss": 3.4792, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087446433122395e-05, + "loss": 3.4876, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507906048561188e-05, + "loss": 3.4721, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507067453810136e-05, + "loss": 3.4863, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062304969394568e-05, + "loss": 3.4742, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5053919021884048e-05, + "loss": 3.4715, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045533074373528e-05, + "loss": 3.4793, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037147126863008e-05, + "loss": 3.4875, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502877755815622e-05, + "loss": 3.4826, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.50203916106457e-05, + "loss": 3.4697, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501200566313518e-05, + "loss": 3.4726, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8517138957977295, + "eval_runtime": 304.5199, + "eval_samples_per_second": 1253.091, + "eval_steps_per_second": 39.16, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500361971562466e-05, + "loss": 3.4758, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499523376811414e-05, + "loss": 3.4768, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4986847820603616e-05, + "loss": 3.4811, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978461873093096e-05, + "loss": 3.4748, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970092304386312e-05, + "loss": 3.4915, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961706356875792e-05, + "loss": 3.4696, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495332040936527e-05, + "loss": 3.4784, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494493446185475e-05, + "loss": 3.4672, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493656489314796e-05, + "loss": 3.4818, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492817894563744e-05, + "loss": 3.4797, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.491979299812692e-05, + "loss": 3.4751, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.49114070506164e-05, + "loss": 3.4787, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490302110310588e-05, + "loss": 3.4651, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489465153439909e-05, + "loss": 3.4713, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488626558688857e-05, + "loss": 3.4743, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487787963937805e-05, + "loss": 3.469, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869493691867533e-05, + "loss": 3.4732, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861124123160743e-05, + "loss": 3.4696, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852738175650222e-05, + "loss": 3.4745, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844352228139702e-05, + "loss": 3.4866, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4835966280629182e-05, + "loss": 3.4802, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827596711922395e-05, + "loss": 3.4778, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819210764411875e-05, + "loss": 3.4807, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4810824816901355e-05, + "loss": 3.4823, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802438869390835e-05, + "loss": 3.4654, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794069300684044e-05, + "loss": 3.4861, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4785683353173524e-05, + "loss": 3.4721, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777297405663004e-05, + "loss": 3.4681, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4768911458152487e-05, + "loss": 3.4652, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760541889445696e-05, + "loss": 3.4731, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752155941935176e-05, + "loss": 3.4759, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4743769994424656e-05, + "loss": 3.4859, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735384046914136e-05, + "loss": 3.4755, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4726998099403616e-05, + "loss": 3.4773, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471862853069683e-05, + "loss": 3.4661, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471024258318631e-05, + "loss": 3.4763, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470185663567579e-05, + "loss": 3.4711, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469347068816527e-05, + "loss": 3.4769, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685101119458477e-05, + "loss": 3.46, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676715171947957e-05, + "loss": 3.4709, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.466832922443744e-05, + "loss": 3.4699, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.465994327692692e-05, + "loss": 3.4851, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465157370822013e-05, + "loss": 3.4758, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464318776070961e-05, + "loss": 3.4691, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463480181319909e-05, + "loss": 3.4718, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462641586568857e-05, + "loss": 3.4706, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461802991817805e-05, + "loss": 3.4785, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609660349471262e-05, + "loss": 3.4646, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601274401960742e-05, + "loss": 3.4586, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459288845445022e-05, + "loss": 3.4792, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.45845025069397e-05, + "loss": 3.4704, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457613293823291e-05, + "loss": 3.467, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4567746990722394e-05, + "loss": 3.465, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.455936104321187e-05, + "loss": 3.4676, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455097509570135e-05, + "loss": 3.4543, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542605526994563e-05, + "loss": 3.4729, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534219579484043e-05, + "loss": 3.4583, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452583363197352e-05, + "loss": 3.4697, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517447684463003e-05, + "loss": 3.4726, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509061736952483e-05, + "loss": 3.469, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500692168245692e-05, + "loss": 3.4693, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492306220735172e-05, + "loss": 3.4777, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4483920273224652e-05, + "loss": 3.4576, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475534325714132e-05, + "loss": 3.4596, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467164757007345e-05, + "loss": 3.4733, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4458778809496825e-05, + "loss": 3.4682, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450392861986305e-05, + "loss": 3.4641, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442006914475785e-05, + "loss": 3.4555, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4433637345768994e-05, + "loss": 3.4599, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425251398258474e-05, + "loss": 3.468, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4416865450747957e-05, + "loss": 3.4759, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408479503237437e-05, + "loss": 3.4674, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400109934530646e-05, + "loss": 3.4773, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4391723987020126e-05, + "loss": 3.4761, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383338039509606e-05, + "loss": 3.4911, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4374952091999086e-05, + "loss": 3.4574, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.43665825232923e-05, + "loss": 3.4709, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435819657578178e-05, + "loss": 3.4759, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4349810628271258e-05, + "loss": 3.4572, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341424680760738e-05, + "loss": 3.4753, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333055112053947e-05, + "loss": 3.4742, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324669164543427e-05, + "loss": 3.4746, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431628321703291e-05, + "loss": 3.4724, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430789726952239e-05, + "loss": 3.4585, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.42995277008156e-05, + "loss": 3.4599, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429114175330508e-05, + "loss": 3.4677, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428275580579456e-05, + "loss": 3.4684, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427436985828404e-05, + "loss": 3.4761, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.426598391077352e-05, + "loss": 3.4614, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257614342066732e-05, + "loss": 3.4677, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249228394556212e-05, + "loss": 3.4569, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4240842447045692e-05, + "loss": 3.465, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423245649953517e-05, + "loss": 3.468, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422408693082838e-05, + "loss": 3.4699, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215700983317864e-05, + "loss": 3.4763, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207315035807344e-05, + "loss": 3.4653, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419892908829682e-05, + "loss": 3.4653, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.41905431407863e-05, + "loss": 3.4711, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182173572079513e-05, + "loss": 3.4661, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4173787624568993e-05, + "loss": 3.474, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165401677058473e-05, + "loss": 3.4612, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157015729547953e-05, + "loss": 3.4659, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148646160841166e-05, + "loss": 3.4689, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140260213330642e-05, + "loss": 3.4769, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4131874265820122e-05, + "loss": 3.4531, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123488318309602e-05, + "loss": 3.4649, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115118749602818e-05, + "loss": 3.473, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4106732802092295e-05, + "loss": 3.4682, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098346854581774e-05, + "loss": 3.4528, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4089960907071254e-05, + "loss": 3.4647, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081591338364467e-05, + "loss": 3.46, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073205390853944e-05, + "loss": 3.4771, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4064819443343427e-05, + "loss": 3.4626, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056433495832907e-05, + "loss": 3.4609, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048063927126116e-05, + "loss": 3.4751, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4039677979615596e-05, + "loss": 3.4816, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031292032105076e-05, + "loss": 3.4705, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4022906084594556e-05, + "loss": 3.4709, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014536515887768e-05, + "loss": 3.4737, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006150568377248e-05, + "loss": 3.4677, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3997764620866728e-05, + "loss": 3.4603, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989378673356208e-05, + "loss": 3.4688, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3980992725845688e-05, + "loss": 3.4597, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972623157138897e-05, + "loss": 3.467, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396423720962838e-05, + "loss": 3.4626, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395585126211786e-05, + "loss": 3.4714, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394746531460734e-05, + "loss": 3.4603, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393909574590055e-05, + "loss": 3.458, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393070979839003e-05, + "loss": 3.4662, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392232385087951e-05, + "loss": 3.4729, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391393790336899e-05, + "loss": 3.4744, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905568334662202e-05, + "loss": 3.4766, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897182387151682e-05, + "loss": 3.4594, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3888796439641162e-05, + "loss": 3.4744, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880410492130642e-05, + "loss": 3.4715, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387202454462012e-05, + "loss": 3.4704, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863654975913334e-05, + "loss": 3.4599, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855269028402814e-05, + "loss": 3.4752, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3846883080892294e-05, + "loss": 3.4656, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383849713338177e-05, + "loss": 3.4766, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830127564674983e-05, + "loss": 3.4547, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3821741617164463e-05, + "loss": 3.4793, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813355669653943e-05, + "loss": 3.4598, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3804969722143423e-05, + "loss": 3.4611, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796600153436635e-05, + "loss": 3.4692, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788214205926115e-05, + "loss": 3.4718, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3779828258415592e-05, + "loss": 3.4732, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771442310905072e-05, + "loss": 3.4541, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763056363394552e-05, + "loss": 3.467, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8533527851104736, + "eval_runtime": 304.9802, + "eval_samples_per_second": 1251.199, + "eval_steps_per_second": 39.101, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3754686794687768e-05, + "loss": 3.4672, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746300847177244e-05, + "loss": 3.4672, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3737914899666724e-05, + "loss": 3.4705, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729528952156204e-05, + "loss": 3.4632, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721159383449417e-05, + "loss": 3.4794, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3712773435938897e-05, + "loss": 3.4606, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704387488428377e-05, + "loss": 3.4622, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696001540917857e-05, + "loss": 3.4605, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687631972211066e-05, + "loss": 3.4685, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679246024700546e-05, + "loss": 3.4699, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3670860077190026e-05, + "loss": 3.4638, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662474129679506e-05, + "loss": 3.4692, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365408818216899e-05, + "loss": 3.456, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3645718613462198e-05, + "loss": 3.459, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637332665951678e-05, + "loss": 3.4655, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3628946718441158e-05, + "loss": 3.4553, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620560770930638e-05, + "loss": 3.4625, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361219120222385e-05, + "loss": 3.455, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.360380525471333e-05, + "loss": 3.46, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.359541930720281e-05, + "loss": 3.4796, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358703335969229e-05, + "loss": 3.4662, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.35786637909855e-05, + "loss": 3.4724, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357027784347498e-05, + "loss": 3.4655, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356189189596446e-05, + "loss": 3.47, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553505948453943e-05, + "loss": 3.4522, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545136379747152e-05, + "loss": 3.4756, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.353675043223663e-05, + "loss": 3.4636, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352836448472611e-05, + "loss": 3.4553, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.351997853721559e-05, + "loss": 3.455, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511608968508804e-05, + "loss": 3.4587, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503223020998284e-05, + "loss": 3.4663, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3494837073487764e-05, + "loss": 3.4718, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486451125977244e-05, + "loss": 3.4696, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478081557270453e-05, + "loss": 3.4643, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3469695609759933e-05, + "loss": 3.4539, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461309662249413e-05, + "loss": 3.4629, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3452923714738896e-05, + "loss": 3.4603, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444554146032105e-05, + "loss": 3.4643, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436168198521585e-05, + "loss": 3.4536, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3427782251011065e-05, + "loss": 3.4561, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419396303500545e-05, + "loss": 3.4592, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411026734793758e-05, + "loss": 3.4724, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3402640787283238e-05, + "loss": 3.4646, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394254839772718e-05, + "loss": 3.4563, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3385868892262194e-05, + "loss": 3.4629, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377499323555407e-05, + "loss": 3.4574, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369113376044887e-05, + "loss": 3.465, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3360727428534367e-05, + "loss": 3.4547, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352341481023847e-05, + "loss": 3.4452, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334397191231706e-05, + "loss": 3.4654, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333558596480654e-05, + "loss": 3.4614, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332720001729602e-05, + "loss": 3.4554, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3318814069785496e-05, + "loss": 3.4567, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310428122274975e-05, + "loss": 3.4545, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330205855356819e-05, + "loss": 3.4449, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3293672606057668e-05, + "loss": 3.4572, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285286658547148e-05, + "loss": 3.4498, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3276900711036628e-05, + "loss": 3.4578, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.326853114232984e-05, + "loss": 3.4646, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.326014519481932e-05, + "loss": 3.4528, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.32517592473088e-05, + "loss": 3.4576, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.324337329979828e-05, + "loss": 3.4669, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323498735228776e-05, + "loss": 3.4473, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322661778358097e-05, + "loss": 3.4455, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321823183607045e-05, + "loss": 3.4589, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.320984588855993e-05, + "loss": 3.4589, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.320147631985314e-05, + "loss": 3.4488, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319309037234262e-05, + "loss": 3.4477, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.31847044248321e-05, + "loss": 3.447, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317631847732158e-05, + "loss": 3.4561, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316794890861479e-05, + "loss": 3.4627, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159562961104274e-05, + "loss": 3.4569, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151177013593754e-05, + "loss": 3.4663, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3142791066083234e-05, + "loss": 3.461, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134405118572714e-05, + "loss": 3.4862, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126035549865923e-05, + "loss": 3.4483, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3117649602355403e-05, + "loss": 3.4593, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109263654844883e-05, + "loss": 3.4654, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3100877707334366e-05, + "loss": 3.4473, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092508138627575e-05, + "loss": 3.4665, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084122191117055e-05, + "loss": 3.4627, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3075736243606535e-05, + "loss": 3.4601, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067350296096015e-05, + "loss": 3.4607, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3058980727389228e-05, + "loss": 3.4457, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3050594779878708e-05, + "loss": 3.4548, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042208832368188e-05, + "loss": 3.4506, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3033822884857667e-05, + "loss": 3.4597, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025453316150877e-05, + "loss": 3.4651, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017067368640357e-05, + "loss": 3.4478, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008681421129836e-05, + "loss": 3.4583, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.300029547361932e-05, + "loss": 3.4483, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299192590491253e-05, + "loss": 3.4507, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298353995740201e-05, + "loss": 3.4523, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297515400989149e-05, + "loss": 3.4642, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296676806238097e-05, + "loss": 3.4669, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295839849367418e-05, + "loss": 3.4517, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295001254616366e-05, + "loss": 3.4494, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.294162659865314e-05, + "loss": 3.4624, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933240651142618e-05, + "loss": 3.4524, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292487108243583e-05, + "loss": 3.4648, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291648513492531e-05, + "loss": 3.4506, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.290809918741479e-05, + "loss": 3.4559, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.289971323990427e-05, + "loss": 3.4604, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.289132729239375e-05, + "loss": 3.4629, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2882957723686963e-05, + "loss": 3.4425, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874571776176442e-05, + "loss": 3.4538, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286618582866592e-05, + "loss": 3.4583, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.28577998811554e-05, + "loss": 3.4608, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849430312448615e-05, + "loss": 3.4407, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284104436493809e-05, + "loss": 3.461, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283265841742757e-05, + "loss": 3.4456, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282427246991705e-05, + "loss": 3.4607, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2815902901210264e-05, + "loss": 3.4559, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2807516953699744e-05, + "loss": 3.4514, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799147384992956e-05, + "loss": 3.4621, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2790761437482436e-05, + "loss": 3.4722, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782375489971916e-05, + "loss": 3.4564, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2773989542461393e-05, + "loss": 3.461, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2765603594950873e-05, + "loss": 3.4627, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757217647440353e-05, + "loss": 3.4562, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2748831699929836e-05, + "loss": 3.4472, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740445752419316e-05, + "loss": 3.4528, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732076183712525e-05, + "loss": 3.4526, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2723690236202005e-05, + "loss": 3.4567, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715304288691485e-05, + "loss": 3.4567, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2706918341180965e-05, + "loss": 3.4555, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698548772474177e-05, + "loss": 3.4512, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690162824963657e-05, + "loss": 3.444, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2681776877453137e-05, + "loss": 3.4559, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673390929942617e-05, + "loss": 3.4629, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665021361235826e-05, + "loss": 3.4591, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656635413725306e-05, + "loss": 3.4643, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264824946621479e-05, + "loss": 3.4456, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.263986351870427e-05, + "loss": 3.4669, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263149394999748e-05, + "loss": 3.4597, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262310800248696e-05, + "loss": 3.4567, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261472205497644e-05, + "loss": 3.4534, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.260633610746592e-05, + "loss": 3.4598, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.25979501599554e-05, + "loss": 3.4542, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.258958059124861e-05, + "loss": 3.4701, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258119464373809e-05, + "loss": 3.442, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2572808696227568e-05, + "loss": 3.4655, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564422748717048e-05, + "loss": 3.4479, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255605318001026e-05, + "loss": 3.4549, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2547667232499743e-05, + "loss": 3.4569, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.253928128498922e-05, + "loss": 3.4549, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.25308953374787e-05, + "loss": 3.468, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522525768771912e-05, + "loss": 3.4385, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514139821261392e-05, + "loss": 3.4575, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.854790687561035, + "eval_runtime": 303.613, + "eval_samples_per_second": 1256.834, + "eval_steps_per_second": 39.277, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250575387375087e-05, + "loss": 3.4544, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497367926240352e-05, + "loss": 3.4518, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2488981978729832e-05, + "loss": 3.4588, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2480596031219312e-05, + "loss": 3.4545, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.247222646251252e-05, + "loss": 3.4648, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2463840515002e-05, + "loss": 3.4493, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245545456749148e-05, + "loss": 3.4485, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244706861998096e-05, + "loss": 3.4519, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2438699051274174e-05, + "loss": 3.4568, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430313103763654e-05, + "loss": 3.4571, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2421927156253134e-05, + "loss": 3.4561, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413541208742613e-05, + "loss": 3.4547, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405171640035823e-05, + "loss": 3.4482, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2396785692525306e-05, + "loss": 3.4456, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388399745014786e-05, + "loss": 3.4543, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380013797504266e-05, + "loss": 3.4447, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2371644228797475e-05, + "loss": 3.4504, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363258281286955e-05, + "loss": 3.4455, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2354872333776435e-05, + "loss": 3.4486, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346486386265915e-05, + "loss": 3.4674, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338116817559127e-05, + "loss": 3.4576, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2329730870048607e-05, + "loss": 3.4591, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321344922538087e-05, + "loss": 3.4532, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2312958975027567e-05, + "loss": 3.4595, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304589406320776e-05, + "loss": 3.4426, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.229620345881026e-05, + "loss": 3.4645, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228781751129974e-05, + "loss": 3.4505, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227943156378922e-05, + "loss": 3.4432, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227106199508243e-05, + "loss": 3.4457, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226267604757191e-05, + "loss": 3.4494, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225429010006139e-05, + "loss": 3.4529, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224590415255087e-05, + "loss": 3.4623, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223753458384408e-05, + "loss": 3.457, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222914863633356e-05, + "loss": 3.4565, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222076268882304e-05, + "loss": 3.4411, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221237674131252e-05, + "loss": 3.4547, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220400717260573e-05, + "loss": 3.4532, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2195621225095213e-05, + "loss": 3.4461, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187235277584693e-05, + "loss": 3.4454, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217884933007417e-05, + "loss": 3.4426, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170479761367382e-05, + "loss": 3.4491, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162093813856862e-05, + "loss": 3.46, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2153707866346342e-05, + "loss": 3.4547, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145321918835822e-05, + "loss": 3.4453, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2136935971325302e-05, + "loss": 3.453, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128566402618515e-05, + "loss": 3.4452, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120180455107995e-05, + "loss": 3.4564, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211179450759747e-05, + "loss": 3.4438, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210340856008695e-05, + "loss": 3.4302, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095038991380167e-05, + "loss": 3.4546, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2086653043869643e-05, + "loss": 3.4503, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078267096359123e-05, + "loss": 3.4477, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2069881148848603e-05, + "loss": 3.4448, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061511580141816e-05, + "loss": 3.4401, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053125632631292e-05, + "loss": 3.4362, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2044739685120776e-05, + "loss": 3.4454, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036353737610256e-05, + "loss": 3.4408, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2027984168903468e-05, + "loss": 3.4492, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019598221392945e-05, + "loss": 3.4498, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011212273882425e-05, + "loss": 3.4435, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2002826326371905e-05, + "loss": 3.4445, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994456757665117e-05, + "loss": 3.4614, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986070810154597e-05, + "loss": 3.4335, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1977684862644077e-05, + "loss": 3.4349, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969298915133557e-05, + "loss": 3.4488, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1960929346426766e-05, + "loss": 3.4505, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952543398916246e-05, + "loss": 3.438, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.194415745140573e-05, + "loss": 3.4359, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.193578788269894e-05, + "loss": 3.4373, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192740193518842e-05, + "loss": 3.4426, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.19190159876779e-05, + "loss": 3.4563, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191063004016738e-05, + "loss": 3.4456, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190226047146059e-05, + "loss": 3.4508, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.189387452395007e-05, + "loss": 3.4538, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.188548857643955e-05, + "loss": 3.4695, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187710262892903e-05, + "loss": 3.4401, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186873306022224e-05, + "loss": 3.4498, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186034711271172e-05, + "loss": 3.453, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.18519611652012e-05, + "loss": 3.4368, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843575217690683e-05, + "loss": 3.4536, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835205648983892e-05, + "loss": 3.4517, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1826819701473372e-05, + "loss": 3.4504, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818433753962852e-05, + "loss": 3.4505, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810047806452332e-05, + "loss": 3.4342, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1801678237745545e-05, + "loss": 3.442, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793292290235025e-05, + "loss": 3.4434, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1784906342724504e-05, + "loss": 3.4466, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776520395213984e-05, + "loss": 3.455, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768134447703464e-05, + "loss": 3.4386, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1759764878996673e-05, + "loss": 3.4469, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751378931486153e-05, + "loss": 3.4396, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1742992983975637e-05, + "loss": 3.438, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1734607036465117e-05, + "loss": 3.4452, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726237467758326e-05, + "loss": 3.4492, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1717851520247806e-05, + "loss": 3.4568, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709465572737286e-05, + "loss": 3.4447, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701079625226766e-05, + "loss": 3.4391, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1692710056519978e-05, + "loss": 3.4513, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684324109009458e-05, + "loss": 3.4419, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1675938161498938e-05, + "loss": 3.4495, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667552213988418e-05, + "loss": 3.4427, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659182645281627e-05, + "loss": 3.4423, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1650796697771107e-05, + "loss": 3.4481, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164241075026059e-05, + "loss": 3.4565, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634024802750067e-05, + "loss": 3.4267, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162565523404328e-05, + "loss": 3.4445, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161726928653276e-05, + "loss": 3.4447, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160888333902224e-05, + "loss": 3.4512, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600497391511716e-05, + "loss": 3.4279, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592127822804932e-05, + "loss": 3.4453, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1583741875294412e-05, + "loss": 3.4416, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575355927783892e-05, + "loss": 3.4456, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156696998027337e-05, + "loss": 3.4491, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155860041156658e-05, + "loss": 3.4407, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155021446405606e-05, + "loss": 3.4463, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154182851654554e-05, + "loss": 3.4635, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153344256903502e-05, + "loss": 3.4469, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525073000328233e-05, + "loss": 3.4456, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1516687052817713e-05, + "loss": 3.4542, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150830110530719e-05, + "loss": 3.4452, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.149991515779667e-05, + "loss": 3.4313, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491529210286153e-05, + "loss": 3.4464, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483159641579365e-05, + "loss": 3.4388, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1474773694068842e-05, + "loss": 3.4439, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466387746558322e-05, + "loss": 3.4459, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458018177851534e-05, + "loss": 3.4452, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1449632230341014e-05, + "loss": 3.443, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441246282830494e-05, + "loss": 3.436, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1432860335319974e-05, + "loss": 3.4429, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424474387809454e-05, + "loss": 3.453, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416104819102663e-05, + "loss": 3.4458, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1407718871592143e-05, + "loss": 3.4537, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399332924081623e-05, + "loss": 3.4342, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1390946976571107e-05, + "loss": 3.4602, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382577407864316e-05, + "loss": 3.4452, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374191460353796e-05, + "loss": 3.446, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1365805512843276e-05, + "loss": 3.443, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357419565332756e-05, + "loss": 3.4483, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349049996625968e-05, + "loss": 3.4407, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1340664049115448e-05, + "loss": 3.4625, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332278101604928e-05, + "loss": 3.4302, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1323892154094408e-05, + "loss": 3.4508, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315522585387617e-05, + "loss": 3.4401, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307136637877097e-05, + "loss": 3.4447, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1298750690366577e-05, + "loss": 3.4431, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.129036474285606e-05, + "loss": 3.4425, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.128199517414927e-05, + "loss": 3.4595, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127360922663875e-05, + "loss": 3.4325, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126522327912823e-05, + "loss": 3.4476, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8551995754241943, + "eval_runtime": 305.7386, + "eval_samples_per_second": 1248.096, + "eval_steps_per_second": 39.004, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.125683733161771e-05, + "loss": 3.4456, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248467762910922e-05, + "loss": 3.44, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240081815400402e-05, + "loss": 3.4471, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.123169586788988e-05, + "loss": 3.4456, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122330992037936e-05, + "loss": 3.4528, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121494035167257e-05, + "loss": 3.4382, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120655440416205e-05, + "loss": 3.4433, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119816845665153e-05, + "loss": 3.4373, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1189782509141014e-05, + "loss": 3.4484, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181412940434223e-05, + "loss": 3.4472, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173026992923703e-05, + "loss": 3.4449, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1164641045413183e-05, + "loss": 3.4414, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1156255097902663e-05, + "loss": 3.4387, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1147885529195875e-05, + "loss": 3.4342, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1139499581685355e-05, + "loss": 3.4459, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131113634174835e-05, + "loss": 3.4328, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1122727686664315e-05, + "loss": 3.4389, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114341739153792e-05, + "loss": 3.438, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1105972170447004e-05, + "loss": 3.4356, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1097586222936484e-05, + "loss": 3.4521, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089200275425964e-05, + "loss": 3.4513, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1080830706719177e-05, + "loss": 3.4501, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072444759208657e-05, + "loss": 3.4441, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064058811698137e-05, + "loss": 3.4454, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1055672864187613e-05, + "loss": 3.4321, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104730329548083e-05, + "loss": 3.4556, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.103891734797031e-05, + "loss": 3.4377, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.103053140045979e-05, + "loss": 3.434, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022145452949266e-05, + "loss": 3.435, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1013759505438746e-05, + "loss": 3.4387, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005389936731958e-05, + "loss": 3.4407, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997003989221438e-05, + "loss": 3.4492, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0988618041710918e-05, + "loss": 3.4478, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980232094200398e-05, + "loss": 3.4394, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.097186252549361e-05, + "loss": 3.4316, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963476577983087e-05, + "loss": 3.446, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955090630472567e-05, + "loss": 3.4424, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0946704682962047e-05, + "loss": 3.4341, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938335114255263e-05, + "loss": 3.4364, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.092994916674474e-05, + "loss": 3.4318, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.092156321923422e-05, + "loss": 3.4352, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.09131772717237e-05, + "loss": 3.449, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0904807703016908e-05, + "loss": 3.4446, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089642175550639e-05, + "loss": 3.4342, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088803580799587e-05, + "loss": 3.4404, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.087964986048535e-05, + "loss": 3.4348, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.087128029177856e-05, + "loss": 3.446, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086289434426804e-05, + "loss": 3.4354, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085450839675752e-05, + "loss": 3.4177, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846122449247e-05, + "loss": 3.445, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0837752880540213e-05, + "loss": 3.4385, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829366933029693e-05, + "loss": 3.4397, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0820980985519173e-05, + "loss": 3.4325, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0812595038008653e-05, + "loss": 3.4288, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804225469301862e-05, + "loss": 3.4252, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0795839521791345e-05, + "loss": 3.4318, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0787453574280825e-05, + "loss": 3.4334, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779067626770305e-05, + "loss": 3.4358, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0770698058063514e-05, + "loss": 3.4454, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762312110552994e-05, + "loss": 3.4279, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0753926163042474e-05, + "loss": 3.4349, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0745540215531954e-05, + "loss": 3.4472, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737170646825167e-05, + "loss": 3.4229, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0728784699314647e-05, + "loss": 3.4221, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720398751804127e-05, + "loss": 3.4412, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712012804293607e-05, + "loss": 3.4375, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0703643235586816e-05, + "loss": 3.4277, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.06952572880763e-05, + "loss": 3.4286, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.068687134056578e-05, + "loss": 3.4261, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067848539305526e-05, + "loss": 3.4356, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670115824348468e-05, + "loss": 3.4413, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0661729876837948e-05, + "loss": 3.4367, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653343929327428e-05, + "loss": 3.4391, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0644957981816908e-05, + "loss": 3.4439, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.063658841311012e-05, + "loss": 3.456, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.06282024655996e-05, + "loss": 3.4319, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.061981651808908e-05, + "loss": 3.4379, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061143057057856e-05, + "loss": 3.4426, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.060306100187177e-05, + "loss": 3.4267, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0594675054361253e-05, + "loss": 3.4395, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586289106850733e-05, + "loss": 3.4436, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0577903159340213e-05, + "loss": 3.4405, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056953359063342e-05, + "loss": 3.4422, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.05611476431229e-05, + "loss": 3.4266, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055276169561238e-05, + "loss": 3.4257, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054437574810186e-05, + "loss": 3.4339, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536006179395074e-05, + "loss": 3.4379, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527620231884554e-05, + "loss": 3.4396, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519234284374034e-05, + "loss": 3.4278, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051084833686351e-05, + "loss": 3.4334, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0502478768156723e-05, + "loss": 3.4308, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494092820646203e-05, + "loss": 3.4255, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0485706873135686e-05, + "loss": 3.4332, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477320925625163e-05, + "loss": 3.4387, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0468951356918375e-05, + "loss": 3.4455, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460565409407855e-05, + "loss": 3.4378, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452179461897332e-05, + "loss": 3.4245, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0443793514386815e-05, + "loss": 3.4413, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435423945680028e-05, + "loss": 3.432, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0427037998169508e-05, + "loss": 3.436, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0418652050658984e-05, + "loss": 3.4337, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410266103148464e-05, + "loss": 3.433, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0401896534441677e-05, + "loss": 3.4347, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393510586931157e-05, + "loss": 3.4454, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385124639420637e-05, + "loss": 3.4187, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0376738691910117e-05, + "loss": 3.4345, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368352744399596e-05, + "loss": 3.4314, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0359983175692806e-05, + "loss": 3.442, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0351597228182286e-05, + "loss": 3.4222, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034321128067177e-05, + "loss": 3.4349, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033482533316125e-05, + "loss": 3.4262, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326455764454458e-05, + "loss": 3.4379, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318069816943938e-05, + "loss": 3.4419, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0309683869433418e-05, + "loss": 3.4282, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301297921922898e-05, + "loss": 3.4366, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.029292835321611e-05, + "loss": 3.4511, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028454240570559e-05, + "loss": 3.4376, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027615645819507e-05, + "loss": 3.4358, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026777051068455e-05, + "loss": 3.4393, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025940094197776e-05, + "loss": 3.4378, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025101499446724e-05, + "loss": 3.424, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0242629046956723e-05, + "loss": 3.4346, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234243099446202e-05, + "loss": 3.424, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022587353073941e-05, + "loss": 3.4354, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021748758322889e-05, + "loss": 3.4306, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020910163571837e-05, + "loss": 3.4363, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0200732067011584e-05, + "loss": 3.4352, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192346119501064e-05, + "loss": 3.4262, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0183960171990544e-05, + "loss": 3.4294, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175574224480024e-05, + "loss": 3.4448, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167188276969504e-05, + "loss": 3.4376, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0158818708262713e-05, + "loss": 3.4435, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150432760752193e-05, + "loss": 3.425, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142046813241676e-05, + "loss": 3.4497, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0133677244534885e-05, + "loss": 3.4338, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125291297024365e-05, + "loss": 3.4372, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0116905349513845e-05, + "loss": 3.4346, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108519402003325e-05, + "loss": 3.4333, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100149833296538e-05, + "loss": 3.4321, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0091763885786018e-05, + "loss": 3.45, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083377938275498e-05, + "loss": 3.4245, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0074991990764978e-05, + "loss": 3.4428, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0066622422058187e-05, + "loss": 3.4298, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058236474547667e-05, + "loss": 3.4326, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0049850527037147e-05, + "loss": 3.4301, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041464579526626e-05, + "loss": 3.4326, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.003309501081984e-05, + "loss": 3.4479, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002470906330932e-05, + "loss": 3.4249, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.00163231157988e-05, + "loss": 3.434, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8573269844055176, + "eval_runtime": 304.6131, + "eval_samples_per_second": 1252.707, + "eval_steps_per_second": 39.148, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.000793716828828e-05, + "loss": 3.433, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.999955122077776e-05, + "loss": 3.4326, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999116527326724e-05, + "loss": 3.435, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998277932575672e-05, + "loss": 3.4308, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997440975704993e-05, + "loss": 3.4448, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966023809539408e-05, + "loss": 3.4269, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9957637862028888e-05, + "loss": 3.435, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949251914518368e-05, + "loss": 3.4296, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.994088234581158e-05, + "loss": 3.4328, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.993249639830106e-05, + "loss": 3.4399, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992411045079054e-05, + "loss": 3.4339, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991572450328002e-05, + "loss": 3.4278, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990735493457323e-05, + "loss": 3.4359, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989896898706271e-05, + "loss": 3.4175, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890583039552192e-05, + "loss": 3.4335, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882197092041672e-05, + "loss": 3.4251, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987382752333488e-05, + "loss": 3.4281, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.986544157582436e-05, + "loss": 3.4256, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985705562831384e-05, + "loss": 3.4244, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984866968080332e-05, + "loss": 3.4419, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840300112096534e-05, + "loss": 3.4442, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9831914164586014e-05, + "loss": 3.4396, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823528217075494e-05, + "loss": 3.4303, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815142269564974e-05, + "loss": 3.4309, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9806772700858183e-05, + "loss": 3.427, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798386753347663e-05, + "loss": 3.4414, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790000805837146e-05, + "loss": 3.4311, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9781614858326626e-05, + "loss": 3.4305, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773245289619835e-05, + "loss": 3.4243, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9764859342109315e-05, + "loss": 3.4284, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756473394598795e-05, + "loss": 3.4247, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748087447088275e-05, + "loss": 3.4419, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9739717878381487e-05, + "loss": 3.4376, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9731331930870967e-05, + "loss": 3.4292, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9722945983360447e-05, + "loss": 3.423, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9714560035849927e-05, + "loss": 3.4327, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706190467143136e-05, + "loss": 3.4316, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9697804519632616e-05, + "loss": 3.4266, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.96894185721221e-05, + "loss": 3.4296, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968103262461158e-05, + "loss": 3.4211, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967266305590479e-05, + "loss": 3.4242, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966427710839427e-05, + "loss": 3.438, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965589116088375e-05, + "loss": 3.4396, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964750521337323e-05, + "loss": 3.4236, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.963913564466644e-05, + "loss": 3.4306, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.963074969715592e-05, + "loss": 3.4248, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.96223637496454e-05, + "loss": 3.4321, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961397780213488e-05, + "loss": 3.4259, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960560823342809e-05, + "loss": 3.4042, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959722228591757e-05, + "loss": 3.4393, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958883633840705e-05, + "loss": 3.427, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580450390896533e-05, + "loss": 3.4312, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572080822189742e-05, + "loss": 3.4245, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563694874679222e-05, + "loss": 3.4211, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555308927168702e-05, + "loss": 3.4113, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9546922979658182e-05, + "loss": 3.4218, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538553410951395e-05, + "loss": 3.4237, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530167463440875e-05, + "loss": 3.4228, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9521781515930355e-05, + "loss": 3.4364, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951339556841983e-05, + "loss": 3.4172, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505025999713044e-05, + "loss": 3.4256, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496640052202524e-05, + "loss": 3.4375, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488254104692004e-05, + "loss": 3.4137, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9479884535985216e-05, + "loss": 3.413, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471498588474696e-05, + "loss": 3.4293, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463112640964176e-05, + "loss": 3.4275, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9454726693453656e-05, + "loss": 3.418, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446357124746865e-05, + "loss": 3.4172, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943797117723635e-05, + "loss": 3.4166, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942958522972583e-05, + "loss": 3.4235, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421199282215305e-05, + "loss": 3.4303, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9412829713508517e-05, + "loss": 3.4259, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404443765997997e-05, + "loss": 3.4303, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396057818487477e-05, + "loss": 3.4323, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387671870976957e-05, + "loss": 3.4459, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937930230227017e-05, + "loss": 3.4187, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937091635475965e-05, + "loss": 3.4345, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936253040724913e-05, + "loss": 3.43, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354144459738606e-05, + "loss": 3.4181, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934577489103182e-05, + "loss": 3.4241, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337388943521302e-05, + "loss": 3.4374, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932900299601078e-05, + "loss": 3.4285, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932061704850026e-05, + "loss": 3.4319, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931224747979347e-05, + "loss": 3.4141, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930386153228295e-05, + "loss": 3.4157, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929547558477243e-05, + "loss": 3.4222, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.928708963726191e-05, + "loss": 3.4283, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9278720068555123e-05, + "loss": 3.4306, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.92703341210446e-05, + "loss": 3.4211, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926194817353408e-05, + "loss": 3.4157, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925356222602356e-05, + "loss": 3.4251, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245192657316772e-05, + "loss": 3.4138, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9236806709806252e-05, + "loss": 3.4229, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228420762295732e-05, + "loss": 3.4287, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220034814785212e-05, + "loss": 3.4324, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9211665246078425e-05, + "loss": 3.4259, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.92032792985679e-05, + "loss": 3.4156, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9194893351057385e-05, + "loss": 3.431, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186507403546865e-05, + "loss": 3.4207, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178137834840074e-05, + "loss": 3.4268, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169751887329554e-05, + "loss": 3.4263, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161365939819034e-05, + "loss": 3.419, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9152979992308514e-05, + "loss": 3.4335, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144610423601726e-05, + "loss": 3.4307, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136224476091206e-05, + "loss": 3.4069, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9127838528580686e-05, + "loss": 3.4214, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119452581070166e-05, + "loss": 3.4145, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111083012363375e-05, + "loss": 3.4371, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102697064852855e-05, + "loss": 3.4075, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094311117342335e-05, + "loss": 3.4264, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908592516983182e-05, + "loss": 3.4156, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077555601125027e-05, + "loss": 3.4251, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069169653614507e-05, + "loss": 3.4278, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9060783706103987e-05, + "loss": 3.4194, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052397758593467e-05, + "loss": 3.4227, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904402818988668e-05, + "loss": 3.442, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903564224237616e-05, + "loss": 3.4236, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902725629486564e-05, + "loss": 3.4306, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901887034735512e-05, + "loss": 3.4282, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.901050077864833e-05, + "loss": 3.4259, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.900211483113781e-05, + "loss": 3.4224, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899372888362729e-05, + "loss": 3.4208, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985342936116772e-05, + "loss": 3.4118, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897697336740998e-05, + "loss": 3.4238, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896858741989946e-05, + "loss": 3.4205, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896020147238894e-05, + "loss": 3.4241, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895181552487842e-05, + "loss": 3.4216, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943445956171633e-05, + "loss": 3.4166, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935060008661113e-05, + "loss": 3.4179, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926674061150593e-05, + "loss": 3.4351, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918288113640073e-05, + "loss": 3.4227, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8909918544933282e-05, + "loss": 3.4349, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8901532597422762e-05, + "loss": 3.4099, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8893146649912242e-05, + "loss": 3.4416, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8884760702401726e-05, + "loss": 3.4207, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876391133694935e-05, + "loss": 3.4283, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868005186184415e-05, + "loss": 3.4245, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859619238673895e-05, + "loss": 3.4216, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851233291163375e-05, + "loss": 3.4245, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8842863722456587e-05, + "loss": 3.4401, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834477774946067e-05, + "loss": 3.4086, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826091827435547e-05, + "loss": 3.4331, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8817705879925027e-05, + "loss": 3.4237, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809336311218236e-05, + "loss": 3.4171, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.880096674251145e-05, + "loss": 3.4229, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.879258079500093e-05, + "loss": 3.4212, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878419484749041e-05, + "loss": 3.4389, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877580889997989e-05, + "loss": 3.4159, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876742295246937e-05, + "loss": 3.421, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.858464241027832, + "eval_runtime": 303.1259, + "eval_samples_per_second": 1258.853, + "eval_steps_per_second": 39.34, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875903700495885e-05, + "loss": 3.4218, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750651057448325e-05, + "loss": 3.4215, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742265109937808e-05, + "loss": 3.4219, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873389554123102e-05, + "loss": 3.4253, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.87255095937205e-05, + "loss": 3.4381, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717123646209977e-05, + "loss": 3.4127, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8708737698699457e-05, + "loss": 3.4232, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.870036812999267e-05, + "loss": 3.42, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.869198218248215e-05, + "loss": 3.4225, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.868359623497163e-05, + "loss": 3.43, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.867521028746111e-05, + "loss": 3.4217, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8666840718754322e-05, + "loss": 3.4174, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.86584547712438e-05, + "loss": 3.4289, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.865006882373328e-05, + "loss": 3.406, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.864168287622276e-05, + "loss": 3.4215, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.863331330751597e-05, + "loss": 3.4122, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.862492736000545e-05, + "loss": 3.4192, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861654141249493e-05, + "loss": 3.4159, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860815546498441e-05, + "loss": 3.4158, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8599785896277623e-05, + "loss": 3.4318, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591399948767103e-05, + "loss": 3.4298, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583014001256583e-05, + "loss": 3.4309, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574628053746063e-05, + "loss": 3.422, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566258485039272e-05, + "loss": 3.4191, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8557872537528752e-05, + "loss": 3.4156, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8549486590018232e-05, + "loss": 3.431, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541100642507712e-05, + "loss": 3.4219, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8532731073800925e-05, + "loss": 3.4196, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524345126290405e-05, + "loss": 3.4122, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8515959178779885e-05, + "loss": 3.4178, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507573231269365e-05, + "loss": 3.4125, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499203662562574e-05, + "loss": 3.4305, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8490817715052057e-05, + "loss": 3.4297, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482431767541537e-05, + "loss": 3.4173, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474045820031017e-05, + "loss": 3.4166, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8465676251324226e-05, + "loss": 3.4151, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457290303813706e-05, + "loss": 3.4237, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8448904356303186e-05, + "loss": 3.4159, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440518408792666e-05, + "loss": 3.417, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843214884008588e-05, + "loss": 3.4079, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842376289257536e-05, + "loss": 3.4171, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415376945064838e-05, + "loss": 3.4232, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8406990997554318e-05, + "loss": 3.4259, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398621428847527e-05, + "loss": 3.4184, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839023548133701e-05, + "loss": 3.4169, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838184953382649e-05, + "loss": 3.4198, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837346358631597e-05, + "loss": 3.4193, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836509401760918e-05, + "loss": 3.4167, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835670807009866e-05, + "loss": 3.3928, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834832212258814e-05, + "loss": 3.427, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.833993617507762e-05, + "loss": 3.4183, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331566606370832e-05, + "loss": 3.4227, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323180658860312e-05, + "loss": 3.4114, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8314794711349792e-05, + "loss": 3.4101, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306408763839272e-05, + "loss": 3.4037, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829803919513248e-05, + "loss": 3.4086, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289653247621964e-05, + "loss": 3.4171, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281267300111444e-05, + "loss": 3.405, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8272881352600924e-05, + "loss": 3.4247, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264511783894133e-05, + "loss": 3.4114, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256125836383613e-05, + "loss": 3.412, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8247739888873093e-05, + "loss": 3.4302, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239353941362573e-05, + "loss": 3.4053, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8230984372655786e-05, + "loss": 3.4028, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222598425145266e-05, + "loss": 3.4194, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214212477634746e-05, + "loss": 3.4163, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8205842908927955e-05, + "loss": 3.408, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197456961417435e-05, + "loss": 3.4065, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8189071013906918e-05, + "loss": 3.4011, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8180685066396398e-05, + "loss": 3.4156, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172299118885875e-05, + "loss": 3.4175, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8163929550179087e-05, + "loss": 3.4202, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155543602668567e-05, + "loss": 3.4189, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147157655158044e-05, + "loss": 3.4205, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813878808645126e-05, + "loss": 3.4356, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813040213894074e-05, + "loss": 3.4126, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.812201619143022e-05, + "loss": 3.4256, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8113630243919696e-05, + "loss": 3.4155, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810526067521291e-05, + "loss": 3.4108, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809687472770239e-05, + "loss": 3.4122, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808848878019187e-05, + "loss": 3.426, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080102832681348e-05, + "loss": 3.4177, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.807173326397456e-05, + "loss": 3.422, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806334731646404e-05, + "loss": 3.4036, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8054961368953517e-05, + "loss": 3.4048, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046575421442997e-05, + "loss": 3.4125, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038205852736213e-05, + "loss": 3.4157, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8029819905225693e-05, + "loss": 3.4201, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802143395771517e-05, + "loss": 3.4145, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801304801020465e-05, + "loss": 3.4033, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8004678441497862e-05, + "loss": 3.4186, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996292493987342e-05, + "loss": 3.4069, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7987906546476822e-05, + "loss": 3.4099, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979520598966302e-05, + "loss": 3.4193, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971151030259514e-05, + "loss": 3.4216, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.796276508274899e-05, + "loss": 3.4167, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795437913523847e-05, + "loss": 3.4072, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.794599318772795e-05, + "loss": 3.4165, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937623619021167e-05, + "loss": 3.4101, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929237671510643e-05, + "loss": 3.4208, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7920851724000123e-05, + "loss": 3.4116, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912465776489603e-05, + "loss": 3.412, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904096207782812e-05, + "loss": 3.4171, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7895710260272296e-05, + "loss": 3.4202, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7887324312761776e-05, + "loss": 3.3987, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7878938365251256e-05, + "loss": 3.4125, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870568796544465e-05, + "loss": 3.4052, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862182849033945e-05, + "loss": 3.4226, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7853796901523425e-05, + "loss": 3.4016, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845410954012905e-05, + "loss": 3.4142, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837041385306117e-05, + "loss": 3.4032, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7828655437795597e-05, + "loss": 3.4205, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820269490285077e-05, + "loss": 3.4148, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7811883542774557e-05, + "loss": 3.4072, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803513974067766e-05, + "loss": 3.4136, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779512802655725e-05, + "loss": 3.4311, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778674207904673e-05, + "loss": 3.4129, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777835613153621e-05, + "loss": 3.4224, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.776998656282942e-05, + "loss": 3.4139, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761600615318898e-05, + "loss": 3.4124, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753214667808378e-05, + "loss": 3.4172, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7744828720297858e-05, + "loss": 3.4072, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773645915159107e-05, + "loss": 3.4024, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772807320408055e-05, + "loss": 3.4133, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771968725657003e-05, + "loss": 3.4134, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771130130905951e-05, + "loss": 3.4138, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770293174035272e-05, + "loss": 3.4156, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694545792842203e-05, + "loss": 3.408, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686159845331683e-05, + "loss": 3.4088, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7677773897821163e-05, + "loss": 3.423, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669404329114372e-05, + "loss": 3.4133, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7661018381603852e-05, + "loss": 3.4263, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7652632434093332e-05, + "loss": 3.4005, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644246486582812e-05, + "loss": 3.4283, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7635876917876024e-05, + "loss": 3.4169, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627490970365504e-05, + "loss": 3.4135, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619105022854984e-05, + "loss": 3.4128, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7610719075344464e-05, + "loss": 3.4103, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602349506637673e-05, + "loss": 3.4145, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7593963559127157e-05, + "loss": 3.4294, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585577611616637e-05, + "loss": 3.4016, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577191664106117e-05, + "loss": 3.4214, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568822095399326e-05, + "loss": 3.4102, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560436147888806e-05, + "loss": 3.4085, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552066579182018e-05, + "loss": 3.4155, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543680631671498e-05, + "loss": 3.4112, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535294684160978e-05, + "loss": 3.4226, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7526908736650458e-05, + "loss": 3.4135, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518522789139938e-05, + "loss": 3.4096, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.858882427215576, + "eval_runtime": 304.5648, + "eval_samples_per_second": 1252.906, + "eval_steps_per_second": 39.154, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510136841629415e-05, + "loss": 3.4123, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501750894118894e-05, + "loss": 3.4123, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493364946608374e-05, + "loss": 3.4116, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7484978999097858e-05, + "loss": 3.4164, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476609430391067e-05, + "loss": 3.4258, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468223482880547e-05, + "loss": 3.4043, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7459837535370027e-05, + "loss": 3.4141, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451451587859507e-05, + "loss": 3.4144, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744308201915272e-05, + "loss": 3.4107, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.74346960716422e-05, + "loss": 3.418, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.742631012413168e-05, + "loss": 3.4113, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741792417662116e-05, + "loss": 3.4109, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409554607914368e-05, + "loss": 3.4174, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401168660403848e-05, + "loss": 3.3949, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7392782712893328e-05, + "loss": 3.4097, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738439676538281e-05, + "loss": 3.4005, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737602719667602e-05, + "loss": 3.4108, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.73676412491655e-05, + "loss": 3.4064, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735925530165498e-05, + "loss": 3.4029, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735086935414446e-05, + "loss": 3.4215, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342499785437673e-05, + "loss": 3.4161, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334113837927153e-05, + "loss": 3.4205, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325727890416633e-05, + "loss": 3.4143, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317341942906113e-05, + "loss": 3.4111, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7308972374199322e-05, + "loss": 3.4101, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7300586426688802e-05, + "loss": 3.4144, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292200479178282e-05, + "loss": 3.4112, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7283814531667765e-05, + "loss": 3.4125, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275444962960974e-05, + "loss": 3.4041, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267059015450454e-05, + "loss": 3.4039, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7258673067939934e-05, + "loss": 3.4035, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250287120429414e-05, + "loss": 3.4132, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7241917551722627e-05, + "loss": 3.42, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233531604212106e-05, + "loss": 3.4094, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225145656701586e-05, + "loss": 3.4069, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7216759709191066e-05, + "loss": 3.4027, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208390140484276e-05, + "loss": 3.416, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200004192973755e-05, + "loss": 3.4086, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7191618245463235e-05, + "loss": 3.4064, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718323229795272e-05, + "loss": 3.3989, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7174862729245928e-05, + "loss": 3.4086, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166476781735408e-05, + "loss": 3.4077, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158090834224888e-05, + "loss": 3.416, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149704886714364e-05, + "loss": 3.4091, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.714133531800758e-05, + "loss": 3.4062, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713294937049706e-05, + "loss": 3.4084, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.712456342298654e-05, + "loss": 3.4104, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116177475476017e-05, + "loss": 3.4082, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710780790676923e-05, + "loss": 3.3842, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709942195925871e-05, + "loss": 3.415, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.709103601174819e-05, + "loss": 3.4053, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.708265006423767e-05, + "loss": 3.414, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707428049553088e-05, + "loss": 3.402, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706589454802036e-05, + "loss": 3.4011, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057508600509838e-05, + "loss": 3.3927, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049122652999318e-05, + "loss": 3.3991, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040753084292534e-05, + "loss": 3.4101, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032367136782014e-05, + "loss": 3.392, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702398118927149e-05, + "loss": 3.4141, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701559524176097e-05, + "loss": 3.4006, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007225673054183e-05, + "loss": 3.3977, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998839725543663e-05, + "loss": 3.4213, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990453778033143e-05, + "loss": 3.4016, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982067830522623e-05, + "loss": 3.3914, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6973698261815835e-05, + "loss": 3.4079, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965312314305312e-05, + "loss": 3.4056, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6956926366794792e-05, + "loss": 3.3975, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948556798088004e-05, + "loss": 3.3988, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6940170850577488e-05, + "loss": 3.3925, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6931784903066964e-05, + "loss": 3.4012, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923398955556444e-05, + "loss": 3.4103, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915029386849657e-05, + "loss": 3.4103, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906643439339137e-05, + "loss": 3.406, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898257491828613e-05, + "loss": 3.4095, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6889871544318096e-05, + "loss": 3.4264, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.688150197561131e-05, + "loss": 3.4068, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873116028100785e-05, + "loss": 3.4136, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864730080590265e-05, + "loss": 3.4038, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856344133079745e-05, + "loss": 3.4014, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6847974564372958e-05, + "loss": 3.4013, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839588616862438e-05, + "loss": 3.4191, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6831202669351918e-05, + "loss": 3.4072, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6822816721841398e-05, + "loss": 3.4148, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681444715313461e-05, + "loss": 3.3913, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806061205624087e-05, + "loss": 3.398, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797675258113567e-05, + "loss": 3.4034, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.678928931060305e-05, + "loss": 3.4057, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.678091974189626e-05, + "loss": 3.4073, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.677253379438574e-05, + "loss": 3.4067, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.676414784687522e-05, + "loss": 3.3923, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.67557618993647e-05, + "loss": 3.4067, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.674739233065791e-05, + "loss": 3.3982, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673900638314739e-05, + "loss": 3.3994, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.673062043563687e-05, + "loss": 3.4094, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.672223448812635e-05, + "loss": 3.4118, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.671386491941956e-05, + "loss": 3.4053, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670547897190904e-05, + "loss": 3.3986, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669709302439852e-05, + "loss": 3.4075, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688707076888004e-05, + "loss": 3.3957, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680337508181213e-05, + "loss": 3.4121, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6671951560670693e-05, + "loss": 3.402, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663565613160173e-05, + "loss": 3.4054, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655179665649653e-05, + "loss": 3.407, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6646810096942865e-05, + "loss": 3.4053, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638424149432345e-05, + "loss": 3.3967, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6630038201921825e-05, + "loss": 3.4007, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621652254411305e-05, + "loss": 3.3952, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613282685704514e-05, + "loss": 3.4132, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6604896738193994e-05, + "loss": 3.397, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596510790683474e-05, + "loss": 3.398, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6588124843172957e-05, + "loss": 3.391, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6579755274466167e-05, + "loss": 3.4063, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571369326955646e-05, + "loss": 3.4107, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6562983379445126e-05, + "loss": 3.3972, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554597431934606e-05, + "loss": 3.4071, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654622786322782e-05, + "loss": 3.4196, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.65378419157173e-05, + "loss": 3.4027, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652945596820678e-05, + "loss": 3.4133, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652107002069626e-05, + "loss": 3.406, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512700451989468e-05, + "loss": 3.4037, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504314504478948e-05, + "loss": 3.406, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6495928556968428e-05, + "loss": 3.3969, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.648754260945791e-05, + "loss": 3.396, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647917304075112e-05, + "loss": 3.4029, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.64707870932406e-05, + "loss": 3.4045, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.646240114573008e-05, + "loss": 3.4046, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.645401519821956e-05, + "loss": 3.4006, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445645629512773e-05, + "loss": 3.3991, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437259682002252e-05, + "loss": 3.3935, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6428873734491732e-05, + "loss": 3.4136, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.642048778698121e-05, + "loss": 3.4025, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641211821827442e-05, + "loss": 3.4157, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.64037322707639e-05, + "loss": 3.3939, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639534632325338e-05, + "loss": 3.4147, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638696037574286e-05, + "loss": 3.4074, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378590807036074e-05, + "loss": 3.4049, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370204859525554e-05, + "loss": 3.4039, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6361818912015034e-05, + "loss": 3.3995, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635343296450451e-05, + "loss": 3.4066, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345063395797723e-05, + "loss": 3.4192, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336677448287206e-05, + "loss": 3.3938, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328291500776683e-05, + "loss": 3.4106, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6319905553266163e-05, + "loss": 3.4, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311535984559375e-05, + "loss": 3.3999, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6303166415852588e-05, + "loss": 3.4032, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6294780468342068e-05, + "loss": 3.4005, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286394520831548e-05, + "loss": 3.4143, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6278008573321028e-05, + "loss": 3.4048, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269622625810507e-05, + "loss": 3.3989, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8613440990448, + "eval_runtime": 305.8043, + "eval_samples_per_second": 1247.827, + "eval_steps_per_second": 38.996, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6261236678299984e-05, + "loss": 3.3967, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6252850730789464e-05, + "loss": 3.3989, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244464783278944e-05, + "loss": 3.4055, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6236095214572156e-05, + "loss": 3.4046, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6227709267061636e-05, + "loss": 3.416, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219323319551116e-05, + "loss": 3.3939, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6210937372040596e-05, + "loss": 3.4047, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202567803333805e-05, + "loss": 3.4004, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619418185582329e-05, + "loss": 3.4013, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618579590831277e-05, + "loss": 3.4002, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617740996080225e-05, + "loss": 3.4076, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6169040392095458e-05, + "loss": 3.4002, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6160654444584938e-05, + "loss": 3.4045, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152268497074418e-05, + "loss": 3.3896, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6143882549563898e-05, + "loss": 3.3985, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.613551298085711e-05, + "loss": 3.3899, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.612712703334659e-05, + "loss": 3.4058, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611874108583607e-05, + "loss": 3.3968, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.611035513832555e-05, + "loss": 3.3919, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.610198556961876e-05, + "loss": 3.4095, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093599622108242e-05, + "loss": 3.4093, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085213674597722e-05, + "loss": 3.405, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6076827727087202e-05, + "loss": 3.4068, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.606845815838041e-05, + "loss": 3.4004, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.606007221086989e-05, + "loss": 3.4002, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.605168626335937e-05, + "loss": 3.4087, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.604330031584885e-05, + "loss": 3.3947, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6034930747142064e-05, + "loss": 3.4034, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026544799631544e-05, + "loss": 3.3963, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018158852121024e-05, + "loss": 3.3928, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6009772904610504e-05, + "loss": 3.3966, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001403335903713e-05, + "loss": 3.4049, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993017388393196e-05, + "loss": 3.4059, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984631440882676e-05, + "loss": 3.4075, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976245493372156e-05, + "loss": 3.3971, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5967875924665365e-05, + "loss": 3.392, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959489977154845e-05, + "loss": 3.4066, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951104029644325e-05, + "loss": 3.3956, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5942718082133805e-05, + "loss": 3.3975, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5934348513427017e-05, + "loss": 3.3921, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5925962565916497e-05, + "loss": 3.3972, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5917576618405977e-05, + "loss": 3.3976, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5909190670895457e-05, + "loss": 3.4087, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5900821102188666e-05, + "loss": 3.4012, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5892435154678146e-05, + "loss": 3.3925, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588404920716763e-05, + "loss": 3.4029, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5875663259657106e-05, + "loss": 3.3971, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.586729369095032e-05, + "loss": 3.3996, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.58589077434398e-05, + "loss": 3.3773, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.585052179592928e-05, + "loss": 3.4038, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.584213584841876e-05, + "loss": 3.3955, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.583376627971197e-05, + "loss": 3.4071, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.582538033220145e-05, + "loss": 3.3918, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.581699438469093e-05, + "loss": 3.3896, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808608437180408e-05, + "loss": 3.3843, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.580023886847362e-05, + "loss": 3.3873, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.57918529209631e-05, + "loss": 3.4019, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.578346697345258e-05, + "loss": 3.3819, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.577508102594206e-05, + "loss": 3.4072, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5766711457235272e-05, + "loss": 3.391, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5758325509724752e-05, + "loss": 3.3863, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.574993956221423e-05, + "loss": 3.41, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741553614703712e-05, + "loss": 3.3906, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733184045996925e-05, + "loss": 3.3831, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5724798098486405e-05, + "loss": 3.3991, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.571641215097588e-05, + "loss": 3.396, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.570802620346536e-05, + "loss": 3.3855, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5699656634758574e-05, + "loss": 3.392, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5691270687248054e-05, + "loss": 3.3811, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5682884739737534e-05, + "loss": 3.3907, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674498792227014e-05, + "loss": 3.4011, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666129223520226e-05, + "loss": 3.3997, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5657743276009703e-05, + "loss": 3.3968, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649357328499183e-05, + "loss": 3.3989, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5640971380988666e-05, + "loss": 3.4148, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.563260181228188e-05, + "loss": 3.3981, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624215864771355e-05, + "loss": 3.4056, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5615846296064567e-05, + "loss": 3.3927, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607460348554047e-05, + "loss": 3.3912, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599074401043527e-05, + "loss": 3.3931, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5590688453533007e-05, + "loss": 3.4059, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5582302506022487e-05, + "loss": 3.3981, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5573916558511967e-05, + "loss": 3.4042, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5565530611001447e-05, + "loss": 3.3851, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5557144663490927e-05, + "loss": 3.3859, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5548775094784136e-05, + "loss": 3.3912, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.554038914727362e-05, + "loss": 3.3945, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.55320031997631e-05, + "loss": 3.395, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552361725225258e-05, + "loss": 3.3987, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551524768354579e-05, + "loss": 3.387, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550686173603527e-05, + "loss": 3.3929, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549847578852475e-05, + "loss": 3.3901, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.549008984101423e-05, + "loss": 3.386, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.548172027230744e-05, + "loss": 3.4009, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.547333432479692e-05, + "loss": 3.4032, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.54649483772864e-05, + "loss": 3.3977, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.545656242977588e-05, + "loss": 3.3842, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.544819286106909e-05, + "loss": 3.3992, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.543980691355857e-05, + "loss": 3.3859, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431420966048053e-05, + "loss": 3.3973, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423035018537533e-05, + "loss": 3.3953, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5414665449830742e-05, + "loss": 3.3905, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406279502320222e-05, + "loss": 3.3986, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397893554809702e-05, + "loss": 3.393, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389507607299182e-05, + "loss": 3.391, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381138038592395e-05, + "loss": 3.3875, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372752091081875e-05, + "loss": 3.385, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364366143571355e-05, + "loss": 3.4009, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.535598019606083e-05, + "loss": 3.3897, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5347610627354044e-05, + "loss": 3.3852, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5339224679843524e-05, + "loss": 3.3839, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5330838732333004e-05, + "loss": 3.3938, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322452784822483e-05, + "loss": 3.4033, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314083216115696e-05, + "loss": 3.3866, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5305697268605176e-05, + "loss": 3.3968, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297311321094652e-05, + "loss": 3.4067, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5288925373584136e-05, + "loss": 3.3962, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.528055580487735e-05, + "loss": 3.3987, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5272169857366828e-05, + "loss": 3.401, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5263783909856305e-05, + "loss": 3.3928, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255397962345785e-05, + "loss": 3.3957, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247028393638999e-05, + "loss": 3.3854, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238642446128476e-05, + "loss": 3.387, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230256498617955e-05, + "loss": 3.3945, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221870551107437e-05, + "loss": 3.3954, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.521350098240065e-05, + "loss": 3.3911, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205115034890128e-05, + "loss": 3.3938, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5196729087379608e-05, + "loss": 3.383, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188343139869088e-05, + "loss": 3.3876, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.51799735711623e-05, + "loss": 3.4022, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171587623651779e-05, + "loss": 3.3917, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163218054944991e-05, + "loss": 3.4084, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5154832107434471e-05, + "loss": 3.3808, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.514644615992395e-05, + "loss": 3.4048, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.513806021241343e-05, + "loss": 3.3985, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.512967426490291e-05, + "loss": 3.3928, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.512128831739239e-05, + "loss": 3.3899, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.511290236988187e-05, + "loss": 3.3928, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510451642237135e-05, + "loss": 3.3957, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5096146853664562e-05, + "loss": 3.4053, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5087760906154041e-05, + "loss": 3.3875, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079374958643521e-05, + "loss": 3.3953, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5070989011133001e-05, + "loss": 3.3916, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5062619442426212e-05, + "loss": 3.3894, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5054249873719423e-05, + "loss": 3.3909, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5045863926208903e-05, + "loss": 3.397, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037477978698383e-05, + "loss": 3.3997, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5029092031187863e-05, + "loss": 3.3958, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5020706083677344e-05, + "loss": 3.3901, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8617968559265137, + "eval_runtime": 305.4115, + "eval_samples_per_second": 1249.432, + "eval_steps_per_second": 39.046, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012320136166824e-05, + "loss": 3.3983, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5003934188656304e-05, + "loss": 3.3859, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995548241145783e-05, + "loss": 3.3958, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987162293635263e-05, + "loss": 3.3956, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978792724928475e-05, + "loss": 3.3987, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970406777417955e-05, + "loss": 3.3897, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962020829907433e-05, + "loss": 3.3946, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953634882396913e-05, + "loss": 3.3931, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945265313690127e-05, + "loss": 3.3853, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936879366179604e-05, + "loss": 3.3936, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928493418669084e-05, + "loss": 3.3997, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920107471158566e-05, + "loss": 3.3903, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4911737902451778e-05, + "loss": 3.3997, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903351954941255e-05, + "loss": 3.3748, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894966007430736e-05, + "loss": 3.3865, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886580059920216e-05, + "loss": 3.383, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878210491213429e-05, + "loss": 3.3965, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4869824543702907e-05, + "loss": 3.3849, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861438596192387e-05, + "loss": 3.383, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853052648681867e-05, + "loss": 3.3961, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4844683079975078e-05, + "loss": 3.398, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836297132464558e-05, + "loss": 3.3984, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4827911184954038e-05, + "loss": 3.3959, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819525237443518e-05, + "loss": 3.3881, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811155668736728e-05, + "loss": 3.3956, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4802769721226208e-05, + "loss": 3.3959, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.479438377371569e-05, + "loss": 3.383, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.478599782620517e-05, + "loss": 3.3923, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4777628257498379e-05, + "loss": 3.3848, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.476924230998786e-05, + "loss": 3.3809, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.476085636247734e-05, + "loss": 3.3888, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.475247041496682e-05, + "loss": 3.392, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4744100846260031e-05, + "loss": 3.3958, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4735714898749511e-05, + "loss": 3.3971, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4727328951238991e-05, + "loss": 3.3871, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4718943003728471e-05, + "loss": 3.3833, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710573435021682e-05, + "loss": 3.3982, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4702187487511162e-05, + "loss": 3.3838, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4693801540000644e-05, + "loss": 3.3892, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685415592490124e-05, + "loss": 3.3841, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677046023783333e-05, + "loss": 3.3823, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4668660076272814e-05, + "loss": 3.3858, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660274128762294e-05, + "loss": 3.3988, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651888181251774e-05, + "loss": 3.3888, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643518612544985e-05, + "loss": 3.3839, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635132665034465e-05, + "loss": 3.3924, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626746717523945e-05, + "loss": 3.3861, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618360770013425e-05, + "loss": 3.3898, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4609991201306636e-05, + "loss": 3.3712, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601605253796116e-05, + "loss": 3.392, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593219306285597e-05, + "loss": 3.3849, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4584833358775077e-05, + "loss": 3.396, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576463790068286e-05, + "loss": 3.3824, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568077842557768e-05, + "loss": 3.3831, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4559691895047248e-05, + "loss": 3.3751, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551322326340459e-05, + "loss": 3.3772, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542936378829939e-05, + "loss": 3.3927, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534550431319419e-05, + "loss": 3.3697, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526164483808899e-05, + "loss": 3.3977, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.451779491510211e-05, + "loss": 3.3829, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.450940896759159e-05, + "loss": 3.3751, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.450102302008107e-05, + "loss": 3.4036, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4492637072570551e-05, + "loss": 3.3773, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.448426750386376e-05, + "loss": 3.3736, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.447588155635324e-05, + "loss": 3.3841, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4467495608842722e-05, + "loss": 3.3866, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459109661332202e-05, + "loss": 3.3771, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4450740092625412e-05, + "loss": 3.3846, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4442354145114892e-05, + "loss": 3.3689, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4433968197604372e-05, + "loss": 3.3815, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425582250093852e-05, + "loss": 3.3899, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417212681387063e-05, + "loss": 3.3917, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4408826733876543e-05, + "loss": 3.3841, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400440786366023e-05, + "loss": 3.3876, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392054838855501e-05, + "loss": 3.4068, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383685270148714e-05, + "loss": 3.3858, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375299322638194e-05, + "loss": 3.3978, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4366929753931404e-05, + "loss": 3.3813, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358543806420884e-05, + "loss": 3.384, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350157858910364e-05, + "loss": 3.3777, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4341771911399846e-05, + "loss": 3.395, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333385963889326e-05, + "loss": 3.3871, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4325000016378803e-05, + "loss": 3.3969, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4316614068868284e-05, + "loss": 3.3766, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308228121357764e-05, + "loss": 3.3753, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299858552650975e-05, + "loss": 3.3812, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291472605140455e-05, + "loss": 3.3896, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283086657629935e-05, + "loss": 3.3819, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4274700710119415e-05, + "loss": 3.3892, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266331141412626e-05, + "loss": 3.3789, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4257945193902106e-05, + "loss": 3.3807, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249559246391586e-05, + "loss": 3.3803, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241173298881067e-05, + "loss": 3.3784, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232803730174276e-05, + "loss": 3.3877, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224417782663756e-05, + "loss": 3.3961, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4216031835153238e-05, + "loss": 3.3888, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4207645887642718e-05, + "loss": 3.3779, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199276318935929e-05, + "loss": 3.3858, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4190890371425409e-05, + "loss": 3.3814, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182504423914889e-05, + "loss": 3.3876, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174118476404369e-05, + "loss": 3.3837, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.416574890769758e-05, + "loss": 3.3799, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.415736296018706e-05, + "loss": 3.3909, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.414897701267654e-05, + "loss": 3.3842, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4140591065166021e-05, + "loss": 3.3802, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.413222149645923e-05, + "loss": 3.377, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.412383554894871e-05, + "loss": 3.3794, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115449601438192e-05, + "loss": 3.3876, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4107063653927672e-05, + "loss": 3.3829, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4098694085220882e-05, + "loss": 3.3767, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090308137710362e-05, + "loss": 3.3733, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081922190199842e-05, + "loss": 3.3794, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073536242689322e-05, + "loss": 3.3931, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4065166673982533e-05, + "loss": 3.3791, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4056780726472013e-05, + "loss": 3.3848, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4048394778961493e-05, + "loss": 3.396, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4040025210254704e-05, + "loss": 3.3881, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4031639262744184e-05, + "loss": 3.387, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023253315233664e-05, + "loss": 3.3912, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014883746526874e-05, + "loss": 3.3854, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006497799016354e-05, + "loss": 3.3882, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998111851505836e-05, + "loss": 3.3732, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3989725903995316e-05, + "loss": 3.3794, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981339956484796e-05, + "loss": 3.3823, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3972954008974276e-05, + "loss": 3.3845, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964568061463754e-05, + "loss": 3.3829, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956182113953234e-05, + "loss": 3.3816, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947812545246447e-05, + "loss": 3.3719, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939426597735925e-05, + "loss": 3.3783, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931040650225405e-05, + "loss": 3.3914, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922654702714885e-05, + "loss": 3.3851, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914285134008099e-05, + "loss": 3.394, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905899186497575e-05, + "loss": 3.3768, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897513238987055e-05, + "loss": 3.3888, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889127291476537e-05, + "loss": 3.3912, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.388075772276975e-05, + "loss": 3.3825, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872371775259226e-05, + "loss": 3.3777, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863985827748708e-05, + "loss": 3.3821, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3855599880238188e-05, + "loss": 3.3907, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847230311531399e-05, + "loss": 3.3955, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3838844364020878e-05, + "loss": 3.3792, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830458416510358e-05, + "loss": 3.3828, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822072468999838e-05, + "loss": 3.383, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.381370290029305e-05, + "loss": 3.3834, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805316952782529e-05, + "loss": 3.3781, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3796947384075742e-05, + "loss": 3.3903, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788561436565223e-05, + "loss": 3.3855, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.37801754890547e-05, + "loss": 3.3876, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.377178954154418e-05, + "loss": 3.3776, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.863250255584717, + "eval_runtime": 304.4444, + "eval_samples_per_second": 1253.401, + "eval_steps_per_second": 39.17, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3763403594033661e-05, + "loss": 3.3823, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3755017646523141e-05, + "loss": 3.3764, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746631699012621e-05, + "loss": 3.3852, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3738262130305832e-05, + "loss": 3.3907, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729876182795312e-05, + "loss": 3.3868, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721490235284792e-05, + "loss": 3.3839, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3713104287774272e-05, + "loss": 3.382, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3704734719067483e-05, + "loss": 3.3815, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3696348771556963e-05, + "loss": 3.3776, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3687962824046444e-05, + "loss": 3.389, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3679576876535924e-05, + "loss": 3.3825, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3671207307829133e-05, + "loss": 3.3844, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3662821360318615e-05, + "loss": 3.3904, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654435412808095e-05, + "loss": 3.3662, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3646049465297575e-05, + "loss": 3.3766, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3637679896590786e-05, + "loss": 3.3728, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3629293949080266e-05, + "loss": 3.3879, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3620908001569746e-05, + "loss": 3.3746, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612522054059226e-05, + "loss": 3.375, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3604152485352436e-05, + "loss": 3.3843, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3595766537841916e-05, + "loss": 3.3909, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3587380590331396e-05, + "loss": 3.3867, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3578994642820878e-05, + "loss": 3.3864, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3570625074114087e-05, + "loss": 3.379, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562239126603569e-05, + "loss": 3.3891, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3553853179093049e-05, + "loss": 3.3794, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545467231582525e-05, + "loss": 3.3777, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.353709766287574e-05, + "loss": 3.382, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.352871171536522e-05, + "loss": 3.3777, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.35203257678547e-05, + "loss": 3.3705, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3511939820344178e-05, + "loss": 3.3774, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.350357025163739e-05, + "loss": 3.3828, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.349518430412687e-05, + "loss": 3.3887, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.348679835661635e-05, + "loss": 3.3832, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3478412409105828e-05, + "loss": 3.3784, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.347004284039904e-05, + "loss": 3.3736, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461656892888522e-05, + "loss": 3.3926, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3453270945377999e-05, + "loss": 3.3677, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3444884997867479e-05, + "loss": 3.3842, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3436515429160693e-05, + "loss": 3.3767, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3428129481650173e-05, + "loss": 3.3714, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.341974353413965e-05, + "loss": 3.3767, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3411357586629131e-05, + "loss": 3.3895, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3402988017922344e-05, + "loss": 3.381, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394602070411822e-05, + "loss": 3.3756, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386216122901302e-05, + "loss": 3.3824, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3377830175390782e-05, + "loss": 3.3754, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3369460606683994e-05, + "loss": 3.3837, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3361074659173473e-05, + "loss": 3.3599, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3352688711662953e-05, + "loss": 3.3796, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3344302764152433e-05, + "loss": 3.3754, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3335933195445647e-05, + "loss": 3.3891, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3327547247935123e-05, + "loss": 3.3689, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3319161300424603e-05, + "loss": 3.3759, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3310775352914085e-05, + "loss": 3.3588, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302405784207294e-05, + "loss": 3.3696, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3294019836696776e-05, + "loss": 3.3848, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285633889186256e-05, + "loss": 3.3598, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277264320479468e-05, + "loss": 3.3856, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268878372968946e-05, + "loss": 3.3748, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260492425458426e-05, + "loss": 3.3688, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3252106477947906e-05, + "loss": 3.39, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243736909241119e-05, + "loss": 3.365, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235350961730597e-05, + "loss": 3.3652, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226965014220077e-05, + "loss": 3.3722, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3218579066709557e-05, + "loss": 3.3818, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3210209498002768e-05, + "loss": 3.3658, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3201823550492248e-05, + "loss": 3.3723, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.319343760298173e-05, + "loss": 3.3588, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.318505165547121e-05, + "loss": 3.3733, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176682086764418e-05, + "loss": 3.3767, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.31682961392539e-05, + "loss": 3.3863, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.315991019174338e-05, + "loss": 3.3766, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.315152424423286e-05, + "loss": 3.3783, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.314315467552607e-05, + "loss": 3.3928, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.313476872801555e-05, + "loss": 3.378, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.312638278050503e-05, + "loss": 3.3846, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3118013211798241e-05, + "loss": 3.3762, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3109627264287721e-05, + "loss": 3.3755, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3101241316777201e-05, + "loss": 3.3709, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3092855369266683e-05, + "loss": 3.3826, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3084469421756163e-05, + "loss": 3.3748, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3076083474245643e-05, + "loss": 3.3887, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3067697526735123e-05, + "loss": 3.3742, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3059311579224601e-05, + "loss": 3.3625, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3050942010517814e-05, + "loss": 3.3704, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3042556063007294e-05, + "loss": 3.3785, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3034170115496774e-05, + "loss": 3.3683, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3025784167986252e-05, + "loss": 3.3782, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3017414599279464e-05, + "loss": 3.3748, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3009028651768946e-05, + "loss": 3.3697, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3000642704258423e-05, + "loss": 3.3711, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2992256756747903e-05, + "loss": 3.3729, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2983887188041117e-05, + "loss": 3.377, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975501240530597e-05, + "loss": 3.3832, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2967115293020073e-05, + "loss": 3.384, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2958729345509555e-05, + "loss": 3.3651, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2950359776802767e-05, + "loss": 3.379, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2941973829292247e-05, + "loss": 3.3701, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933587881781726e-05, + "loss": 3.3791, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925201934271206e-05, + "loss": 3.3776, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2916832365564418e-05, + "loss": 3.3682, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2908446418053896e-05, + "loss": 3.3796, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2900060470543376e-05, + "loss": 3.3742, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2891674523032856e-05, + "loss": 3.3717, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.288330495432607e-05, + "loss": 3.3693, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2874919006815547e-05, + "loss": 3.3683, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866533059305027e-05, + "loss": 3.3784, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2858147111794509e-05, + "loss": 3.3752, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2849777543087721e-05, + "loss": 3.3642, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.28413915955772e-05, + "loss": 3.3649, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.283300564806668e-05, + "loss": 3.3691, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.282461970055616e-05, + "loss": 3.3844, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.281625013184937e-05, + "loss": 3.3717, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.280786418433885e-05, + "loss": 3.3745, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.279947823682833e-05, + "loss": 3.3799, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.279109228931781e-05, + "loss": 3.3836, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.278272272061102e-05, + "loss": 3.3773, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.27743367731005e-05, + "loss": 3.3769, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.276595082558998e-05, + "loss": 3.3776, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2757564878079462e-05, + "loss": 3.3785, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2749195309372671e-05, + "loss": 3.3638, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2740809361862153e-05, + "loss": 3.3705, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2732423414351633e-05, + "loss": 3.366, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2724053845644842e-05, + "loss": 3.3776, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2715667898134324e-05, + "loss": 3.375, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2707281950623804e-05, + "loss": 3.3699, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2698896003113284e-05, + "loss": 3.3626, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690526434406494e-05, + "loss": 3.3697, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2682140486895974e-05, + "loss": 3.3811, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2673754539385454e-05, + "loss": 3.3774, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2665368591874934e-05, + "loss": 3.3832, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656999023168145e-05, + "loss": 3.3683, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648613075657625e-05, + "loss": 3.3825, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640227128147105e-05, + "loss": 3.3809, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2631841180636587e-05, + "loss": 3.3756, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2623471611929796e-05, + "loss": 3.3696, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2615085664419277e-05, + "loss": 3.373, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606699716908757e-05, + "loss": 3.3803, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598313769398237e-05, + "loss": 3.3843, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589944200691448e-05, + "loss": 3.3696, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2581558253180928e-05, + "loss": 3.37, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2573172305670408e-05, + "loss": 3.3761, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2564786358159888e-05, + "loss": 3.3721, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2556416789453099e-05, + "loss": 3.3665, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2548047220746311e-05, + "loss": 3.3832, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.253966127323579e-05, + "loss": 3.3758, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.253127532572527e-05, + "loss": 3.383, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.252288937821475e-05, + "loss": 3.3624, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.8633034229278564, + "eval_runtime": 304.3131, + "eval_samples_per_second": 1253.942, + "eval_steps_per_second": 39.187, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514503430704231e-05, + "loss": 3.3846, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2506117483193711e-05, + "loss": 3.3692, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.249773153568319e-05, + "loss": 3.372, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2489345588172669e-05, + "loss": 3.3784, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2480976019465882e-05, + "loss": 3.3769, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472590071955362e-05, + "loss": 3.3752, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2464204124444842e-05, + "loss": 3.3699, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2455818176934321e-05, + "loss": 3.3745, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447448608227532e-05, + "loss": 3.367, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2439079039520745e-05, + "loss": 3.3764, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2430693092010223e-05, + "loss": 3.3745, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422307144499703e-05, + "loss": 3.3774, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2413921196989185e-05, + "loss": 3.3772, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2405535249478663e-05, + "loss": 3.3585, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2397149301968143e-05, + "loss": 3.3647, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2388763354457623e-05, + "loss": 3.3611, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380377406947103e-05, + "loss": 3.3804, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2372007838240314e-05, + "loss": 3.3649, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2363621890729794e-05, + "loss": 3.3683, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2355235943219275e-05, + "loss": 3.3758, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2346849995708753e-05, + "loss": 3.381, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338480427001966e-05, + "loss": 3.3781, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2330094479491446e-05, + "loss": 3.3735, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2321708531980926e-05, + "loss": 3.3718, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313322584470404e-05, + "loss": 3.3816, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2304953015763617e-05, + "loss": 3.3663, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296567068253097e-05, + "loss": 3.3731, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2288181120742576e-05, + "loss": 3.3745, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2279795173232056e-05, + "loss": 3.3648, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271425604525267e-05, + "loss": 3.3611, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2263039657014747e-05, + "loss": 3.3673, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2254653709504227e-05, + "loss": 3.3713, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2246267761993707e-05, + "loss": 3.3821, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.223789819328692e-05, + "loss": 3.3737, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.22295122457764e-05, + "loss": 3.3663, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2221126298265878e-05, + "loss": 3.367, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2212740350755358e-05, + "loss": 3.378, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.220435440324484e-05, + "loss": 3.3595, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2195968455734318e-05, + "loss": 3.3745, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2187582508223798e-05, + "loss": 3.3631, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.217921293951701e-05, + "loss": 3.3628, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.217082699200649e-05, + "loss": 3.3668, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2162441044495968e-05, + "loss": 3.3873, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.215405509698545e-05, + "loss": 3.3665, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.214568552827866e-05, + "loss": 3.3636, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2137299580768139e-05, + "loss": 3.3699, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.212891363325762e-05, + "loss": 3.3674, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.21205276857471e-05, + "loss": 3.3711, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2112158117040311e-05, + "loss": 3.3535, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2103772169529791e-05, + "loss": 3.3704, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2095386222019271e-05, + "loss": 3.3685, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2087000274508751e-05, + "loss": 3.3777, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078630705801962e-05, + "loss": 3.3587, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070244758291442e-05, + "loss": 3.3633, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2061858810780922e-05, + "loss": 3.3569, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053472863270402e-05, + "loss": 3.3543, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2045103294563613e-05, + "loss": 3.3764, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2036717347053093e-05, + "loss": 3.3525, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028331399542574e-05, + "loss": 3.3743, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2019945452032053e-05, + "loss": 3.3664, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2011575883325263e-05, + "loss": 3.3613, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003189935814745e-05, + "loss": 3.3797, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1994803988304225e-05, + "loss": 3.3582, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986418040793703e-05, + "loss": 3.3602, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1978048472086916e-05, + "loss": 3.3561, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969662524576396e-05, + "loss": 3.3761, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961276577065876e-05, + "loss": 3.36, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1952890629555356e-05, + "loss": 3.3569, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944521060848566e-05, + "loss": 3.3564, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1936135113338046e-05, + "loss": 3.3577, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1927749165827526e-05, + "loss": 3.3707, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919363218317006e-05, + "loss": 3.374, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1910993649610217e-05, + "loss": 3.3659, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1902607702099699e-05, + "loss": 3.3703, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1894221754589177e-05, + "loss": 3.3832, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1885835807078657e-05, + "loss": 3.3683, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.187746623837187e-05, + "loss": 3.375, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.186909666966508e-05, + "loss": 3.3689, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.186071072215456e-05, + "loss": 3.3685, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.185232477464404e-05, + "loss": 3.3634, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184393882713352e-05, + "loss": 3.3705, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835552879623e-05, + "loss": 3.3698, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.182716693211248e-05, + "loss": 3.3759, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.181878098460196e-05, + "loss": 3.3668, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.181039503709144e-05, + "loss": 3.3505, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.180202546838465e-05, + "loss": 3.3595, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.179363952087413e-05, + "loss": 3.3696, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.178525357336361e-05, + "loss": 3.3602, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.177686762585309e-05, + "loss": 3.3693, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1768498057146301e-05, + "loss": 3.3663, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1760112109635781e-05, + "loss": 3.3587, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1751726162125263e-05, + "loss": 3.3561, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743340214614741e-05, + "loss": 3.3638, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1734970645907952e-05, + "loss": 3.3671, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1726584698397434e-05, + "loss": 3.3718, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718198750886914e-05, + "loss": 3.369, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1709812803376392e-05, + "loss": 3.3559, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701443234669604e-05, + "loss": 3.3672, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1693057287159084e-05, + "loss": 3.3631, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684671339648563e-05, + "loss": 3.3656, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676285392138044e-05, + "loss": 3.3676, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1667915823431255e-05, + "loss": 3.3567, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659529875920735e-05, + "loss": 3.3692, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1651160307213946e-05, + "loss": 3.3662, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1642774359703426e-05, + "loss": 3.3629, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634388412192906e-05, + "loss": 3.3569, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1626002464682387e-05, + "loss": 3.3592, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1617616517171866e-05, + "loss": 3.3676, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609230569661346e-05, + "loss": 3.3696, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1600844622150825e-05, + "loss": 3.355, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592458674640305e-05, + "loss": 3.3556, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1584089105933516e-05, + "loss": 3.3564, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1575703158422998e-05, + "loss": 3.3771, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567317210912478e-05, + "loss": 3.3632, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1558931263401956e-05, + "loss": 3.3626, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1550561694695169e-05, + "loss": 3.3727, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1542175747184649e-05, + "loss": 3.3731, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1533789799674127e-05, + "loss": 3.3662, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525403852163608e-05, + "loss": 3.3697, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.151703428345682e-05, + "loss": 3.3708, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.15086483359463e-05, + "loss": 3.3667, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1500262388435779e-05, + "loss": 3.3558, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1491876440925259e-05, + "loss": 3.3599, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.148350687221847e-05, + "loss": 3.361, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.147512092470795e-05, + "loss": 3.3646, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.146673497719743e-05, + "loss": 3.3638, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.145834902968691e-05, + "loss": 3.3611, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1449979460980122e-05, + "loss": 3.3572, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.14415935134696e-05, + "loss": 3.3634, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.143320756595908e-05, + "loss": 3.3647, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.142482161844856e-05, + "loss": 3.3716, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1416452049741773e-05, + "loss": 3.376, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1408066102231251e-05, + "loss": 3.357, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1399680154720733e-05, + "loss": 3.3703, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391294207210213e-05, + "loss": 3.3704, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1382924638503424e-05, + "loss": 3.3691, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374538690992904e-05, + "loss": 3.3613, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1366152743482383e-05, + "loss": 3.3665, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1357783174775594e-05, + "loss": 3.3703, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1349397227265074e-05, + "loss": 3.3723, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1341011279754554e-05, + "loss": 3.3607, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1332625332244034e-05, + "loss": 3.3645, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324255763537247e-05, + "loss": 3.3669, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1315869816026725e-05, + "loss": 3.3613, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307483868516205e-05, + "loss": 3.3563, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1299114299809417e-05, + "loss": 3.3723, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1290728352298896e-05, + "loss": 3.3659, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282342404788376e-05, + "loss": 3.3741, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1273956457277857e-05, + "loss": 3.3544, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.865121364593506, + "eval_runtime": 302.9628, + "eval_samples_per_second": 1259.531, + "eval_steps_per_second": 39.361, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1265570509767337e-05, + "loss": 3.3637, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1257184562256815e-05, + "loss": 3.3613, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1248798614746297e-05, + "loss": 3.3612, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240412667235777e-05, + "loss": 3.3705, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1232043098528986e-05, + "loss": 3.3663, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1223657151018468e-05, + "loss": 3.3688, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215271203507948e-05, + "loss": 3.3591, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1206901634801158e-05, + "loss": 3.3622, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198515687290638e-05, + "loss": 3.361, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1190129739780118e-05, + "loss": 3.3662, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1181743792269598e-05, + "loss": 3.3617, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173374223562811e-05, + "loss": 3.3715, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1164988276052289e-05, + "loss": 3.3702, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1156602328541769e-05, + "loss": 3.3507, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1148216381031249e-05, + "loss": 3.3518, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.113984681232446e-05, + "loss": 3.3567, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.113146086481394e-05, + "loss": 3.3663, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1123074917303421e-05, + "loss": 3.3619, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1114688969792901e-05, + "loss": 3.3557, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.110631940108611e-05, + "loss": 3.3615, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1097933453575592e-05, + "loss": 3.3681, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1089547506065072e-05, + "loss": 3.3689, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.108116155855455e-05, + "loss": 3.3621, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1072791989847763e-05, + "loss": 3.3622, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064406042337243e-05, + "loss": 3.3771, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1056020094826723e-05, + "loss": 3.3543, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1047634147316203e-05, + "loss": 3.3638, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1039264578609413e-05, + "loss": 3.365, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1030878631098893e-05, + "loss": 3.3542, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1022492683588375e-05, + "loss": 3.3556, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1014106736077853e-05, + "loss": 3.3541, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1005737167371064e-05, + "loss": 3.3632, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0997351219860546e-05, + "loss": 3.3701, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0988965272350024e-05, + "loss": 3.3644, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0980579324839504e-05, + "loss": 3.3577, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0972209756132716e-05, + "loss": 3.3557, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0963823808622196e-05, + "loss": 3.369, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0955437861111675e-05, + "loss": 3.3532, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0947051913601156e-05, + "loss": 3.3651, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0938682344894367e-05, + "loss": 3.3529, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0930296397383847e-05, + "loss": 3.3535, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0921910449873327e-05, + "loss": 3.3567, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913524502362807e-05, + "loss": 3.3756, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0905154933656018e-05, + "loss": 3.352, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0896768986145498e-05, + "loss": 3.3591, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0888383038634978e-05, + "loss": 3.3623, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0879997091124458e-05, + "loss": 3.3591, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.087162752241767e-05, + "loss": 3.3604, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0863241574907148e-05, + "loss": 3.3405, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0854855627396628e-05, + "loss": 3.3594, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.084646967988611e-05, + "loss": 3.3614, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0838100111179319e-05, + "loss": 3.3651, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0829714163668799e-05, + "loss": 3.35, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.082132821615828e-05, + "loss": 3.3487, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.081294226864776e-05, + "loss": 3.3514, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0804572699940971e-05, + "loss": 3.3435, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0796186752430451e-05, + "loss": 3.3713, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0787800804919931e-05, + "loss": 3.3422, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.077941485740941e-05, + "loss": 3.3605, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0771045288702622e-05, + "loss": 3.3575, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0762659341192102e-05, + "loss": 3.3525, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0754273393681582e-05, + "loss": 3.3672, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0745887446171062e-05, + "loss": 3.3518, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737517877464273e-05, + "loss": 3.3511, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0729131929953753e-05, + "loss": 3.3469, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0720745982443234e-05, + "loss": 3.3677, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712376413736443e-05, + "loss": 3.3488, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0703990466225925e-05, + "loss": 3.3466, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0695604518715405e-05, + "loss": 3.3456, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0687218571204883e-05, + "loss": 3.3523, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0678849002498096e-05, + "loss": 3.362, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670463054987576e-05, + "loss": 3.3648, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0662077107477056e-05, + "loss": 3.3514, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0653707538770267e-05, + "loss": 3.363, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0645321591259747e-05, + "loss": 3.3724, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0636935643749226e-05, + "loss": 3.3633, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628549696238706e-05, + "loss": 3.3599, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0620180127531917e-05, + "loss": 3.3597, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0611794180021397e-05, + "loss": 3.3577, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0603408232510879e-05, + "loss": 3.3559, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0595022285000357e-05, + "loss": 3.3544, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0586636337489837e-05, + "loss": 3.3641, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0578250389979317e-05, + "loss": 3.3663, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0569864442468799e-05, + "loss": 3.3619, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0561478494958277e-05, + "loss": 3.3405, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0553108926251488e-05, + "loss": 3.3485, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.054472297874097e-05, + "loss": 3.3604, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0536337031230448e-05, + "loss": 3.3526, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0527951083719928e-05, + "loss": 3.361, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.051958151501314e-05, + "loss": 3.3559, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.051119556750262e-05, + "loss": 3.3509, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0502809619992098e-05, + "loss": 3.3447, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.049442367248158e-05, + "loss": 3.3568, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.048605410377479e-05, + "loss": 3.3563, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.047766815626427e-05, + "loss": 3.3619, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.046928220875375e-05, + "loss": 3.3623, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.046089626124323e-05, + "loss": 3.3427, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452526692536441e-05, + "loss": 3.3605, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0444140745025921e-05, + "loss": 3.3539, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0435754797515401e-05, + "loss": 3.3584, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427368850004881e-05, + "loss": 3.3599, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0418999281298094e-05, + "loss": 3.35, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0410613333787572e-05, + "loss": 3.355, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0402243765080784e-05, + "loss": 3.3587, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0393857817570264e-05, + "loss": 3.3559, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385471870059744e-05, + "loss": 3.347, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0377085922549223e-05, + "loss": 3.3509, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0368699975038704e-05, + "loss": 3.3586, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360314027528184e-05, + "loss": 3.359, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0351928080017662e-05, + "loss": 3.3427, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343542132507142e-05, + "loss": 3.3474, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0335172563800355e-05, + "loss": 3.3446, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0326786616289835e-05, + "loss": 3.3666, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318400668779315e-05, + "loss": 3.3544, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0310014721268795e-05, + "loss": 3.3546, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0301645152562006e-05, + "loss": 3.3643, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0293259205051486e-05, + "loss": 3.3648, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0284873257540965e-05, + "loss": 3.3568, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276487310030445e-05, + "loss": 3.3609, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0268117741323658e-05, + "loss": 3.3618, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0259731793813136e-05, + "loss": 3.3538, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251345846302616e-05, + "loss": 3.3473, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0242959898792096e-05, + "loss": 3.3516, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0234590330085309e-05, + "loss": 3.3484, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0226204382574787e-05, + "loss": 3.3543, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0217818435064269e-05, + "loss": 3.3507, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209432487553748e-05, + "loss": 3.3564, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0201062918846958e-05, + "loss": 3.3489, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.019267697133644e-05, + "loss": 3.3521, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.018429102382592e-05, + "loss": 3.3537, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0175905076315397e-05, + "loss": 3.3642, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.016753550760861e-05, + "loss": 3.3659, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.015914956009809e-05, + "loss": 3.3549, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.015076361258757e-05, + "loss": 3.3547, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.014237766507705e-05, + "loss": 3.3583, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.013400809637026e-05, + "loss": 3.3573, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.012562214885974e-05, + "loss": 3.355, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0117236201349222e-05, + "loss": 3.3558, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.01088502538387e-05, + "loss": 3.3625, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100480685131911e-05, + "loss": 3.3603, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0092094737621393e-05, + "loss": 3.3552, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0083708790110871e-05, + "loss": 3.353, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0075322842600351e-05, + "loss": 3.3547, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0066953273893564e-05, + "loss": 3.354, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0058567326383044e-05, + "loss": 3.3458, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0050197757676254e-05, + "loss": 3.3645, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0041811810165734e-05, + "loss": 3.3569, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033425862655214e-05, + "loss": 3.3616, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0025039915144694e-05, + "loss": 3.346, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0016653967634174e-05, + "loss": 3.3519, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.864434003829956, + "eval_runtime": 302.9128, + "eval_samples_per_second": 1259.739, + "eval_steps_per_second": 39.368, + "step": 2442240 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7002654837232763e+18, + "trial_name": null, + "trial_params": null +}