| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9982255399865387, | |
| "global_step": 49000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.001979603907891248, | |
| "loss": 0.0528, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0019592078157824964, | |
| "loss": 0.0543, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0019388117236737441, | |
| "loss": 0.0531, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.001918415631564992, | |
| "loss": 0.0534, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0018980195394562402, | |
| "loss": 0.0528, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0018776234473474882, | |
| "loss": 0.052, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0018572273552387361, | |
| "loss": 0.0518, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0018368312631299843, | |
| "loss": 0.0509, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0018164351710212323, | |
| "loss": 0.0507, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0017960390789124802, | |
| "loss": 0.049, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0017756429868037286, | |
| "loss": 0.0487, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0017552468946949765, | |
| "loss": 0.0484, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0017348508025862245, | |
| "loss": 0.0498, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0017144547104774727, | |
| "loss": 0.0507, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0016940586183687206, | |
| "loss": 0.0467, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0016736625262599688, | |
| "loss": 0.0469, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0016532664341512167, | |
| "loss": 0.0473, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0016328703420424647, | |
| "loss": 0.047, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0016124742499337129, | |
| "loss": 0.0465, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0015920781578249608, | |
| "loss": 0.0461, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0015716820657162088, | |
| "loss": 0.045, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.001551285973607457, | |
| "loss": 0.0468, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0015308898814987049, | |
| "loss": 0.0445, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0015104937893899528, | |
| "loss": 0.0443, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.001490097697281201, | |
| "loss": 0.0439, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.001469701605172449, | |
| "loss": 0.0437, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.001449305513063697, | |
| "loss": 0.0432, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.001428909420954945, | |
| "loss": 0.0434, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.001408513328846193, | |
| "loss": 0.044, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.001388117236737441, | |
| "loss": 0.0433, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0013677211446286891, | |
| "loss": 0.0427, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.001347325052519937, | |
| "loss": 0.043, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.03870956972241402, | |
| "eval_runtime": 667.1114, | |
| "eval_samples_per_second": 146.987, | |
| "eval_steps_per_second": 6.125, | |
| "step": 16343 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0013269289604111853, | |
| "loss": 0.0404, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0013065328683024334, | |
| "loss": 0.037, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0012861367761936814, | |
| "loss": 0.0371, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0012657406840849293, | |
| "loss": 0.0372, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0012453445919761775, | |
| "loss": 0.0386, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0012249484998674255, | |
| "loss": 0.0377, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0012045524077586734, | |
| "loss": 0.0385, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0011841563156499216, | |
| "loss": 0.0377, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0011637602235411695, | |
| "loss": 0.0378, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0011433641314324175, | |
| "loss": 0.0364, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0011229680393236656, | |
| "loss": 0.0372, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0011025719472149136, | |
| "loss": 0.0372, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0010821758551061618, | |
| "loss": 0.0387, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0010617797629974097, | |
| "loss": 0.0387, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0010413836708886577, | |
| "loss": 0.0387, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0010209875787799058, | |
| "loss": 0.0363, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0010005914866711538, | |
| "loss": 0.0385, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0009801953945624017, | |
| "loss": 0.0387, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0009597993024536499, | |
| "loss": 0.0381, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.000939403210344898, | |
| "loss": 0.039, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.000919007118236146, | |
| "loss": 0.0369, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.000898611026127394, | |
| "loss": 0.0372, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.000878214934018642, | |
| "loss": 0.0379, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0008578188419098901, | |
| "loss": 0.0367, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0008374227498011381, | |
| "loss": 0.0361, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0008170266576923861, | |
| "loss": 0.0364, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0007966305655836342, | |
| "loss": 0.0361, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0007762344734748822, | |
| "loss": 0.0359, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0007558383813661303, | |
| "loss": 0.0357, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0007354422892573784, | |
| "loss": 0.0358, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0007150461971486263, | |
| "loss": 0.0357, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0006946501050398744, | |
| "loss": 0.0352, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0006742540129311224, | |
| "loss": 0.0351, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.03284740820527077, | |
| "eval_runtime": 666.0258, | |
| "eval_samples_per_second": 147.227, | |
| "eval_steps_per_second": 6.135, | |
| "step": 32686 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0006538579208223705, | |
| "loss": 0.0325, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0006334618287136184, | |
| "loss": 0.0314, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0006130657366048665, | |
| "loss": 0.0308, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0005926696444961146, | |
| "loss": 0.0315, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0005722735523873625, | |
| "loss": 0.0308, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0005518774602786107, | |
| "loss": 0.0306, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0005314813681698587, | |
| "loss": 0.0309, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0005110852760611067, | |
| "loss": 0.0304, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0004906891839523547, | |
| "loss": 0.0306, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00047029309184360276, | |
| "loss": 0.0307, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0004498969997348508, | |
| "loss": 0.0296, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0004295009076260988, | |
| "loss": 0.0302, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0004091048155173469, | |
| "loss": 0.0299, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00038870872340859494, | |
| "loss": 0.0297, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.00036831263129984295, | |
| "loss": 0.0292, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.000347916539191091, | |
| "loss": 0.0302, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.000327520447082339, | |
| "loss": 0.0295, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0003071243549735871, | |
| "loss": 0.0295, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00028672826286483513, | |
| "loss": 0.0289, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00026633217075608314, | |
| "loss": 0.0297, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00024593607864733115, | |
| "loss": 0.0291, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002255399865385792, | |
| "loss": 0.0288, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00020514389442982727, | |
| "loss": 0.0278, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0001847478023210753, | |
| "loss": 0.0284, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0001643517102123233, | |
| "loss": 0.0285, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.00014395561810357136, | |
| "loss": 0.0278, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0001235595259948194, | |
| "loss": 0.0286, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.00010316343388606743, | |
| "loss": 0.028, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.276734177731548e-05, | |
| "loss": 0.0279, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 6.23712496685635e-05, | |
| "loss": 0.0286, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 4.197515755981154e-05, | |
| "loss": 0.0278, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.157906545105958e-05, | |
| "loss": 0.0279, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.1829733423076138e-06, | |
| "loss": 0.0277, | |
| "step": 49000 | |
| } | |
| ], | |
| "max_steps": 49029, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.591600637458514e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |