| { | |
| "best_metric": 6.703342437744141, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0353198686697841, | |
| "eval_steps": 25, | |
| "global_step": 71, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004974629390110437, | |
| "grad_norm": 2.0978946685791016, | |
| "learning_rate": 0.00015, | |
| "loss": 6.9589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004974629390110437, | |
| "eval_loss": 6.9487104415893555, | |
| "eval_runtime": 0.0398, | |
| "eval_samples_per_second": 1255.231, | |
| "eval_steps_per_second": 75.314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009949258780220873, | |
| "grad_norm": 0.784283459186554, | |
| "learning_rate": 0.0003, | |
| "loss": 6.9495, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014923888170331311, | |
| "grad_norm": 1.2301733493804932, | |
| "learning_rate": 0.0002998600959423082, | |
| "loss": 6.9501, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019898517560441747, | |
| "grad_norm": 1.3414157629013062, | |
| "learning_rate": 0.0002994406737417567, | |
| "loss": 6.947, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024873146950552183, | |
| "grad_norm": 1.5272213220596313, | |
| "learning_rate": 0.00029874260271490463, | |
| "loss": 6.9409, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029847776340662623, | |
| "grad_norm": 1.9261209964752197, | |
| "learning_rate": 0.00029776732972055516, | |
| "loss": 6.9326, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003482240573077306, | |
| "grad_norm": 1.9587503671646118, | |
| "learning_rate": 0.0002965168761609197, | |
| "loss": 6.9088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003979703512088349, | |
| "grad_norm": 0.8569906949996948, | |
| "learning_rate": 0.0002949938337919529, | |
| "loss": 6.9137, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004477166451099393, | |
| "grad_norm": 1.1164758205413818, | |
| "learning_rate": 0.0002932013593515431, | |
| "loss": 6.9299, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0049746293901104365, | |
| "grad_norm": 1.2469490766525269, | |
| "learning_rate": 0.00029114316801669057, | |
| "loss": 6.8841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0054720923291214805, | |
| "grad_norm": 1.5062528848648071, | |
| "learning_rate": 0.00028882352570323616, | |
| "loss": 6.8565, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0059695552681325245, | |
| "grad_norm": 1.8433338403701782, | |
| "learning_rate": 0.00028624724022409897, | |
| "loss": 6.822, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006467018207143568, | |
| "grad_norm": 1.1858328580856323, | |
| "learning_rate": 0.0002834196513243502, | |
| "loss": 6.8764, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006964481146154612, | |
| "grad_norm": 1.0784205198287964, | |
| "learning_rate": 0.0002803466196137759, | |
| "loss": 6.8753, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007461944085165655, | |
| "grad_norm": 0.946907639503479, | |
| "learning_rate": 0.00027703451441986836, | |
| "loss": 6.8735, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007959407024176699, | |
| "grad_norm": 1.3893108367919922, | |
| "learning_rate": 0.000273490200586422, | |
| "loss": 6.8587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008456869963187742, | |
| "grad_norm": 0.709138810634613, | |
| "learning_rate": 0.00026972102424509665, | |
| "loss": 6.8263, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008954332902198787, | |
| "grad_norm": 1.2287291288375854, | |
| "learning_rate": 0.00026573479758943753, | |
| "loss": 6.7822, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00945179584120983, | |
| "grad_norm": 1.5594730377197266, | |
| "learning_rate": 0.0002615397826829114, | |
| "loss": 6.7248, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009949258780220873, | |
| "grad_norm": 1.0414823293685913, | |
| "learning_rate": 0.0002571446743345183, | |
| "loss": 6.8372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010446721719231918, | |
| "grad_norm": 1.1876541376113892, | |
| "learning_rate": 0.00025255858207747205, | |
| "loss": 6.8816, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010944184658242961, | |
| "grad_norm": 1.0211689472198486, | |
| "learning_rate": 0.0002477910112883017, | |
| "loss": 6.836, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011441647597254004, | |
| "grad_norm": 1.1104573011398315, | |
| "learning_rate": 0.00024285184348550706, | |
| "loss": 6.7411, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011939110536265049, | |
| "grad_norm": 1.2712668180465698, | |
| "learning_rate": 0.0002377513158486027, | |
| "loss": 6.6863, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012436573475276092, | |
| "grad_norm": 1.0742238759994507, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 6.7343, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012436573475276092, | |
| "eval_loss": 6.77644157409668, | |
| "eval_runtime": 0.0409, | |
| "eval_samples_per_second": 1222.387, | |
| "eval_steps_per_second": 73.343, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012934036414287135, | |
| "grad_norm": 1.5590488910675049, | |
| "learning_rate": 0.00022710878009370554, | |
| "loss": 6.8274, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013431499353298178, | |
| "grad_norm": 0.6883417367935181, | |
| "learning_rate": 0.00022158883025624965, | |
| "loss": 6.8454, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013928962292309223, | |
| "grad_norm": 1.1368870735168457, | |
| "learning_rate": 0.0002159515914266029, | |
| "loss": 6.8375, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014426425231320266, | |
| "grad_norm": 0.9605547785758972, | |
| "learning_rate": 0.0002102087476430831, | |
| "loss": 6.8131, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01492388817033131, | |
| "grad_norm": 1.0653886795043945, | |
| "learning_rate": 0.00020437220182640135, | |
| "loss": 6.71, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015421351109342354, | |
| "grad_norm": 1.2283194065093994, | |
| "learning_rate": 0.00019845405110904146, | |
| "loss": 6.6504, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015918814048353398, | |
| "grad_norm": 0.8201404213905334, | |
| "learning_rate": 0.00019246656176210558, | |
| "loss": 6.7202, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01641627698736444, | |
| "grad_norm": 0.8443421125411987, | |
| "learning_rate": 0.0001864221437715939, | |
| "loss": 6.8298, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016913739926375484, | |
| "grad_norm": 1.0041660070419312, | |
| "learning_rate": 0.0001803333251168141, | |
| "loss": 6.8294, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01741120286538653, | |
| "grad_norm": 0.729718804359436, | |
| "learning_rate": 0.00017421272580423058, | |
| "loss": 6.7173, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017908665804397574, | |
| "grad_norm": 0.9453200101852417, | |
| "learning_rate": 0.00016807303171057425, | |
| "loss": 6.6455, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018406128743408617, | |
| "grad_norm": 1.152786135673523, | |
| "learning_rate": 0.00016192696828942573, | |
| "loss": 6.5751, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01890359168241966, | |
| "grad_norm": 1.0720747709274292, | |
| "learning_rate": 0.00015578727419576942, | |
| "loss": 6.8176, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019401054621430703, | |
| "grad_norm": 1.0019649267196655, | |
| "learning_rate": 0.00014966667488318586, | |
| "loss": 6.8212, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019898517560441746, | |
| "grad_norm": 1.0470595359802246, | |
| "learning_rate": 0.00014357785622840606, | |
| "loss": 6.8254, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02039598049945279, | |
| "grad_norm": 1.326593279838562, | |
| "learning_rate": 0.00013753343823789445, | |
| "loss": 6.7906, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020893443438463836, | |
| "grad_norm": 0.5931538939476013, | |
| "learning_rate": 0.00013154594889095854, | |
| "loss": 6.7336, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02139090637747488, | |
| "grad_norm": 0.9888867735862732, | |
| "learning_rate": 0.00012562779817359865, | |
| "loss": 6.6365, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021888369316485922, | |
| "grad_norm": 1.1606509685516357, | |
| "learning_rate": 0.00011979125235691685, | |
| "loss": 6.5585, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022385832255496965, | |
| "grad_norm": 0.9471900463104248, | |
| "learning_rate": 0.00011404840857339706, | |
| "loss": 6.7794, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02288329519450801, | |
| "grad_norm": 1.0708708763122559, | |
| "learning_rate": 0.0001084111697437504, | |
| "loss": 6.8215, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02338075813351905, | |
| "grad_norm": 0.7427545785903931, | |
| "learning_rate": 0.00010289121990629447, | |
| "loss": 6.7288, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023878221072530098, | |
| "grad_norm": 0.9723594188690186, | |
| "learning_rate": 9.750000000000003e-05, | |
| "loss": 6.6319, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02437568401154114, | |
| "grad_norm": 0.9104545712471008, | |
| "learning_rate": 9.22486841513973e-05, | |
| "loss": 6.5588, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024873146950552184, | |
| "grad_norm": 0.8541779518127441, | |
| "learning_rate": 8.714815651449293e-05, | |
| "loss": 6.6375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024873146950552184, | |
| "eval_loss": 6.703342437744141, | |
| "eval_runtime": 0.0414, | |
| "eval_samples_per_second": 1208.754, | |
| "eval_steps_per_second": 72.525, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025370609889563227, | |
| "grad_norm": 1.8086193799972534, | |
| "learning_rate": 8.220898871169827e-05, | |
| "loss": 6.8079, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02586807282857427, | |
| "grad_norm": 0.7370948195457458, | |
| "learning_rate": 7.744141792252794e-05, | |
| "loss": 6.8023, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.026365535767585314, | |
| "grad_norm": 1.0690277814865112, | |
| "learning_rate": 7.285532566548172e-05, | |
| "loss": 6.7905, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.026862998706596357, | |
| "grad_norm": 1.2137597799301147, | |
| "learning_rate": 6.846021731708856e-05, | |
| "loss": 6.77, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.027360461645607403, | |
| "grad_norm": 0.7531571984291077, | |
| "learning_rate": 6.426520241056245e-05, | |
| "loss": 6.661, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.027857924584618447, | |
| "grad_norm": 0.8767682313919067, | |
| "learning_rate": 6.0278975754903317e-05, | |
| "loss": 6.6017, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02835538752362949, | |
| "grad_norm": 0.7823953628540039, | |
| "learning_rate": 5.6509799413577934e-05, | |
| "loss": 6.5955, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.028852850462640533, | |
| "grad_norm": 0.8727318048477173, | |
| "learning_rate": 5.296548558013161e-05, | |
| "loss": 6.7922, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.029350313401651576, | |
| "grad_norm": 0.996519148349762, | |
| "learning_rate": 4.9653380386224046e-05, | |
| "loss": 6.7956, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.02984777634066262, | |
| "grad_norm": 0.6733922362327576, | |
| "learning_rate": 4.658034867564977e-05, | |
| "loss": 6.6694, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.030345239279673666, | |
| "grad_norm": 0.8655278086662292, | |
| "learning_rate": 4.375275977590104e-05, | |
| "loss": 6.5892, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03084270221868471, | |
| "grad_norm": 0.9837325811386108, | |
| "learning_rate": 4.117647429676387e-05, | |
| "loss": 6.5165, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03134016515769575, | |
| "grad_norm": 1.1237236261367798, | |
| "learning_rate": 3.885683198330941e-05, | |
| "loss": 6.7888, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.031837628096706795, | |
| "grad_norm": 1.0909230709075928, | |
| "learning_rate": 3.679864064845691e-05, | |
| "loss": 6.8041, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03233509103571784, | |
| "grad_norm": 0.9223988652229309, | |
| "learning_rate": 3.500616620804712e-05, | |
| "loss": 6.7929, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03283255397472888, | |
| "grad_norm": 1.2748134136199951, | |
| "learning_rate": 3.348312383908033e-05, | |
| "loss": 6.7633, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03333001691373993, | |
| "grad_norm": 0.5331524014472961, | |
| "learning_rate": 3.223267027944483e-05, | |
| "loss": 6.7201, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.03382747985275097, | |
| "grad_norm": 0.9274587035179138, | |
| "learning_rate": 3.125739728509535e-05, | |
| "loss": 6.6011, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.034324942791762014, | |
| "grad_norm": 1.011277198791504, | |
| "learning_rate": 3.055932625824328e-05, | |
| "loss": 6.5109, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.03482240573077306, | |
| "grad_norm": 0.7799229025840759, | |
| "learning_rate": 3.0139904057691777e-05, | |
| "loss": 6.6674, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0353198686697841, | |
| "grad_norm": 1.039928674697876, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 6.8205, | |
| "step": 71 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 71, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7767234478080.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |