| { | |
| "best_metric": 0.011089812964200974, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.91324200913242, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0182648401826484, | |
| "grad_norm": 4.97927188873291, | |
| "learning_rate": 5e-05, | |
| "loss": 9.2064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0182648401826484, | |
| "eval_loss": 9.222379684448242, | |
| "eval_runtime": 35.9912, | |
| "eval_samples_per_second": 10.253, | |
| "eval_steps_per_second": 1.306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0365296803652968, | |
| "grad_norm": 5.021515369415283, | |
| "learning_rate": 0.0001, | |
| "loss": 9.3595, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 5.704291820526123, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.9454, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0730593607305936, | |
| "grad_norm": 7.59834098815918, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.4214, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 6.393439292907715, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.476, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 4.328259468078613, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.0761, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1278538812785388, | |
| "grad_norm": 3.696347236633301, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.0658, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1461187214611872, | |
| "grad_norm": 3.935392379760742, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6876, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 4.143343925476074, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.0568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 3.8842058181762695, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3215, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2009132420091324, | |
| "grad_norm": 2.776092767715454, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.794, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 5.042316436767578, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0092, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2374429223744292, | |
| "grad_norm": 6.087222099304199, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5964, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2557077625570776, | |
| "grad_norm": 5.527134418487549, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1932, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.9342890977859497, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1162, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2922374429223744, | |
| "grad_norm": 1.9712278842926025, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2089, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3105022831050228, | |
| "grad_norm": 2.8087289333343506, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1325, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 1.6563050746917725, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0541, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3470319634703196, | |
| "grad_norm": 0.32680124044418335, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 0.4098830223083496, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0094, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3835616438356164, | |
| "grad_norm": 0.7213758230209351, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0124, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4018264840182648, | |
| "grad_norm": 0.2860282063484192, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0072, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4200913242009132, | |
| "grad_norm": 0.02835237979888916, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0005, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.024994798004627228, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0006, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 1.8546289205551147, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1561, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "eval_loss": 0.011089812964200974, | |
| "eval_runtime": 35.4919, | |
| "eval_samples_per_second": 10.397, | |
| "eval_steps_per_second": 1.324, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4748858447488584, | |
| "grad_norm": 0.5133668780326843, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0056, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4931506849315068, | |
| "grad_norm": 1.287654995918274, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0164, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5114155251141552, | |
| "grad_norm": 0.18463000655174255, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0036, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5296803652968036, | |
| "grad_norm": 0.03979532793164253, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0009, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.01812467910349369, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0005, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5662100456621004, | |
| "grad_norm": 0.008781279437243938, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0002, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5844748858447488, | |
| "grad_norm": 0.0651770532131195, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0015, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6027397260273972, | |
| "grad_norm": 0.01783256232738495, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0005, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6210045662100456, | |
| "grad_norm": 0.003473809454590082, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 0.003669138764962554, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0001, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.03214825317263603, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0005, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6757990867579908, | |
| "grad_norm": 0.4901163578033447, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0857, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6940639269406392, | |
| "grad_norm": 0.011674696579575539, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0002, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7123287671232876, | |
| "grad_norm": 0.009491109289228916, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0002, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.006969192996621132, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7488584474885844, | |
| "grad_norm": 0.003321270225569606, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7671232876712328, | |
| "grad_norm": 0.024109523743391037, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0005, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7853881278538812, | |
| "grad_norm": 0.009124420583248138, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8036529680365296, | |
| "grad_norm": 0.004407109692692757, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0002, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.003542846068739891, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8401826484018264, | |
| "grad_norm": 0.014414651319384575, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0003, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8584474885844748, | |
| "grad_norm": 0.1259673833847046, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.003, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.01385512761771679, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0003, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8949771689497716, | |
| "grad_norm": 0.005186452530324459, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0002, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 0.5546965003013611, | |
| "learning_rate": 0.0, | |
| "loss": 0.1002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "eval_loss": 0.01725011318922043, | |
| "eval_runtime": 69.4723, | |
| "eval_samples_per_second": 5.311, | |
| "eval_steps_per_second": 0.677, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9974437372229059e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |