| { | |
| "best_metric": 2.2997690393822268e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.24806201550387597, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00496124031007752, | |
| "grad_norm": 23.23585319519043, | |
| "learning_rate": 5e-05, | |
| "loss": 11.3401, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00496124031007752, | |
| "eval_loss": 10.861466407775879, | |
| "eval_runtime": 34.401, | |
| "eval_samples_per_second": 39.476, | |
| "eval_steps_per_second": 4.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00992248062015504, | |
| "grad_norm": 24.292354583740234, | |
| "learning_rate": 0.0001, | |
| "loss": 10.9325, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014883720930232559, | |
| "grad_norm": 22.498645782470703, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.2178, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01984496124031008, | |
| "grad_norm": 17.426952362060547, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.1054, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024806201550387597, | |
| "grad_norm": 14.538772583007812, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.0699, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029767441860465118, | |
| "grad_norm": 13.055420875549316, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4166, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03472868217054263, | |
| "grad_norm": 12.215715408325195, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.9664, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03968992248062016, | |
| "grad_norm": 7.951274394989014, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7269, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.044651162790697675, | |
| "grad_norm": 1.9474599361419678, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1395, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04961240310077519, | |
| "grad_norm": 0.40482786297798157, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05457364341085271, | |
| "grad_norm": 0.06929321587085724, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0042, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.059534883720930236, | |
| "grad_norm": 0.0293231550604105, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0016, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06449612403100775, | |
| "grad_norm": 0.012703669257462025, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06945736434108526, | |
| "grad_norm": 0.006540760863572359, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0003, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 0.004683414474129677, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0002, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07937984496124031, | |
| "grad_norm": 0.003430376062169671, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08434108527131783, | |
| "grad_norm": 0.003030678490176797, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08930232558139535, | |
| "grad_norm": 0.0023646620102226734, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09426356589147286, | |
| "grad_norm": 0.002618241822347045, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09922480620155039, | |
| "grad_norm": 0.0019350913353264332, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10418604651162791, | |
| "grad_norm": 0.001895522465929389, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10914728682170542, | |
| "grad_norm": 0.0017253287369385362, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11410852713178295, | |
| "grad_norm": 0.001647541648708284, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11906976744186047, | |
| "grad_norm": 0.0016631092876195908, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 0.002164131496101618, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "eval_loss": 3.499747981550172e-05, | |
| "eval_runtime": 34.3197, | |
| "eval_samples_per_second": 39.569, | |
| "eval_steps_per_second": 4.953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1289922480620155, | |
| "grad_norm": 0.0009804804576560855, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13395348837209303, | |
| "grad_norm": 0.0011718858731910586, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13891472868217053, | |
| "grad_norm": 0.0011278550373390317, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14387596899224805, | |
| "grad_norm": 0.0011067610466852784, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 0.0009319029632024467, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1537984496124031, | |
| "grad_norm": 0.001149399671703577, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15875968992248063, | |
| "grad_norm": 0.0009815137600526214, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16372093023255813, | |
| "grad_norm": 0.0009451531805098057, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16868217054263565, | |
| "grad_norm": 0.0009667045087553561, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17364341085271318, | |
| "grad_norm": 0.0008827492711134255, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1786046511627907, | |
| "grad_norm": 0.0009160165209323168, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18356589147286823, | |
| "grad_norm": 0.0013087359257042408, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.18852713178294572, | |
| "grad_norm": 0.0009455772233195603, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19348837209302325, | |
| "grad_norm": 0.0009561454644426703, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19844961240310077, | |
| "grad_norm": 0.0007501421496272087, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2034108527131783, | |
| "grad_norm": 0.0008627751376479864, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.20837209302325582, | |
| "grad_norm": 0.0007621397380717099, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 0.0006791076739318669, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.21829457364341084, | |
| "grad_norm": 0.0007713348604738712, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": 0.000771517341490835, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2282170542635659, | |
| "grad_norm": 0.000766627723351121, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.23317829457364342, | |
| "grad_norm": 0.001595512148924172, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.23813953488372094, | |
| "grad_norm": 0.0008882001275196671, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24310077519379844, | |
| "grad_norm": 0.0010015094885602593, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 0.0012133317068219185, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "eval_loss": 2.2997690393822268e-05, | |
| "eval_runtime": 34.3546, | |
| "eval_samples_per_second": 39.529, | |
| "eval_steps_per_second": 4.948, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |