| { | |
| "best_metric": 0.00994301587343216, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011268875366238449, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000225377507324769, | |
| "grad_norm": 11.877915382385254, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000225377507324769, | |
| "eval_loss": 7.1420392990112305, | |
| "eval_runtime": 1839.8249, | |
| "eval_samples_per_second": 16.247, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000450755014649538, | |
| "grad_norm": 12.769062042236328, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7865, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000676132521974307, | |
| "grad_norm": 12.042207717895508, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.1808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000901510029299076, | |
| "grad_norm": 12.270781517028809, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.0662, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001126887536623845, | |
| "grad_norm": 10.869080543518066, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.9042, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001352265043948614, | |
| "grad_norm": 5.981398105621338, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6202, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015776425512733828, | |
| "grad_norm": 1.7641795873641968, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1551, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001803020058598152, | |
| "grad_norm": 1.5607192516326904, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0875, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002028397565922921, | |
| "grad_norm": 0.4291340112686157, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0204, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00225377507324769, | |
| "grad_norm": 1.1973085403442383, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0443, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024791525805724587, | |
| "grad_norm": 0.7830405235290527, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0283, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002704530087897228, | |
| "grad_norm": 0.39667654037475586, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.019, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002929907595221997, | |
| "grad_norm": 0.6528044939041138, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0209, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0031552851025467656, | |
| "grad_norm": 0.9219077825546265, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.012, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0033806626098715348, | |
| "grad_norm": 0.6906279921531677, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0092, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003606040117196304, | |
| "grad_norm": 0.6515050530433655, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0193, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0038314176245210726, | |
| "grad_norm": 0.7428199648857117, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004056795131845842, | |
| "grad_norm": 0.6576622128486633, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0039, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00428217263917061, | |
| "grad_norm": 0.714439332485199, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0114, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00450755014649538, | |
| "grad_norm": 0.44880980253219604, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004732927653820149, | |
| "grad_norm": 0.28526055812835693, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0142, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004958305161144917, | |
| "grad_norm": 0.292219340801239, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0121, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005183682668469687, | |
| "grad_norm": 0.7755442261695862, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0167, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005409060175794456, | |
| "grad_norm": 0.7047219276428223, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0132, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005634437683119224, | |
| "grad_norm": 0.4816979765892029, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0235, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005634437683119224, | |
| "eval_loss": 0.016585199162364006, | |
| "eval_runtime": 918.876, | |
| "eval_samples_per_second": 32.531, | |
| "eval_steps_per_second": 4.067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005859815190443994, | |
| "grad_norm": 0.42453789710998535, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0169, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006085192697768763, | |
| "grad_norm": 0.13364818692207336, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0078, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006310570205093531, | |
| "grad_norm": 0.36047905683517456, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0104, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006535947712418301, | |
| "grad_norm": 0.2539707124233246, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0075, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0067613252197430695, | |
| "grad_norm": 0.1371479481458664, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006986702727067838, | |
| "grad_norm": 0.3025669753551483, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0076, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007212080234392608, | |
| "grad_norm": 0.09683921933174133, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0054, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0074374577417173765, | |
| "grad_norm": 0.6243895888328552, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.02, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007662835249042145, | |
| "grad_norm": 0.4139314889907837, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0165, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007888212756366914, | |
| "grad_norm": 0.33643707633018494, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0083, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008113590263691683, | |
| "grad_norm": 0.36276066303253174, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0111, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008338967771016453, | |
| "grad_norm": 0.20926550030708313, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0052, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00856434527834122, | |
| "grad_norm": 0.09445331245660782, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0083, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00878972278566599, | |
| "grad_norm": 0.1011340394616127, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.004, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00901510029299076, | |
| "grad_norm": 0.3738754391670227, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0213, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009240477800315528, | |
| "grad_norm": 0.5829588174819946, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0107, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009465855307640297, | |
| "grad_norm": 0.4242364466190338, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.008, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009691232814965067, | |
| "grad_norm": 0.14530935883522034, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0032, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009916610322289835, | |
| "grad_norm": 0.3869449198246002, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0088, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010141987829614604, | |
| "grad_norm": 0.7613345384597778, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0169, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010367365336939374, | |
| "grad_norm": 0.10731913149356842, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0085, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010592742844264142, | |
| "grad_norm": 0.13133440911769867, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0066, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010818120351588911, | |
| "grad_norm": 0.31385451555252075, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0138, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01104349785891368, | |
| "grad_norm": 0.3443942964076996, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0062, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011268875366238449, | |
| "grad_norm": 0.5915001630783081, | |
| "learning_rate": 0.0, | |
| "loss": 0.0236, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011268875366238449, | |
| "eval_loss": 0.00994301587343216, | |
| "eval_runtime": 907.1642, | |
| "eval_samples_per_second": 32.951, | |
| "eval_steps_per_second": 4.119, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |