| { | |
| "best_metric": 0.6564589142799377, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.564102564102564, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 0.9672800302505493, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1886, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "eval_loss": 1.5803714990615845, | |
| "eval_runtime": 3.6081, | |
| "eval_samples_per_second": 36.585, | |
| "eval_steps_per_second": 4.712, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 1.3355220556259155, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 1.95944344997406, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4243, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.9178346395492554, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1365, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.7719805240631104, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9886, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.6093124151229858, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9104, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 0.7734506726264954, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8633, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 1.0146095752716064, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9498, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.9810937643051147, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.857, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.5339524745941162, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7722, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 0.46282830834388733, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7708, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.4825150668621063, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.5821698904037476, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.786, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.6364465951919556, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6887, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.45385560393333435, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.692, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.5232996940612793, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7566, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 0.507578432559967, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6827, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.6283358931541443, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7013, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 0.6958040595054626, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6565, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 0.7207463979721069, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0116, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 0.48482224345207214, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6333, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1282051282051282, | |
| "grad_norm": 0.489801824092865, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6145, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1794871794871795, | |
| "grad_norm": 0.5469512939453125, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6701, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.47528180480003357, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.425, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.282051282051282, | |
| "grad_norm": 0.5249252319335938, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7017, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.282051282051282, | |
| "eval_loss": 0.7022424340248108, | |
| "eval_runtime": 3.5883, | |
| "eval_samples_per_second": 36.786, | |
| "eval_steps_per_second": 4.738, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.48070189356803894, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6136, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 0.4862198829650879, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5567, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.435897435897436, | |
| "grad_norm": 0.5944578051567078, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6054, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4871794871794872, | |
| "grad_norm": 0.44747453927993774, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3329, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.5775405764579773, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.75, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5897435897435899, | |
| "grad_norm": 0.5205840468406677, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.613, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 0.5326344966888428, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.555, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 0.6287438273429871, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4934, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.7435897435897436, | |
| "grad_norm": 0.5123702883720398, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4381, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7948717948717947, | |
| "grad_norm": 0.5365183353424072, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6485, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 0.5241835713386536, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5542, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8974358974358974, | |
| "grad_norm": 0.5163524150848389, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5152, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "grad_norm": 0.6703210473060608, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5067, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8151555061340332, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6857, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 0.43518462777137756, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5214, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.1025641025641026, | |
| "grad_norm": 0.46697771549224854, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4954, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 0.5525245666503906, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4891, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.2051282051282053, | |
| "grad_norm": 0.5733924508094788, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4404, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.2564102564102564, | |
| "grad_norm": 0.5429036617279053, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.444, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.5037180781364441, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5491, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.358974358974359, | |
| "grad_norm": 0.4842893183231354, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4957, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.41025641025641, | |
| "grad_norm": 0.5672169923782349, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4998, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 0.6230229139328003, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4331, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.5128205128205128, | |
| "grad_norm": 0.5308722257614136, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4575, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 0.5225934386253357, | |
| "learning_rate": 0.0, | |
| "loss": 0.5903, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 0.6564589142799377, | |
| "eval_runtime": 3.8615, | |
| "eval_samples_per_second": 34.184, | |
| "eval_steps_per_second": 4.402, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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 | |
| } | |