| { | |
| "best_metric": 0.10377126187086105, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6756756756756757, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 12.255108833312988, | |
| "learning_rate": 5e-05, | |
| "loss": 8.4274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "eval_loss": 7.954690456390381, | |
| "eval_runtime": 14.6788, | |
| "eval_samples_per_second": 33.995, | |
| "eval_steps_per_second": 4.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 9.243254661560059, | |
| "learning_rate": 0.0001, | |
| "loss": 7.9128, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04054054054054054, | |
| "grad_norm": 8.655728340148926, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.8057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 7.235657215118408, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.2931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 6.825467109680176, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.8394, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08108108108108109, | |
| "grad_norm": 6.22944974899292, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0945945945945946, | |
| "grad_norm": 5.156695365905762, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.1692, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 5.830663204193115, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0249, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12162162162162163, | |
| "grad_norm": 4.911316871643066, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6124, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 3.971449851989746, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4772, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14864864864864866, | |
| "grad_norm": 3.330519199371338, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1434, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 2.213716506958008, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6182, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17567567567567569, | |
| "grad_norm": 1.719006061553955, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4751, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1891891891891892, | |
| "grad_norm": 7.296812057495117, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5524, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20270270270270271, | |
| "grad_norm": 3.740504264831543, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3333, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 2.1354198455810547, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.294, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22972972972972974, | |
| "grad_norm": 2.9046542644500732, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3744, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24324324324324326, | |
| "grad_norm": 3.3071227073669434, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3319, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25675675675675674, | |
| "grad_norm": 1.5425763130187988, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3234, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 2.437530279159546, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2451, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28378378378378377, | |
| "grad_norm": 1.9057947397232056, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2815, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2972972972972973, | |
| "grad_norm": 1.2744722366333008, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2686, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3108108108108108, | |
| "grad_norm": 1.0754117965698242, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1933, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 1.1910902261734009, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1232, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "grad_norm": 1.2786903381347656, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1893, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "eval_loss": 0.13296709954738617, | |
| "eval_runtime": 14.6359, | |
| "eval_samples_per_second": 34.094, | |
| "eval_steps_per_second": 4.304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35135135135135137, | |
| "grad_norm": 1.1895753145217896, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1106, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.36486486486486486, | |
| "grad_norm": 2.3610384464263916, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2791, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3783783783783784, | |
| "grad_norm": 1.643008828163147, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1546, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3918918918918919, | |
| "grad_norm": 1.6177732944488525, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1978, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 1.8108652830123901, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4189189189189189, | |
| "grad_norm": 2.1313583850860596, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1894, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 1.4777275323867798, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.232, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.44594594594594594, | |
| "grad_norm": 1.6066914796829224, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2551, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4594594594594595, | |
| "grad_norm": 1.397235631942749, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.253, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47297297297297297, | |
| "grad_norm": 1.329254150390625, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2383, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4864864864864865, | |
| "grad_norm": 1.3167423009872437, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1335, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.0337791442871094, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1781, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5135135135135135, | |
| "grad_norm": 0.6120166778564453, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1018, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.527027027027027, | |
| "grad_norm": 0.6781937479972839, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1015, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 0.6627649068832397, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0898, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5540540540540541, | |
| "grad_norm": 0.9930323362350464, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.073, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5675675675675675, | |
| "grad_norm": 0.8100405931472778, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1591, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.581081081081081, | |
| "grad_norm": 0.8315913677215576, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1893, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5945945945945946, | |
| "grad_norm": 1.6323856115341187, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.21, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6081081081081081, | |
| "grad_norm": 1.213604211807251, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1902, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6216216216216216, | |
| "grad_norm": 1.0373070240020752, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1713, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6351351351351351, | |
| "grad_norm": 0.6015317440032959, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1038, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 1.1619991064071655, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1853, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6621621621621622, | |
| "grad_norm": 0.6225360035896301, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1095, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 0.8265971541404724, | |
| "learning_rate": 0.0, | |
| "loss": 0.1351, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "eval_loss": 0.10377126187086105, | |
| "eval_runtime": 14.6286, | |
| "eval_samples_per_second": 34.111, | |
| "eval_steps_per_second": 4.307, | |
| "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": 5.32019209568256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |