| { | |
| "best_metric": 0.1865025758743286, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06286342920006287, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012572685840012573, | |
| "grad_norm": 53.43999481201172, | |
| "learning_rate": 5e-05, | |
| "loss": 13.4857, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012572685840012573, | |
| "eval_loss": 13.226393699645996, | |
| "eval_runtime": 67.192, | |
| "eval_samples_per_second": 79.742, | |
| "eval_steps_per_second": 9.971, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025145371680025145, | |
| "grad_norm": 52.666507720947266, | |
| "learning_rate": 0.0001, | |
| "loss": 12.9537, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003771805752003772, | |
| "grad_norm": 42.24228286743164, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.6073, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005029074336005029, | |
| "grad_norm": 27.329580307006836, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.0604, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006286342920006287, | |
| "grad_norm": 26.369712829589844, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.1771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007543611504007544, | |
| "grad_norm": 23.021930694580078, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0023, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0088008800880088, | |
| "grad_norm": 20.184478759765625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9065, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010058148672010058, | |
| "grad_norm": 10.161637306213379, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4738, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011315417256011316, | |
| "grad_norm": 19.171974182128906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6064, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012572685840012573, | |
| "grad_norm": 12.57507038116455, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01382995442401383, | |
| "grad_norm": 13.242116928100586, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5477, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015087223008015087, | |
| "grad_norm": 10.257842063903809, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5072, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016344491592016345, | |
| "grad_norm": 15.582720756530762, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0176017601760176, | |
| "grad_norm": 4.773410320281982, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3376, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01885902876001886, | |
| "grad_norm": 4.96658992767334, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3037, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020116297344020116, | |
| "grad_norm": 5.735321044921875, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3311, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021373565928021372, | |
| "grad_norm": 5.072901248931885, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3874, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02263083451202263, | |
| "grad_norm": 5.95760440826416, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3659, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023888103096023888, | |
| "grad_norm": 1.5819381475448608, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3067, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025145371680025147, | |
| "grad_norm": 8.529723167419434, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3965, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026402640264026403, | |
| "grad_norm": 10.18874454498291, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4538, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02765990884802766, | |
| "grad_norm": 9.016319274902344, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4154, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02891717743202892, | |
| "grad_norm": 1.9254709482192993, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.267, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030174446016030174, | |
| "grad_norm": 5.987302303314209, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3105, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031431714600031434, | |
| "grad_norm": 10.182058334350586, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.443, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031431714600031434, | |
| "eval_loss": 0.33480188250541687, | |
| "eval_runtime": 67.1657, | |
| "eval_samples_per_second": 79.773, | |
| "eval_steps_per_second": 9.975, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03268898318403269, | |
| "grad_norm": 6.639444351196289, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2724, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.033946251768033946, | |
| "grad_norm": 3.8194305896759033, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2312, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0352035203520352, | |
| "grad_norm": 2.612955331802368, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1923, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03646078893603646, | |
| "grad_norm": 1.882875680923462, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2243, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03771805752003772, | |
| "grad_norm": 3.010631561279297, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.22, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038975326104038976, | |
| "grad_norm": 3.0281689167022705, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1856, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04023259468804023, | |
| "grad_norm": 2.0920002460479736, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2179, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04148986327204149, | |
| "grad_norm": 1.6378231048583984, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1979, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.042747131856042744, | |
| "grad_norm": 3.4983468055725098, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2064, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04400440044004401, | |
| "grad_norm": 4.694855690002441, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04526166902404526, | |
| "grad_norm": 3.535817861557007, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2407, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04651893760804652, | |
| "grad_norm": 4.406174659729004, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2433, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.047776206192047775, | |
| "grad_norm": 2.9204981327056885, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2023, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04903347477604903, | |
| "grad_norm": 1.1347187757492065, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1773, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.050290743360050294, | |
| "grad_norm": 1.2280828952789307, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05154801194405155, | |
| "grad_norm": 1.6335227489471436, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1701, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": 1.564247488975525, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1975, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05406254911205406, | |
| "grad_norm": 2.325559377670288, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1812, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05531981769605532, | |
| "grad_norm": 2.336494207382202, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1892, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.056577086280056574, | |
| "grad_norm": 2.2626729011535645, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1759, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05783435486405784, | |
| "grad_norm": 2.434901714324951, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1839, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05909162344805909, | |
| "grad_norm": 2.663579225540161, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1751, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06034889203206035, | |
| "grad_norm": 2.5975544452667236, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1966, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.061606160616061605, | |
| "grad_norm": 1.679148554801941, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2511, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06286342920006287, | |
| "grad_norm": 3.370861291885376, | |
| "learning_rate": 0.0, | |
| "loss": 0.2432, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06286342920006287, | |
| "eval_loss": 0.1865025758743286, | |
| "eval_runtime": 67.1822, | |
| "eval_samples_per_second": 79.753, | |
| "eval_steps_per_second": 9.973, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |