| { | |
| "best_metric": 1.404244303703308, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06693440428380187, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013386880856760374, | |
| "grad_norm": 5.124406337738037, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4108, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013386880856760374, | |
| "eval_loss": 2.537308931350708, | |
| "eval_runtime": 71.1215, | |
| "eval_samples_per_second": 17.688, | |
| "eval_steps_per_second": 2.222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002677376171352075, | |
| "grad_norm": 5.234611988067627, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2402, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "grad_norm": 5.23838472366333, | |
| "learning_rate": 6e-05, | |
| "loss": 2.133, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00535475234270415, | |
| "grad_norm": 2.3010237216949463, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1439, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006693440428380187, | |
| "grad_norm": 1.4434807300567627, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6299, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 0.9331907629966736, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7632, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009370816599732263, | |
| "grad_norm": 1.7133104801177979, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8334, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0107095046854083, | |
| "grad_norm": 1.4615625143051147, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.96, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 1.668829321861267, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2397, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013386880856760375, | |
| "grad_norm": 0.9116508364677429, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.2661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014725568942436412, | |
| "grad_norm": 1.1170767545700073, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6195, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 0.8861685395240784, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4956, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01740294511378849, | |
| "grad_norm": 1.2484769821166992, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.7205, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018741633199464525, | |
| "grad_norm": 1.0831106901168823, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5407, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": 0.9455034136772156, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.415, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0214190093708166, | |
| "grad_norm": 1.0213031768798828, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.1117, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022757697456492636, | |
| "grad_norm": 0.918285608291626, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.1296, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 1.0008317232131958, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.1813, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025435073627844713, | |
| "grad_norm": 0.9964174032211304, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.2839, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02677376171352075, | |
| "grad_norm": 0.8869675993919373, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "grad_norm": 0.963006854057312, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.0516, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029451137884872823, | |
| "grad_norm": 0.8680381774902344, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.9759, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030789825970548863, | |
| "grad_norm": 1.0366902351379395, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.1641, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0321285140562249, | |
| "grad_norm": 1.0418281555175781, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.1926, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03346720214190094, | |
| "grad_norm": 1.0148645639419556, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.9982, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03346720214190094, | |
| "eval_loss": 1.4752330780029297, | |
| "eval_runtime": 72.4392, | |
| "eval_samples_per_second": 17.366, | |
| "eval_steps_per_second": 2.181, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03480589022757698, | |
| "grad_norm": 1.196060299873352, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.0636, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 1.449025273323059, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.1377, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03748326639892905, | |
| "grad_norm": 1.8445948362350464, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.2107, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.038821954484605084, | |
| "grad_norm": 1.9364060163497925, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.4555, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.040160642570281124, | |
| "grad_norm": 2.409740447998047, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.6639, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041499330655957165, | |
| "grad_norm": 2.1676015853881836, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.3554, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0428380187416332, | |
| "grad_norm": 2.1554808616638184, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.3832, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04417670682730924, | |
| "grad_norm": 2.084815740585327, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.4907, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04551539491298527, | |
| "grad_norm": 2.2933266162872314, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.5189, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04685408299866131, | |
| "grad_norm": 2.28518009185791, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5068, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 2.2734827995300293, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.5619, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.049531459170013385, | |
| "grad_norm": 2.4875550270080566, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6357, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.050870147255689425, | |
| "grad_norm": 2.4092066287994385, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.6984, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05220883534136546, | |
| "grad_norm": 2.840477466583252, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.5653, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0535475234270415, | |
| "grad_norm": 2.624983310699463, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.702, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05488621151271754, | |
| "grad_norm": 2.8492836952209473, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6325, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05622489959839357, | |
| "grad_norm": 3.2326295375823975, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.8388, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05756358768406961, | |
| "grad_norm": 4.206023216247559, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.9769, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.058902275769745646, | |
| "grad_norm": 5.246030330657959, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.1044, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060240963855421686, | |
| "grad_norm": 8.100854873657227, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.7415, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06157965194109773, | |
| "grad_norm": 7.93204927444458, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.3497, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06291834002677377, | |
| "grad_norm": 9.60119915008545, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.1179, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0642570281124498, | |
| "grad_norm": 9.609639167785645, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.4892, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06559571619812583, | |
| "grad_norm": 10.633676528930664, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.7826, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06693440428380187, | |
| "grad_norm": 20.666841506958008, | |
| "learning_rate": 0.0, | |
| "loss": 3.1652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06693440428380187, | |
| "eval_loss": 1.404244303703308, | |
| "eval_runtime": 72.11, | |
| "eval_samples_per_second": 17.446, | |
| "eval_steps_per_second": 2.191, | |
| "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": 5, | |
| "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": 5.022044271516058e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |