| { | |
| "best_metric": 3.0045323371887207, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.001837255874625659, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.349023498502637e-05, | |
| "grad_norm": 8.524636268615723, | |
| "learning_rate": 2e-05, | |
| "loss": 14.4765, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.349023498502637e-05, | |
| "eval_loss": 3.509612560272217, | |
| "eval_runtime": 226.3863, | |
| "eval_samples_per_second": 25.311, | |
| "eval_steps_per_second": 12.655, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014698046997005273, | |
| "grad_norm": 8.564088821411133, | |
| "learning_rate": 4e-05, | |
| "loss": 12.9557, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002204707049550791, | |
| "grad_norm": 8.800429344177246, | |
| "learning_rate": 6e-05, | |
| "loss": 14.4848, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029396093994010547, | |
| "grad_norm": 8.055926322937012, | |
| "learning_rate": 8e-05, | |
| "loss": 14.0229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003674511749251318, | |
| "grad_norm": 10.027109146118164, | |
| "learning_rate": 0.0001, | |
| "loss": 14.5024, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003674511749251318, | |
| "eval_loss": 3.4547383785247803, | |
| "eval_runtime": 226.1904, | |
| "eval_samples_per_second": 25.333, | |
| "eval_steps_per_second": 12.666, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004409414099101582, | |
| "grad_norm": 7.777037620544434, | |
| "learning_rate": 0.00012, | |
| "loss": 14.032, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005144316448951845, | |
| "grad_norm": 8.469795227050781, | |
| "learning_rate": 0.00014, | |
| "loss": 14.5878, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005879218798802109, | |
| "grad_norm": 6.550638198852539, | |
| "learning_rate": 0.00016, | |
| "loss": 13.2989, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006614121148652373, | |
| "grad_norm": 7.667253494262695, | |
| "learning_rate": 0.00018, | |
| "loss": 12.7147, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007349023498502636, | |
| "grad_norm": 7.651482105255127, | |
| "learning_rate": 0.0002, | |
| "loss": 14.0306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007349023498502636, | |
| "eval_loss": 3.2756810188293457, | |
| "eval_runtime": 224.8943, | |
| "eval_samples_per_second": 25.479, | |
| "eval_steps_per_second": 12.739, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00080839258483529, | |
| "grad_norm": 6.639260292053223, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 14.1502, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008818828198203164, | |
| "grad_norm": 6.808887958526611, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 12.9408, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009553730548053427, | |
| "grad_norm": 5.84608793258667, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 12.9238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001028863289790369, | |
| "grad_norm": 7.3352155685424805, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 13.9106, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0011023535247753954, | |
| "grad_norm": 6.594282627105713, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 12.9694, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011023535247753954, | |
| "eval_loss": 3.1025280952453613, | |
| "eval_runtime": 225.7539, | |
| "eval_samples_per_second": 25.382, | |
| "eval_steps_per_second": 12.691, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011758437597604219, | |
| "grad_norm": 7.4922308921813965, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 13.9478, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012493339947454482, | |
| "grad_norm": 8.131263732910156, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 13.4256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0013228242297304747, | |
| "grad_norm": 6.77695894241333, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 11.8111, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001396314464715501, | |
| "grad_norm": 7.733022212982178, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 12.3092, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014698046997005272, | |
| "grad_norm": 7.354087829589844, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 12.6161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014698046997005272, | |
| "eval_loss": 3.0219674110412598, | |
| "eval_runtime": 230.8322, | |
| "eval_samples_per_second": 24.823, | |
| "eval_steps_per_second": 12.412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015432949346855537, | |
| "grad_norm": 8.05355453491211, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 12.4798, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00161678516967058, | |
| "grad_norm": 7.80503511428833, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 12.0225, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016902754046556063, | |
| "grad_norm": 7.3944621086120605, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 12.1289, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0017637656396406328, | |
| "grad_norm": 6.86484956741333, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 12.3028, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001837255874625659, | |
| "grad_norm": 7.060364723205566, | |
| "learning_rate": 0.0, | |
| "loss": 12.4101, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001837255874625659, | |
| "eval_loss": 3.0045323371887207, | |
| "eval_runtime": 226.9661, | |
| "eval_samples_per_second": 25.246, | |
| "eval_steps_per_second": 12.623, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 53073779097600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |