| { | |
| "best_metric": 1.6834224462509155, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.008471584892340275, | |
| "eval_steps": 10, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002823861630780092, | |
| "grad_norm": 1.2056736946105957, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9521, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002823861630780092, | |
| "eval_loss": 2.352551221847534, | |
| "eval_runtime": 133.636, | |
| "eval_samples_per_second": 5.582, | |
| "eval_steps_per_second": 5.582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005647723261560184, | |
| "grad_norm": 4.347576141357422, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1192, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008471584892340275, | |
| "grad_norm": 0.7937899231910706, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1903, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011295446523120368, | |
| "grad_norm": 3.9262712001800537, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014119308153900459, | |
| "grad_norm": 2.7941317558288574, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9205, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001694316978468055, | |
| "grad_norm": 0.9424725770950317, | |
| "learning_rate": 0.00012, | |
| "loss": 2.582, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001976703141546064, | |
| "grad_norm": 1.8026996850967407, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0555, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022590893046240735, | |
| "grad_norm": 1.0503661632537842, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6065, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025414754677020824, | |
| "grad_norm": 2.3215556144714355, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6192, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028238616307800918, | |
| "grad_norm": 1.60389244556427, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028238616307800918, | |
| "eval_loss": 2.1240005493164062, | |
| "eval_runtime": 133.7157, | |
| "eval_samples_per_second": 5.579, | |
| "eval_steps_per_second": 5.579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003106247793858101, | |
| "grad_norm": 1.0237597227096558, | |
| "learning_rate": 0.0001999979446958366, | |
| "loss": 1.8844, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00338863395693611, | |
| "grad_norm": 4.726717472076416, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 3.1172, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036710201200141194, | |
| "grad_norm": 1.6403062343597412, | |
| "learning_rate": 0.00019998150276943902, | |
| "loss": 1.7007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003953406283092128, | |
| "grad_norm": 2.1164722442626953, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 2.5321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004235792446170138, | |
| "grad_norm": 3.5340867042541504, | |
| "learning_rate": 0.0001999486216200688, | |
| "loss": 2.3608, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004518178609248147, | |
| "grad_norm": 5.55496072769165, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 1.6141, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004800564772326156, | |
| "grad_norm": 7.0048136711120605, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 2.2728, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005082950935404165, | |
| "grad_norm": 1.7807990312576294, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 1.6759, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005365337098482174, | |
| "grad_norm": 3.1774418354034424, | |
| "learning_rate": 0.0001998335659801241, | |
| "loss": 0.8362, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0056477232615601836, | |
| "grad_norm": 5.73573637008667, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 2.7934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0056477232615601836, | |
| "eval_loss": 1.7092158794403076, | |
| "eval_runtime": 133.3036, | |
| "eval_samples_per_second": 5.596, | |
| "eval_steps_per_second": 5.596, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005930109424638193, | |
| "grad_norm": 1.705460548400879, | |
| "learning_rate": 0.00019975141040730207, | |
| "loss": 1.3571, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006212495587716202, | |
| "grad_norm": 1.3597909212112427, | |
| "learning_rate": 0.0001997041811497882, | |
| "loss": 1.491, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006494881750794211, | |
| "grad_norm": 1.3038731813430786, | |
| "learning_rate": 0.00019965285344390184, | |
| "loss": 2.4389, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00677726791387222, | |
| "grad_norm": 2.3923144340515137, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 1.3591, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0070596540769502295, | |
| "grad_norm": 2.964477300643921, | |
| "learning_rate": 0.00019953791129491983, | |
| "loss": 1.1022, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007342040240028239, | |
| "grad_norm": 3.184072732925415, | |
| "learning_rate": 0.00019947430157664576, | |
| "loss": 1.4837, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007624426403106248, | |
| "grad_norm": 1.576446294784546, | |
| "learning_rate": 0.00019940660285944803, | |
| "loss": 2.0992, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007906812566184257, | |
| "grad_norm": 2.878796100616455, | |
| "learning_rate": 0.00019933481792615583, | |
| "loss": 2.4712, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008189198729262267, | |
| "grad_norm": 2.5952467918395996, | |
| "learning_rate": 0.0001992589497275665, | |
| "loss": 1.6412, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008471584892340275, | |
| "grad_norm": 2.8451197147369385, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 1.6372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008471584892340275, | |
| "eval_loss": 1.6834224462509155, | |
| "eval_runtime": 133.2875, | |
| "eval_samples_per_second": 5.597, | |
| "eval_steps_per_second": 5.597, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2936410755563520.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |