| { | |
| "best_metric": 1.0927900075912476, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004284857314251435, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001713942925700574, | |
| "grad_norm": 0.7002414464950562, | |
| "learning_rate": 2e-05, | |
| "loss": 5.3109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001713942925700574, | |
| "eval_loss": 1.2564200162887573, | |
| "eval_runtime": 431.1988, | |
| "eval_samples_per_second": 5.698, | |
| "eval_steps_per_second": 2.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003427885851401148, | |
| "grad_norm": 0.5215798616409302, | |
| "learning_rate": 4e-05, | |
| "loss": 5.0649, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005141828777101723, | |
| "grad_norm": 0.6687475442886353, | |
| "learning_rate": 6e-05, | |
| "loss": 4.807, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006855771702802296, | |
| "grad_norm": 0.5465673208236694, | |
| "learning_rate": 8e-05, | |
| "loss": 4.2428, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008569714628502871, | |
| "grad_norm": 0.593774139881134, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5061, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008569714628502871, | |
| "eval_loss": 1.2541313171386719, | |
| "eval_runtime": 431.491, | |
| "eval_samples_per_second": 5.694, | |
| "eval_steps_per_second": 2.848, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010283657554203446, | |
| "grad_norm": 0.6595162153244019, | |
| "learning_rate": 0.00012, | |
| "loss": 4.7018, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011997600479904018, | |
| "grad_norm": 0.6837590932846069, | |
| "learning_rate": 0.00014, | |
| "loss": 4.9708, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013711543405604593, | |
| "grad_norm": 0.6360350847244263, | |
| "learning_rate": 0.00016, | |
| "loss": 4.8818, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015425486331305167, | |
| "grad_norm": 0.7959117293357849, | |
| "learning_rate": 0.00018, | |
| "loss": 4.296, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017139429257005741, | |
| "grad_norm": 1.0661449432373047, | |
| "learning_rate": 0.0002, | |
| "loss": 5.0696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017139429257005741, | |
| "eval_loss": 1.2037712335586548, | |
| "eval_runtime": 435.893, | |
| "eval_samples_per_second": 5.637, | |
| "eval_steps_per_second": 2.819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018853372182706316, | |
| "grad_norm": 1.1513092517852783, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.9643, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002056731510840689, | |
| "grad_norm": 1.0634475946426392, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.6718, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022281258034107464, | |
| "grad_norm": 1.3111153841018677, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.5046, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023995200959808036, | |
| "grad_norm": 0.991614043712616, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.0563, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025709143885508613, | |
| "grad_norm": 1.1510419845581055, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.2992, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025709143885508613, | |
| "eval_loss": 1.1422899961471558, | |
| "eval_runtime": 436.8758, | |
| "eval_samples_per_second": 5.624, | |
| "eval_steps_per_second": 2.813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027423086811209185, | |
| "grad_norm": 1.321584701538086, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.4959, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002913702973690976, | |
| "grad_norm": 1.3295321464538574, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.4349, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030850972662610334, | |
| "grad_norm": 1.6836707592010498, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.4752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003256491558831091, | |
| "grad_norm": 1.7872774600982666, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 4.4012, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034278858514011482, | |
| "grad_norm": 1.1536753177642822, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.1452, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034278858514011482, | |
| "eval_loss": 1.1016162633895874, | |
| "eval_runtime": 433.766, | |
| "eval_samples_per_second": 5.664, | |
| "eval_steps_per_second": 2.833, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003599280143971206, | |
| "grad_norm": 1.463152527809143, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 4.0791, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003770674436541263, | |
| "grad_norm": 1.4073078632354736, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 4.4038, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003942068729111321, | |
| "grad_norm": 1.736242413520813, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.8802, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004113463021681378, | |
| "grad_norm": 1.039347529411316, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.1815, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004284857314251435, | |
| "grad_norm": 1.331517219543457, | |
| "learning_rate": 0.0, | |
| "loss": 3.8949, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004284857314251435, | |
| "eval_loss": 1.0927900075912476, | |
| "eval_runtime": 454.4525, | |
| "eval_samples_per_second": 5.407, | |
| "eval_steps_per_second": 2.704, | |
| "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": 1.03619704651776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |