| { | |
| "best_metric": 1.948099970817566, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.008992805755395683, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00035971223021582735, | |
| "grad_norm": 1.0552481412887573, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1894, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035971223021582735, | |
| "eval_loss": 2.2143394947052, | |
| "eval_runtime": 317.392, | |
| "eval_samples_per_second": 3.689, | |
| "eval_steps_per_second": 1.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007194244604316547, | |
| "grad_norm": 1.6790050268173218, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4818, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001079136690647482, | |
| "grad_norm": 1.3203463554382324, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5191, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014388489208633094, | |
| "grad_norm": 1.14222252368927, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1216, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017985611510791368, | |
| "grad_norm": 1.0097196102142334, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2461, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017985611510791368, | |
| "eval_loss": 2.158903121948242, | |
| "eval_runtime": 314.9939, | |
| "eval_samples_per_second": 3.718, | |
| "eval_steps_per_second": 1.86, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002158273381294964, | |
| "grad_norm": 1.7000837326049805, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0936, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002517985611510791, | |
| "grad_norm": 1.5124508142471313, | |
| "learning_rate": 0.00014, | |
| "loss": 2.523, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0028776978417266188, | |
| "grad_norm": 1.2431156635284424, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5262, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003237410071942446, | |
| "grad_norm": 1.000595211982727, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6474, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0035971223021582736, | |
| "grad_norm": 1.0155411958694458, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035971223021582736, | |
| "eval_loss": 2.0206987857818604, | |
| "eval_runtime": 309.5749, | |
| "eval_samples_per_second": 3.783, | |
| "eval_steps_per_second": 1.893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003956834532374101, | |
| "grad_norm": 1.3787400722503662, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.2416, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004316546762589928, | |
| "grad_norm": 1.321842908859253, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004676258992805755, | |
| "grad_norm": 1.261904239654541, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.1633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005035971223021582, | |
| "grad_norm": 1.3204586505889893, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.3555, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00539568345323741, | |
| "grad_norm": 1.1878812313079834, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.984, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00539568345323741, | |
| "eval_loss": 1.9619755744934082, | |
| "eval_runtime": 310.7244, | |
| "eval_samples_per_second": 3.769, | |
| "eval_steps_per_second": 1.886, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0057553956834532375, | |
| "grad_norm": 1.368757963180542, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8076, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006115107913669065, | |
| "grad_norm": 1.3265300989151, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.9355, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006474820143884892, | |
| "grad_norm": 1.2753698825836182, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5823, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006834532374100719, | |
| "grad_norm": 1.0070078372955322, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.0167, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007194244604316547, | |
| "grad_norm": 1.23676598072052, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.6254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007194244604316547, | |
| "eval_loss": 1.949695348739624, | |
| "eval_runtime": 311.4876, | |
| "eval_samples_per_second": 3.759, | |
| "eval_steps_per_second": 1.881, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007553956834532374, | |
| "grad_norm": 1.2649297714233398, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.8839, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007913669064748202, | |
| "grad_norm": 1.2358827590942383, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.3107, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008273381294964029, | |
| "grad_norm": 0.9645010828971863, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.9028, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008633093525179856, | |
| "grad_norm": 1.1274240016937256, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.6263, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008992805755395683, | |
| "grad_norm": 1.1118935346603394, | |
| "learning_rate": 0.0, | |
| "loss": 2.0588, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008992805755395683, | |
| "eval_loss": 1.948099970817566, | |
| "eval_runtime": 311.2703, | |
| "eval_samples_per_second": 3.762, | |
| "eval_steps_per_second": 1.883, | |
| "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": 5303278680145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |