| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0008742405035625301, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.37120251781265e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.37120251781265e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3310.0675, | |
| "eval_samples_per_second": 2.91, | |
| "eval_steps_per_second": 1.455, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.7424050356253e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013113607553437952, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000174848100712506, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021856012589063252, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021856012589063252, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1742.0118, | |
| "eval_samples_per_second": 5.53, | |
| "eval_steps_per_second": 2.765, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00026227215106875904, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003059841762468855, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000349696201425012, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00039340822660313853, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00043712025178126504, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00043712025178126504, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3045.1749, | |
| "eval_samples_per_second": 3.163, | |
| "eval_steps_per_second": 1.582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004808322769593915, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005245443021375181, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005682563273156445, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000611968352493771, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006556803776718975, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006556803776718975, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3602.512, | |
| "eval_samples_per_second": 2.674, | |
| "eval_steps_per_second": 1.337, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000699392402850024, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007431044280281505, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007868164532062771, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008305284783844036, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008742405035625301, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008742405035625301, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3528.0235, | |
| "eval_samples_per_second": 2.73, | |
| "eval_steps_per_second": 1.365, | |
| "step": 20 | |
| } | |
| ], | |
| "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": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5968528457859072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |