| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07418397626112759, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000741839762611276, | |
| "eval_loss": NaN, | |
| "eval_runtime": 19.1562, | |
| "eval_samples_per_second": 29.651, | |
| "eval_steps_per_second": 7.413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00741839762611276, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.05e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01483679525222552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.01e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02225519287833828, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.323076923076924e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02967359050445104, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.546153846153847e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.037091988130563795, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.76923076923077e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.037091988130563795, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.5569, | |
| "eval_samples_per_second": 30.608, | |
| "eval_steps_per_second": 7.652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04451038575667656, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.992307692307692e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05192878338278932, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.215384615384615e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05934718100890208, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.438461538461538e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06676557863501484, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.661538461538462e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07418397626112759, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.884615384615385e-06, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07418397626112759, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.5563, | |
| "eval_samples_per_second": 30.61, | |
| "eval_steps_per_second": 7.652, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.43327370412032e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |