| { | |
| "best_metric": 1.2736992835998535, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.003021490350115194, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015107451750575972, | |
| "eval_loss": 1.5089695453643799, | |
| "eval_runtime": 568.2976, | |
| "eval_samples_per_second": 4.904, | |
| "eval_steps_per_second": 2.453, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045322355251727916, | |
| "grad_norm": 1.1529654264450073, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5891, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007553725875287985, | |
| "eval_loss": 1.464594841003418, | |
| "eval_runtime": 596.2189, | |
| "eval_samples_per_second": 4.674, | |
| "eval_steps_per_second": 2.338, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009064471050345583, | |
| "grad_norm": 0.9356080889701843, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 1.4835, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013596706575518375, | |
| "grad_norm": 0.6017722487449646, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 1.458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001510745175057597, | |
| "eval_loss": 1.361315369606018, | |
| "eval_runtime": 594.4888, | |
| "eval_samples_per_second": 4.688, | |
| "eval_steps_per_second": 2.345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018128942100691166, | |
| "grad_norm": 1.7533838748931885, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 1.4518, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022661177625863957, | |
| "grad_norm": 0.5131815671920776, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.2514, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022661177625863957, | |
| "eval_loss": 1.305673360824585, | |
| "eval_runtime": 593.153, | |
| "eval_samples_per_second": 4.699, | |
| "eval_steps_per_second": 2.35, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002719341315103675, | |
| "grad_norm": 0.64283686876297, | |
| "learning_rate": 4.6860474023534335e-05, | |
| "loss": 1.2529, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003021490350115194, | |
| "eval_loss": 1.2736992835998535, | |
| "eval_runtime": 593.2721, | |
| "eval_samples_per_second": 4.698, | |
| "eval_steps_per_second": 2.35, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 7418872835604480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |