| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1446540880503147, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.3104, | |
| "eval_samples_per_second": 583.757, | |
| "eval_steps_per_second": 12.24, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 94451.3046875, | |
| "learning_rate": 1.371069182389937e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4472, | |
| "eval_samples_per_second": 569.1, | |
| "eval_steps_per_second": 11.933, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4183, | |
| "eval_samples_per_second": 572.14, | |
| "eval_steps_per_second": 11.996, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 233628.765625, | |
| "learning_rate": 7.421383647798742e-06, | |
| "loss": 0.0, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 260941334653608.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.16176343022645268, | |
| "num_train_epochs": 5, | |
| "temperature": 12 | |
| } | |
| } | |