| { | |
| "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": 0.5880645161290322, | |
| "eval_loss": 0.20545053482055664, | |
| "eval_runtime": 5.4097, | |
| "eval_samples_per_second": 573.042, | |
| "eval_steps_per_second": 12.015, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 0.5401266813278198, | |
| "learning_rate": 1.606918238993711e-05, | |
| "loss": 0.329, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8193548387096774, | |
| "eval_loss": 0.09952054172754288, | |
| "eval_runtime": 5.6388, | |
| "eval_samples_per_second": 549.765, | |
| "eval_steps_per_second": 11.527, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8770967741935484, | |
| "eval_loss": 0.06660476326942444, | |
| "eval_runtime": 5.4854, | |
| "eval_samples_per_second": 565.134, | |
| "eval_steps_per_second": 11.85, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.46109867095947266, | |
| "learning_rate": 1.2138364779874214e-05, | |
| "loss": 0.1154, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2544, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 0.9954095615776885, | |
| "num_train_epochs": 8, | |
| "temperature": 9 | |
| } | |
| } | |