| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1590, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9968553459119497, | |
| "grad_norm": 0.6950033903121948, | |
| "learning_rate": 1.6012578616352204e-05, | |
| "loss": 0.3925, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5609677419354838, | |
| "eval_loss": 0.20299369096755981, | |
| "eval_runtime": 1.7311, | |
| "eval_samples_per_second": 1790.751, | |
| "eval_steps_per_second": 37.548, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 0.4946860373020172, | |
| "learning_rate": 1.2025157232704403e-05, | |
| "loss": 0.1736, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7987096774193548, | |
| "eval_loss": 0.10688149929046631, | |
| "eval_runtime": 1.717, | |
| "eval_samples_per_second": 1805.465, | |
| "eval_steps_per_second": 37.857, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.990566037735849, | |
| "grad_norm": 0.4743373990058899, | |
| "learning_rate": 8.037735849056606e-06, | |
| "loss": 0.1151, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8580645161290322, | |
| "eval_loss": 0.07752583920955658, | |
| "eval_runtime": 1.7617, | |
| "eval_samples_per_second": 1759.674, | |
| "eval_steps_per_second": 36.896, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.9874213836477987, | |
| "grad_norm": 0.4146045744419098, | |
| "learning_rate": 4.0503144654088055e-06, | |
| "loss": 0.0933, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8754838709677419, | |
| "eval_loss": 0.06553368270397186, | |
| "eval_runtime": 1.7696, | |
| "eval_samples_per_second": 1751.791, | |
| "eval_steps_per_second": 36.731, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.984276729559748, | |
| "grad_norm": 0.3400251865386963, | |
| "learning_rate": 6.289308176100629e-08, | |
| "loss": 0.0843, | |
| "step": 1585 | |
| } | |
| ], | |
| "logging_steps": 317, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000000000.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 413495819944032.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.800129291798159, | |
| "num_train_epochs": 5, | |
| "temperature": 15 | |
| } | |
| } | |