| { | |
| "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": 5.16563081741333, | |
| "learning_rate": 1.6012578616352204e-05, | |
| "loss": 6.1306, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 4.372949123382568, | |
| "eval_runtime": 1.6807, | |
| "eval_samples_per_second": 1844.489, | |
| "eval_steps_per_second": 38.675, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 5.353104114532471, | |
| "learning_rate": 1.2025157232704403e-05, | |
| "loss": 3.4791, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8358064516129032, | |
| "eval_loss": 2.2991185188293457, | |
| "eval_runtime": 1.7158, | |
| "eval_samples_per_second": 1806.701, | |
| "eval_steps_per_second": 37.882, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.990566037735849, | |
| "grad_norm": 5.496769428253174, | |
| "learning_rate": 8.037735849056606e-06, | |
| "loss": 1.9597, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8858064516129033, | |
| "eval_loss": 1.4269509315490723, | |
| "eval_runtime": 1.7177, | |
| "eval_samples_per_second": 1804.767, | |
| "eval_steps_per_second": 37.842, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.9874213836477987, | |
| "grad_norm": 5.15789270401001, | |
| "learning_rate": 4.0503144654088055e-06, | |
| "loss": 1.3145, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9093548387096774, | |
| "eval_loss": 1.1322736740112305, | |
| "eval_runtime": 1.7589, | |
| "eval_samples_per_second": 1762.478, | |
| "eval_steps_per_second": 36.955, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.984276729559748, | |
| "grad_norm": 4.026980876922607, | |
| "learning_rate": 6.289308176100629e-08, | |
| "loss": 1.0832, | |
| "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": 0.25402746437335466, | |
| "num_train_epochs": 5, | |
| "temperature": 20 | |
| } | |
| } | |