| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_loss": 1.2404001951217651, | |
| "eval_runtime": 2.5102, | |
| "eval_samples_per_second": 23.106, | |
| "eval_steps_per_second": 0.398, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "eval_loss": 1.2076923847198486, | |
| "eval_runtime": 2.4258, | |
| "eval_samples_per_second": 23.91, | |
| "eval_steps_per_second": 0.412, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "eval_loss": 1.1614313125610352, | |
| "eval_runtime": 2.1248, | |
| "eval_samples_per_second": 27.296, | |
| "eval_steps_per_second": 0.471, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "step": 6, | |
| "total_flos": 1.7361783597563904e+16, | |
| "train_loss": 1.2026246388753254, | |
| "train_runtime": 2846.6656, | |
| "train_samples_per_second": 1.151, | |
| "train_steps_per_second": 0.002 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7361783597563904e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |