| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5383177570093458, | |
| "eval_steps": 7, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029906542056074768, | |
| "eval_loss": 3.908674716949463, | |
| "eval_runtime": 11.8982, | |
| "eval_samples_per_second": 18.995, | |
| "eval_steps_per_second": 2.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20934579439252338, | |
| "eval_loss": 0.4576127827167511, | |
| "eval_runtime": 11.8715, | |
| "eval_samples_per_second": 19.037, | |
| "eval_steps_per_second": 2.443, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 29.873859405517578, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 27.8654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41869158878504675, | |
| "eval_loss": 9.885928193398286e-06, | |
| "eval_runtime": 11.905, | |
| "eval_samples_per_second": 18.984, | |
| "eval_steps_per_second": 2.436, | |
| "step": 14 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.047688983530701e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |