| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994879672299027, | |
| "eval_steps": 500, | |
| "global_step": 976, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5120327700972862, | |
| "grad_norm": 0.4505118429660797, | |
| "learning_rate": 2.530737704918033e-05, | |
| "loss": 0.6045, | |
| "mean_token_accuracy": 0.8118490787744522, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9994879672299027, | |
| "mean_token_accuracy": 0.8271949754542663, | |
| "step": 976, | |
| "total_flos": 1.508642928128426e+18, | |
| "train_loss": 0.5703659995657498, | |
| "train_runtime": 8078.2892, | |
| "train_samples_per_second": 11.603, | |
| "train_steps_per_second": 0.121 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 976, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.508642928128426e+18, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |