| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.15007816571130797, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016675351745700884, | |
| "eval_loss": 11.763640403747559, | |
| "eval_runtime": 1.6992, | |
| "eval_samples_per_second": 119.468, | |
| "eval_steps_per_second": 60.028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05002605523710266, | |
| "grad_norm": 0.028261149302124977, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 11.7625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10005211047420531, | |
| "grad_norm": 0.028932636603713036, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 11.7641, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15007816571130797, | |
| "grad_norm": 0.030681710690259933, | |
| "learning_rate": 6.75e-05, | |
| "loss": 11.7637, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15007816571130797, | |
| "eval_loss": 11.76322078704834, | |
| "eval_runtime": 1.6869, | |
| "eval_samples_per_second": 120.339, | |
| "eval_steps_per_second": 60.466, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "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": 17003186749440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |