| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 3000, |
| "global_step": 6150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00016260162601626016, |
| "grad_norm": 6.182025909423828, |
| "learning_rate": 0.0, |
| "loss": 3.6915, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.4878048780487805, |
| "grad_norm": 4.05953311920166, |
| "learning_rate": 4.062330623306233e-05, |
| "loss": 2.5598, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.4878048780487805, |
| "eval_cosine_accuracy": 0.9593281149864197, |
| "eval_loss": 0.8499817848205566, |
| "eval_runtime": 33.8697, |
| "eval_samples_per_second": 279.483, |
| "eval_steps_per_second": 1.092, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 5.307164192199707, |
| "learning_rate": 4.7043640447017424e-05, |
| "loss": 2.8278, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "eval_cosine_accuracy": 0.9243608713150024, |
| "eval_loss": 1.0148402452468872, |
| "eval_runtime": 32.3667, |
| "eval_samples_per_second": 292.461, |
| "eval_steps_per_second": 1.143, |
| "step": 6000 |
| } |
| ], |
| "logging_steps": 3000, |
| "max_steps": 18450, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
