| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 2663, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0003755163349605708, |
| "grad_norm": 6.263205528259277, |
| "learning_rate": 0.0, |
| "loss": 3.7128, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3755163349605708, |
| "grad_norm": 3.8261115550994873, |
| "learning_rate": 7.502816372512205e-06, |
| "loss": 2.8207, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3755163349605708, |
| "eval_cosine_accuracy": 0.9523609280586243, |
| "eval_loss": 1.359626054763794, |
| "eval_runtime": 22.5746, |
| "eval_samples_per_second": 421.226, |
| "eval_steps_per_second": 1.683, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7510326699211416, |
| "grad_norm": 3.8652374744415283, |
| "learning_rate": 1.5013143071723622e-05, |
| "loss": 2.2515, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.7510326699211416, |
| "eval_cosine_accuracy": 0.9578294157981873, |
| "eval_loss": 1.3198553323745728, |
| "eval_runtime": 22.5254, |
| "eval_samples_per_second": 422.145, |
| "eval_steps_per_second": 1.687, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 13315, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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 |
| } |
|
|
