| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 4749, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00021059281878487945, |
| "grad_norm": 6.283910751342773, |
| "learning_rate": 0.0, |
| "loss": 2.9659, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.42118563756975885, |
| "grad_norm": 3.459829092025757, |
| "learning_rate": 6.308972198820557e-06, |
| "loss": 2.3382, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.42118563756975885, |
| "eval_cosine_accuracy": 0.940467357635498, |
| "eval_loss": 0.7114619016647339, |
| "eval_runtime": 39.4223, |
| "eval_samples_per_second": 239.889, |
| "eval_steps_per_second": 0.939, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8423712751395177, |
| "grad_norm": 3.597459077835083, |
| "learning_rate": 1.262742207245156e-05, |
| "loss": 1.5917, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.8423712751395177, |
| "eval_cosine_accuracy": 0.94924396276474, |
| "eval_loss": 0.6677370667457581, |
| "eval_runtime": 38.4447, |
| "eval_samples_per_second": 245.99, |
| "eval_steps_per_second": 0.962, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 28494, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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 |
| } |
|
|
