| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 185, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 7.509580612182617, |
| "eval_runtime": 14.6263, |
| "eval_samples_per_second": 9.914, |
| "eval_steps_per_second": 0.684, |
| "step": 37 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 6.186887741088867, |
| "eval_runtime": 14.3793, |
| "eval_samples_per_second": 10.084, |
| "eval_steps_per_second": 0.695, |
| "step": 74 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.2302987575531006, |
| "eval_runtime": 14.3821, |
| "eval_samples_per_second": 10.082, |
| "eval_steps_per_second": 0.695, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.7003790736198425, |
| "eval_runtime": 14.581, |
| "eval_samples_per_second": 9.944, |
| "eval_steps_per_second": 0.686, |
| "step": 148 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.5474433898925781, |
| "eval_runtime": 14.3989, |
| "eval_samples_per_second": 10.07, |
| "eval_steps_per_second": 0.694, |
| "step": 185 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 185, |
| "total_flos": 6.705406255177728e+16, |
| "train_loss": 2.0429481300147803, |
| "train_runtime": 422.6396, |
| "train_samples_per_second": 6.873, |
| "train_steps_per_second": 0.438 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 185, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.705406255177728e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
