| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 23, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 0.8347742557525635, |
| "learning_rate": 1.4539904997395468e-05, |
| "loss": 1.3742, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 0.5884836316108704, |
| "learning_rate": 1.0899347581163222e-06, |
| "loss": 1.2486, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.2133620977401733, |
| "eval_runtime": 0.5411, |
| "eval_samples_per_second": 1145.916, |
| "eval_steps_per_second": 9.241, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 23, |
| "total_flos": 3.742438758599885e+16, |
| "train_loss": 1.3040671763212786, |
| "train_runtime": 45.9345, |
| "train_samples_per_second": 256.104, |
| "train_steps_per_second": 0.501 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 23, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 3.742438758599885e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
