| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 384, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13020833333333334, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2604166666666667, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.390625, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5208333333333334, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6510416666666666, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.78125, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9114583333333334, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 384, |
| "total_flos": 2.68510984370604e+17, |
| "train_loss": 0.0, |
| "train_runtime": 10187.5599, |
| "train_samples_per_second": 2.412, |
| "train_steps_per_second": 0.038 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 384, |
| "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": 2.68510984370604e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|