| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.883495145631068, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.970873786407767, |
| "grad_norm": 1.6115515232086182, |
| "learning_rate": 1.6116504854368932e-05, |
| "loss": 0.2004, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.11107288300991058, |
| "eval_runtime": 3.3604, |
| "eval_samples_per_second": 272.289, |
| "eval_steps_per_second": 17.26, |
| "step": 515 |
| }, |
| { |
| "epoch": 1.941747572815534, |
| "grad_norm": 2.384667158126831, |
| "learning_rate": 1.2233009708737864e-05, |
| "loss": 0.088, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.10467015951871872, |
| "eval_runtime": 3.3823, |
| "eval_samples_per_second": 270.524, |
| "eval_steps_per_second": 17.148, |
| "step": 1030 |
| }, |
| { |
| "epoch": 2.912621359223301, |
| "grad_norm": 0.9651037454605103, |
| "learning_rate": 8.349514563106797e-06, |
| "loss": 0.062, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.11426738649606705, |
| "eval_runtime": 3.3899, |
| "eval_samples_per_second": 269.921, |
| "eval_steps_per_second": 17.11, |
| "step": 1545 |
| }, |
| { |
| "epoch": 3.883495145631068, |
| "grad_norm": 1.4941452741622925, |
| "learning_rate": 4.466019417475729e-06, |
| "loss": 0.0423, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2575, |
| "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": 2088546496796160.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
