| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 5256, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0001902587519025875, |
| "grad_norm": 6.173529624938965, |
| "learning_rate": 0.0, |
| "loss": 2.3156, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.380517503805175, |
| "grad_norm": 4.211840629577637, |
| "learning_rate": 1.9509538417053586e-05, |
| "loss": 2.0027, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.380517503805175, |
| "eval_loss": 1.2400720119476318, |
| "eval_runtime": 73.7674, |
| "eval_samples_per_second": 390.769, |
| "eval_steps_per_second": 1.532, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.76103500761035, |
| "grad_norm": 4.12247371673584, |
| "learning_rate": 1.558121760403115e-05, |
| "loss": 2.3392, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.76103500761035, |
| "eval_loss": 1.0379940271377563, |
| "eval_runtime": 15.8497, |
| "eval_samples_per_second": 1818.712, |
| "eval_steps_per_second": 7.129, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 10512, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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 |
| } |
|
|
