| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.4787958427905865, | |
| "eval_steps": 500, | |
| "global_step": 41500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9999402699796918, | |
| "grad_norm": 1.324739933013916, | |
| "learning_rate": 1.3336518934416438e-05, | |
| "loss": 4.0956, | |
| "step": 16741 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.856391191482544, | |
| "eval_runtime": 281.5542, | |
| "eval_samples_per_second": 210.485, | |
| "eval_steps_per_second": 6.578, | |
| "step": 16742 | |
| }, | |
| { | |
| "epoch": 1.9998805399593835, | |
| "grad_norm": 1.373618721961975, | |
| "learning_rate": 6.673037868832876e-06, | |
| "loss": 3.8963, | |
| "step": 33482 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.7781829833984375, | |
| "eval_runtime": 281.2653, | |
| "eval_samples_per_second": 210.701, | |
| "eval_steps_per_second": 6.585, | |
| "step": 33484 | |
| } | |
| ], | |
| "logging_steps": 16741, | |
| "max_steps": 50226, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 8.6747386871808e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |