| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9621993127147767, | |
| "eval_steps": 500, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 2.5390625, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5496, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27491408934707906, | |
| "grad_norm": 1.5771484375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 0.66748046875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5563, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5498281786941581, | |
| "grad_norm": 0.6455078125, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5064, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "grad_norm": 0.62451171875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4592, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8247422680412371, | |
| "grad_norm": 0.62939453125, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4184, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9621993127147767, | |
| "grad_norm": 0.576171875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4028, | |
| "step": 70 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 72, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6958061868515328.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |