| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 53.173946380615234, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 1.6018, | |
| "num_input_tokens_seen": 20336, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 19.21953773498535, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 1.0277, | |
| "num_input_tokens_seen": 41392, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 15.321002006530762, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.7125, | |
| "num_input_tokens_seen": 61520, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 73328, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 869206018179072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |