| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1030, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4114757045128635, | |
| "las": 89.85969387755102, | |
| "step": 206, | |
| "uas": 92.22972972972973 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3510205694169642, | |
| "las": 91.43684500827358, | |
| "step": 412, | |
| "uas": 93.517305570877 | |
| }, | |
| { | |
| "epoch": 2.4271844660194173, | |
| "grad_norm": 1.5433143377304077, | |
| "learning_rate": 0.0001029126213592233, | |
| "loss": 0.5034, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.350202233017048, | |
| "las": 92.37279371207943, | |
| "step": 618, | |
| "uas": 94.20332322118037 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.3903549225809418, | |
| "las": 92.64857970215114, | |
| "step": 824, | |
| "uas": 94.34466354109212 | |
| }, | |
| { | |
| "epoch": 4.854368932038835, | |
| "grad_norm": 0.9959699511528015, | |
| "learning_rate": 5.825242718446602e-06, | |
| "loss": 0.1108, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1030, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.126545536687616e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |