| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9970457902511078, | |
| "eval_steps": 500, | |
| "global_step": 338, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29542097488921715, | |
| "grad_norm": 3.6940183639526367, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.3429, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "grad_norm": 0.5006749033927917, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7796, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8862629246676514, | |
| "grad_norm": 0.5715117454528809, | |
| "learning_rate": 4.726477024070022e-05, | |
| "loss": 0.22, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1816838995568686, | |
| "grad_norm": 0.7143971920013428, | |
| "learning_rate": 4.452954048140044e-05, | |
| "loss": 0.1198, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4771048744460857, | |
| "grad_norm": 0.380874902009964, | |
| "learning_rate": 4.179431072210066e-05, | |
| "loss": 0.117, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7725258493353029, | |
| "grad_norm": 0.3196457028388977, | |
| "learning_rate": 3.9059080962800876e-05, | |
| "loss": 0.1134, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1014, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 5.346534977961984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |