| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 225, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 3.03688383102417, | |
| "learning_rate": 9.070345120512436e-05, | |
| "loss": 2.5962, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.6005353927612305, | |
| "learning_rate": 6.142689677583446e-05, | |
| "loss": 0.7741, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 11.031198501586914, | |
| "learning_rate": 2.6469889419018985e-05, | |
| "loss": 0.3742, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.9459794163703918, | |
| "learning_rate": 3.2099935489722897e-06, | |
| "loss": 0.2984, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 225, | |
| "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": 2.15689039183872e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |