| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.606060606060606, |
| "eval_steps": 500, |
| "global_step": 6, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.30303030303030304, |
| "grad_norm": 5.730191707611084, |
| "learning_rate": 5.0000000000000004e-08, |
| "loss": 2.0962, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.6060606060606061, |
| "grad_norm": 5.801398277282715, |
| "learning_rate": 1.0000000000000001e-07, |
| "loss": 2.1034, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 5.946535110473633, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 2.1172, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.946535110473633, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 2.0792, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.303030303030303, |
| "grad_norm": 9.686559677124023, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 2.1004, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.606060606060606, |
| "grad_norm": 5.795169830322266, |
| "learning_rate": 3.0000000000000004e-07, |
| "loss": 2.1362, |
| "step": 6 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 18, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.901582302458675e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
