| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9846153846153847, |
| "eval_steps": 500, |
| "global_step": 56, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17582417582417584, |
| "grad_norm": 2.1388941533505665, |
| "learning_rate": 4.921457902821578e-06, |
| "loss": 1.154, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3516483516483517, |
| "grad_norm": 1.1259907080099065, |
| "learning_rate": 4.093559974371725e-06, |
| "loss": 0.8713, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5274725274725275, |
| "grad_norm": 0.6382059432052274, |
| "learning_rate": 2.6569762988232838e-06, |
| "loss": 0.762, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7032967032967034, |
| "grad_norm": 0.5375312211343909, |
| "learning_rate": 1.160433012552508e-06, |
| "loss": 0.7202, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8791208791208791, |
| "grad_norm": 0.5032147276883348, |
| "learning_rate": 1.7555878527937164e-07, |
| "loss": 0.6998, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 56, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 55816833990656.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
