| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.10778947368421053, |
| "eval_steps": 500, |
| "global_step": 2, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 1.9848077530122083e-05, |
| "loss": 2.3864, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.11, |
| "eval_loss": 2.3830578327178955, |
| "eval_runtime": 22.0897, |
| "eval_samples_per_second": 22.635, |
| "eval_steps_per_second": 2.852, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11, |
| "step": 2, |
| "total_flos": 1.9781391004729344e+17, |
| "train_loss": 3.4910590648651123, |
| "train_runtime": 1414.3444, |
| "train_samples_per_second": 6.717, |
| "train_steps_per_second": 0.013 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 18, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "total_flos": 1.9781391004729344e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
