| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0017498291182501708, |
| "eval_steps": 2, |
| "global_step": 4, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004374572795625427, |
| "grad_norm": 0.5104346871376038, |
| "learning_rate": 1e-05, |
| "loss": 1.9641, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0004374572795625427, |
| "eval_loss": 3.3701279163360596, |
| "eval_runtime": 348.7851, |
| "eval_samples_per_second": 11.038, |
| "eval_steps_per_second": 5.519, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0008749145591250854, |
| "grad_norm": 0.6189126968383789, |
| "learning_rate": 2e-05, |
| "loss": 2.2266, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0008749145591250854, |
| "eval_loss": 3.3415215015411377, |
| "eval_runtime": 274.714, |
| "eval_samples_per_second": 14.015, |
| "eval_steps_per_second": 7.007, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0013123718386876281, |
| "grad_norm": 0.5454967021942139, |
| "learning_rate": 3e-05, |
| "loss": 1.9636, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0017498291182501708, |
| "grad_norm": 0.7716733813285828, |
| "learning_rate": 4e-05, |
| "loss": 2.9186, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0017498291182501708, |
| "eval_loss": 3.322148323059082, |
| "eval_runtime": 275.0609, |
| "eval_samples_per_second": 13.997, |
| "eval_steps_per_second": 6.998, |
| "step": 4 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2173128962211840.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
