| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00018715288987456078, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.871528898745608e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.871528898745608e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.7501, | |
| "eval_samples_per_second": 396.44, | |
| "eval_steps_per_second": 198.22, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.743057797491216e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.6145866962368234e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.6145866962368234e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.886, | |
| "eval_samples_per_second": 402.57, | |
| "eval_steps_per_second": 201.285, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.486115594982432e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 9.357644493728039e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011229173392473647, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011229173392473647, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.0349, | |
| "eval_samples_per_second": 401.499, | |
| "eval_steps_per_second": 200.75, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013100702291219253, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00014972231189964863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001684376008871047, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001684376008871047, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.5001, | |
| "eval_samples_per_second": 405.369, | |
| "eval_steps_per_second": 202.684, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00018715288987456078, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 304319889408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |