| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.6625103906899419, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.41562759767248547, |
| "grad_norm": 56089.828125, |
| "learning_rate": 1.7229149348850097e-05, |
| "loss": 0.4691, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8312551953449709, |
| "grad_norm": 31839.919921875, |
| "learning_rate": 1.4458298697700195e-05, |
| "loss": 0.392, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.31241247057914734, |
| "eval_runtime": 34.4517, |
| "eval_samples_per_second": 14.339, |
| "eval_steps_per_second": 1.8, |
| "step": 1203 |
| }, |
| { |
| "epoch": 1.2468827930174564, |
| "grad_norm": 29103.794921875, |
| "learning_rate": 1.1687448046550292e-05, |
| "loss": 0.3735, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.6625103906899419, |
| "grad_norm": 38289.87890625, |
| "learning_rate": 8.916597395400388e-06, |
| "loss": 0.3557, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3609, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9742717291069440.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
