| { |
| "best_global_step": 1506, |
| "best_metric": 3.306654214859009, |
| "best_model_checkpoint": null, |
| "epoch": 3.9840637450199203, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00199203187250996, |
| "grad_norm": 30.39765739440918, |
| "learning_rate": 0.0, |
| "loss": 10.3969, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.4528049230575562, |
| "learning_rate": 9.995012468827932e-05, |
| "loss": 4.8126, |
| "step": 502 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.7866852283477783, |
| "eval_runtime": 20.1378, |
| "eval_samples_per_second": 1574.851, |
| "eval_steps_per_second": 6.158, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.2457406520843506, |
| "learning_rate": 7.491271820448879e-05, |
| "loss": 3.5387, |
| "step": 1004 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 3.4403388500213623, |
| "eval_runtime": 20.1359, |
| "eval_samples_per_second": 1574.997, |
| "eval_steps_per_second": 6.158, |
| "step": 1004 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.3165825605392456, |
| "learning_rate": 4.987531172069826e-05, |
| "loss": 3.2924, |
| "step": 1506 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 3.306654214859009, |
| "eval_runtime": 20.2048, |
| "eval_samples_per_second": 1569.627, |
| "eval_steps_per_second": 6.137, |
| "step": 1506 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2510, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 3.3411477454848e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
