| { |
| "best_global_step": 1506, |
| "best_metric": 2.882674217224121, |
| "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": 29.590858459472656, |
| "learning_rate": 0.0, |
| "loss": 10.3947, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.1284607648849487, |
| "learning_rate": 9.995012468827932e-05, |
| "loss": 4.467, |
| "step": 502 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.2831802368164062, |
| "eval_runtime": 19.9942, |
| "eval_samples_per_second": 1587.06, |
| "eval_steps_per_second": 6.202, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7505791187286377, |
| "learning_rate": 7.491271820448879e-05, |
| "loss": 3.0403, |
| "step": 1004 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.982789993286133, |
| "eval_runtime": 20.0654, |
| "eval_samples_per_second": 1581.431, |
| "eval_steps_per_second": 6.18, |
| "step": 1004 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7990893721580505, |
| "learning_rate": 4.987531172069826e-05, |
| "loss": 2.8221, |
| "step": 1506 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.882674217224121, |
| "eval_runtime": 20.0103, |
| "eval_samples_per_second": 1585.785, |
| "eval_steps_per_second": 6.197, |
| "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": 3.3432838078464e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
