| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1908, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9968553459119497, |
| "grad_norm": 9.086099624633789, |
| "learning_rate": 1.668763102725367e-05, |
| "loss": 24.0673, |
| "step": 317 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.0070967741935483875, |
| "eval_loss": 19.49103546142578, |
| "eval_runtime": 7.6153, |
| "eval_samples_per_second": 407.075, |
| "eval_steps_per_second": 8.535, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.9937106918238994, |
| "grad_norm": 27.5584774017334, |
| "learning_rate": 1.3364779874213839e-05, |
| "loss": 18.0349, |
| "step": 634 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.006129032258064516, |
| "eval_loss": 16.721590042114258, |
| "eval_runtime": 7.6867, |
| "eval_samples_per_second": 403.292, |
| "eval_steps_per_second": 8.456, |
| "step": 636 |
| }, |
| { |
| "epoch": 2.990566037735849, |
| "grad_norm": 42.37278747558594, |
| "learning_rate": 1.0041928721174005e-05, |
| "loss": 15.3119, |
| "step": 951 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.004516129032258065, |
| "eval_loss": 14.560099601745605, |
| "eval_runtime": 7.5972, |
| "eval_samples_per_second": 408.046, |
| "eval_steps_per_second": 8.556, |
| "step": 954 |
| }, |
| { |
| "epoch": 3.9874213836477987, |
| "grad_norm": 26.386045455932617, |
| "learning_rate": 6.719077568134172e-06, |
| "loss": 13.2276, |
| "step": 1268 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.004838709677419355, |
| "eval_loss": 13.145710945129395, |
| "eval_runtime": 7.6471, |
| "eval_samples_per_second": 405.382, |
| "eval_steps_per_second": 8.5, |
| "step": 1272 |
| }, |
| { |
| "epoch": 4.984276729559748, |
| "grad_norm": 41.96089553833008, |
| "learning_rate": 3.3962264150943395e-06, |
| "loss": 12.0241, |
| "step": 1585 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.004838709677419355, |
| "eval_loss": 12.470986366271973, |
| "eval_runtime": 7.6586, |
| "eval_samples_per_second": 404.773, |
| "eval_steps_per_second": 8.487, |
| "step": 1590 |
| }, |
| { |
| "epoch": 5.981132075471698, |
| "grad_norm": 49.987388610839844, |
| "learning_rate": 7.337526205450734e-08, |
| "loss": 11.367, |
| "step": 1902 |
| } |
| ], |
| "logging_steps": 317, |
| "max_steps": 1908, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 1000000000.0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 495439677408900.0, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.09741759782391846, |
| "num_train_epochs": 6, |
| "temperature": 7 |
| } |
| } |
|
|
