| { |
| "best_metric": 1.7229349613189697, |
| "best_model_checkpoint": "./lora/checkpoint-20", |
| "epoch": 2.814814814814815, |
| "eval_steps": 10, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 2.1439, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 2.1733, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 2.4e-05, |
| "loss": 2.1888, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 2.1669, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 4e-05, |
| "loss": 2.1474, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 4.8e-05, |
| "loss": 2.1836, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 5.6e-05, |
| "loss": 2.153, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 6.400000000000001e-05, |
| "loss": 2.1718, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 7.2e-05, |
| "loss": 2.1497, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 8e-05, |
| "loss": 2.0833, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.41, |
| "eval_loss": 1.9357084035873413, |
| "eval_runtime": 19.7161, |
| "eval_samples_per_second": 9.028, |
| "eval_steps_per_second": 1.522, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 7.950753362380551e-05, |
| "loss": 2.036, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 7.804226065180615e-05, |
| "loss": 1.9942, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 7.564026096753472e-05, |
| "loss": 1.9095, |
| "step": 13 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 7.236067977499791e-05, |
| "loss": 1.8901, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 6.828427124746191e-05, |
| "loss": 1.8971, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 6.351141009169893e-05, |
| "loss": 1.8543, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 5.8159619989581874e-05, |
| "loss": 1.85, |
| "step": 17 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 5.23606797749979e-05, |
| "loss": 1.8474, |
| "step": 18 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 4.625737860160924e-05, |
| "loss": 1.7926, |
| "step": 19 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 4e-05, |
| "loss": 1.8053, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.81, |
| "eval_loss": 1.7229349613189697, |
| "eval_runtime": 19.7517, |
| "eval_samples_per_second": 9.012, |
| "eval_steps_per_second": 1.519, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 30, |
| "num_train_epochs": 5, |
| "save_steps": 20, |
| "total_flos": 2.5066388549586125e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
