| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.394285714285715, |
| "eval_steps": 500, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.23, |
| "learning_rate": 9.326113116726836e-05, |
| "loss": 0.9377, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 8.122743682310469e-05, |
| "loss": 0.866, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.13, |
| "eval_loss": 0.867071270942688, |
| "eval_runtime": 166.3463, |
| "eval_samples_per_second": 1.803, |
| "eval_steps_per_second": 0.228, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 6.919374247894104e-05, |
| "loss": 0.8347, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.03, |
| "learning_rate": 5.7160048134777375e-05, |
| "loss": 0.8181, |
| "step": 800 |
| }, |
| { |
| "epoch": 6.26, |
| "learning_rate": 4.5126353790613716e-05, |
| "loss": 0.7979, |
| "step": 1000 |
| }, |
| { |
| "epoch": 6.26, |
| "eval_loss": 0.8691695332527161, |
| "eval_runtime": 166.0527, |
| "eval_samples_per_second": 1.807, |
| "eval_steps_per_second": 0.229, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.5, |
| "learning_rate": 3.3092659446450064e-05, |
| "loss": 0.7893, |
| "step": 1200 |
| }, |
| { |
| "epoch": 8.73, |
| "learning_rate": 2.1058965102286405e-05, |
| "loss": 0.7738, |
| "step": 1400 |
| }, |
| { |
| "epoch": 9.39, |
| "eval_loss": 0.8755550980567932, |
| "eval_runtime": 165.9873, |
| "eval_samples_per_second": 1.807, |
| "eval_steps_per_second": 0.229, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 1750, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 1.899984780703826e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
