| { |
| "best_metric": 3.3264334201812744, |
| "best_model_checkpoint": "uripper/ReviewTrainingBot/checkpoint-45000", |
| "epoch": 1.0144274120829577, |
| "global_step": 45000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.0009818840579710146, |
| "loss": 4.0894, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.11, |
| "eval_loss": 3.8452765941619873, |
| "eval_runtime": 381.5421, |
| "eval_samples_per_second": 129.184, |
| "eval_steps_per_second": 6.461, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0009592391304347826, |
| "loss": 3.7663, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.23, |
| "eval_loss": 3.625126600265503, |
| "eval_runtime": 382.09, |
| "eval_samples_per_second": 128.998, |
| "eval_steps_per_second": 6.451, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0009365942028985508, |
| "loss": 3.6267, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.34, |
| "eval_loss": 3.5167148113250732, |
| "eval_runtime": 379.2329, |
| "eval_samples_per_second": 129.97, |
| "eval_steps_per_second": 6.5, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0009139492753623188, |
| "loss": 3.5371, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.45, |
| "eval_loss": 3.4787251949310303, |
| "eval_runtime": 379.8968, |
| "eval_samples_per_second": 129.743, |
| "eval_steps_per_second": 6.489, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0008913043478260869, |
| "loss": 3.4932, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 3.4222865104675293, |
| "eval_runtime": 380.3957, |
| "eval_samples_per_second": 129.573, |
| "eval_steps_per_second": 6.48, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0008686594202898551, |
| "loss": 3.4695, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_loss": 3.398277997970581, |
| "eval_runtime": 379.1493, |
| "eval_samples_per_second": 129.999, |
| "eval_steps_per_second": 6.501, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0008460144927536231, |
| "loss": 3.4292, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.79, |
| "eval_loss": 3.3613269329071045, |
| "eval_runtime": 379.3995, |
| "eval_samples_per_second": 129.913, |
| "eval_steps_per_second": 6.497, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0008233695652173913, |
| "loss": 3.401, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.9, |
| "eval_loss": 3.334460973739624, |
| "eval_runtime": 380.9663, |
| "eval_samples_per_second": 129.379, |
| "eval_steps_per_second": 6.47, |
| "step": 40000 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.0008007246376811594, |
| "loss": 3.3928, |
| "step": 45000 |
| }, |
| { |
| "epoch": 1.01, |
| "eval_loss": 3.3264334201812744, |
| "eval_runtime": 381.4314, |
| "eval_samples_per_second": 129.221, |
| "eval_steps_per_second": 6.462, |
| "step": 45000 |
| } |
| ], |
| "max_steps": 221800, |
| "num_train_epochs": 5, |
| "total_flos": 9186152646574080.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
