| { |
| "best_metric": 0.04804013669490814, |
| "best_model_checkpoint": "reranker_training_output/focal_question_0.1/checkpoint-1074", |
| "epoch": 12.0, |
| "global_step": 4296, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.05196131765842438, |
| "eval_runtime": 16.6877, |
| "eval_samples_per_second": 556.038, |
| "step": 358 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 4.860335195530727e-05, |
| "loss": 0.0343, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.05120062083005905, |
| "eval_runtime": 16.6718, |
| "eval_samples_per_second": 556.569, |
| "step": 716 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 4.7206703910614525e-05, |
| "loss": 0.0152, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.04804013669490814, |
| "eval_runtime": 16.6811, |
| "eval_samples_per_second": 556.259, |
| "step": 1074 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.04958715662360191, |
| "eval_runtime": 16.6857, |
| "eval_samples_per_second": 556.107, |
| "step": 1432 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 4.581005586592179e-05, |
| "loss": 0.0095, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.05102628469467163, |
| "eval_runtime": 16.7038, |
| "eval_samples_per_second": 555.502, |
| "step": 1790 |
| }, |
| { |
| "epoch": 5.59, |
| "learning_rate": 4.4413407821229054e-05, |
| "loss": 0.0071, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.05404501408338547, |
| "eval_runtime": 16.6952, |
| "eval_samples_per_second": 555.788, |
| "step": 2148 |
| }, |
| { |
| "epoch": 6.98, |
| "learning_rate": 4.301675977653631e-05, |
| "loss": 0.0062, |
| "step": 2500 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.05861973389983177, |
| "eval_runtime": 16.6974, |
| "eval_samples_per_second": 555.716, |
| "step": 2506 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.05649217218160629, |
| "eval_runtime": 16.6894, |
| "eval_samples_per_second": 555.983, |
| "step": 2864 |
| }, |
| { |
| "epoch": 8.38, |
| "learning_rate": 4.1620111731843576e-05, |
| "loss": 0.0052, |
| "step": 3000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.05835355445742607, |
| "eval_runtime": 16.6938, |
| "eval_samples_per_second": 555.836, |
| "step": 3222 |
| }, |
| { |
| "epoch": 9.78, |
| "learning_rate": 4.022346368715084e-05, |
| "loss": 0.0049, |
| "step": 3500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.05387857183814049, |
| "eval_runtime": 16.6873, |
| "eval_samples_per_second": 556.051, |
| "step": 3580 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.05784677714109421, |
| "eval_runtime": 16.7026, |
| "eval_samples_per_second": 555.543, |
| "step": 3938 |
| }, |
| { |
| "epoch": 11.17, |
| "learning_rate": 3.8826815642458106e-05, |
| "loss": 0.0046, |
| "step": 4000 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.05557448789477348, |
| "eval_runtime": 16.6808, |
| "eval_samples_per_second": 556.269, |
| "step": 4296 |
| } |
| ], |
| "max_steps": 17900, |
| "num_train_epochs": 50, |
| "total_flos": 2.308026552763853e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
