| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 93, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0001298236559139785, |
| "loss": 5.2886, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00012244731182795699, |
| "loss": 4.8484, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00011507096774193549, |
| "loss": 4.592, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00010769462365591397, |
| "loss": 4.3362, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00010031827956989248, |
| "loss": 4.3381, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 9.294193548387097e-05, |
| "loss": 4.229, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 8.556559139784946e-05, |
| "loss": 4.2006, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 7.818924731182796e-05, |
| "loss": 3.8651, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 7.081290322580646e-05, |
| "loss": 4.0792, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 6.343655913978495e-05, |
| "loss": 3.8664, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 5.606021505376345e-05, |
| "loss": 3.7922, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 4.868387096774194e-05, |
| "loss": 3.727, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 4.130752688172043e-05, |
| "loss": 3.565, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3.3931182795698924e-05, |
| "loss": 3.7849, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 2.655483870967742e-05, |
| "loss": 3.7644, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 1.9178494623655912e-05, |
| "loss": 3.6057, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 1.1802150537634409e-05, |
| "loss": 3.648, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 4.4258064516129036e-06, |
| "loss": 3.6404, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 93, |
| "total_flos": 48600317952000.0, |
| "train_loss": 4.058929084449686, |
| "train_runtime": 28.0555, |
| "train_samples_per_second": 3.315, |
| "train_steps_per_second": 3.315 |
| } |
| ], |
| "max_steps": 93, |
| "num_train_epochs": 1, |
| "total_flos": 48600317952000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
