CoolFace
Modelpublic

kcarnold/inquisitive-full

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes23downloads
trainer_state.json110 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 15.0,5  "global_step": 7470,6  "is_hyper_param_search": false,7  "is_local_process_zero": true,8  "is_world_process_zero": true,9  "log_history": [10    {11      "epoch": 1.0,12      "learning_rate": 4.6653279785809906e-05,13      "loss": 2.185,14      "step": 50015    },16    {17      "epoch": 2.01,18      "learning_rate": 4.3306559571619816e-05,19      "loss": 1.8076,20      "step": 100021    },22    {23      "epoch": 3.01,24      "learning_rate": 3.995983935742972e-05,25      "loss": 1.5817,26      "step": 150027    },28    {29      "epoch": 4.02,30      "learning_rate": 3.661311914323963e-05,31      "loss": 1.3979,32      "step": 200033    },34    {35      "epoch": 5.02,36      "learning_rate": 3.326639892904953e-05,37      "loss": 1.2541,38      "step": 250039    },40    {41      "epoch": 6.02,42      "learning_rate": 2.991967871485944e-05,43      "loss": 1.127,44      "step": 300045    },46    {47      "epoch": 7.03,48      "learning_rate": 2.6572958500669343e-05,49      "loss": 1.0202,50      "step": 350051    },52    {53      "epoch": 8.03,54      "learning_rate": 2.322623828647925e-05,55      "loss": 0.9236,56      "step": 400057    },58    {59      "epoch": 9.04,60      "learning_rate": 1.9879518072289157e-05,61      "loss": 0.8492,62      "step": 450063    },64    {65      "epoch": 10.04,66      "learning_rate": 1.6532797858099064e-05,67      "loss": 0.7856,68      "step": 500069    },70    {71      "epoch": 11.04,72      "learning_rate": 1.318607764390897e-05,73      "loss": 0.7317,74      "step": 550075    },76    {77      "epoch": 12.05,78      "learning_rate": 9.839357429718876e-06,79      "loss": 0.6839,80      "step": 600081    },82    {83      "epoch": 13.05,84      "learning_rate": 6.492637215528783e-06,85      "loss": 0.6487,86      "step": 650087    },88    {89      "epoch": 14.06,90      "learning_rate": 3.1459170013386886e-06,91      "loss": 0.6207,92      "step": 700093    },94    {95      "epoch": 15.0,96      "step": 7470,97      "total_flos": 2.979518169858048e+16,98      "train_loss": 1.0831103017212078,99      "train_runtime": 1681.1253,100      "train_samples_per_second": 142.146,101      "train_steps_per_second": 4.443102    }103  ],104  "max_steps": 7470,105  "num_train_epochs": 15,106  "total_flos": 2.979518169858048e+16,107  "trial_name": null,108  "trial_params": null109}110