This model is a fine-tuned version of google/electra-base-discriminator on the MNLI dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3762 | 1.0 | 12272 | 0.3312 | 0.8794 |
| 0.2542 | 2.0 | 24544 | 0.3467 | 0.8843 |
| 0.1503 | 3.0 | 36816 | 0.4265 | 0.8879 |
pytorch_model.bin 438 MBtraining_dynamics/epoch0_train_logits_[392702, 3].pt 5 MBtraining_dynamics/epoch1_train_logits_[392702, 3].pt 5 MBtraining_dynamics/epoch2_train_logits_[392702, 3].pt 5 MBtraining_dynamics_after_epoch/epoch0_after_epoch_train_logits_[392702, 3].pt 5 MBtraining_dynamics_after_epoch/epoch1_after_epoch_train_logits_[392702, 3].pt 5 MBtraining_dynamics_after_epoch/epoch2_after_epoch_train_logits_[392702, 3].pt 5 MBtraining_dynamics/epoch0_train_idxs_[392702].pt 3 MBtraining_dynamics/epoch1_train_idxs_[392702].pt 3 MBtraining_dynamics/epoch2_train_idxs_[392702].pt 3 MBtraining_dynamics_after_epoch/epoch0_after_epoch_train_idxs_[392702].pt 3 MBtraining_dynamics_after_epoch/epoch1_after_epoch_train_idxs_[392702].pt 3 MBtraining_dynamics_after_epoch/epoch2_after_epoch_train_idxs_[392702].pt 3 MBtraining_args.bin 3.1 kB