Downloads · 30 days
7
3% of all-time downloads
gokuls/hBERTv2_new_pretrain_48_KD_rte
hBERTv2_new_pretrain_48_KD_rte is a text classification model from gokuls. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
7
3% of all-time downloads
All-time downloads
217
Public
Repo size
477 MB
Likes
0
Public
Click a slice to open those files.
.bin477 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48_KD on the GLUE RTE 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 |
|---|---|---|---|---|
| 0.7143 | 1.0 | 20 | 0.6928 | 0.5271 |
| 0.6999 | 2.0 | 40 | 0.6949 | 0.4910 |
| 0.7002 | 3.0 | 60 | 0.6944 | 0.5451 |
| 0.6627 | 4.0 | 80 | 0.7555 | 0.5090 |
| 0.5779 | 5.0 | 100 | 0.9459 | 0.5018 |
| 0.4501 | 6.0 | 120 | 1.1418 | 0.4946 |