Hugging Face's logo

tf-tpu
/
roberta-base-epochs-500-no-wd

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
2
sayakpaul HF staff commited on
Commit
f7ca9b6
•
1 Parent(s): 13b4204

Training in progress epoch 309

Browse files
Files changed (2) hide show
  1. README.md +5 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.7628
18
  - Train Accuracy: 0.1206
19
- - Validation Loss: 0.8120
20
- - Validation Accuracy: 0.1196
21
- - Epoch: 308
22
 
23
  ## Model description
24
 
@@ -353,6 +353,7 @@ The following hyperparameters were used during training:
353
  | 0.7633 | 0.1206 | 0.8223 | 0.1194 | 306 |
354
  | 0.7632 | 0.1206 | 0.8037 | 0.1201 | 307 |
355
  | 0.7628 | 0.1206 | 0.8120 | 0.1196 | 308 |
 
356
 
357
 
358
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.7633
18
  - Train Accuracy: 0.1206
19
+ - Validation Loss: 0.8101
20
+ - Validation Accuracy: 0.1198
21
+ - Epoch: 309
22
 
23
  ## Model description
24
 
 
353
  | 0.7633 | 0.1206 | 0.8223 | 0.1194 | 306 |
354
  | 0.7632 | 0.1206 | 0.8037 | 0.1201 | 307 |
355
  | 0.7628 | 0.1206 | 0.8120 | 0.1196 | 308 |
356
+ | 0.7633 | 0.1206 | 0.8101 | 0.1198 | 309 |
357
 
358
 
359
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c210b5bdd143a91a86a6241e0cbcbc3747f735469c5b42dc1c17655ffdf55fb
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f3221f26df93f5b85a1bf9aafa863304393a47198e0a60832ef2ade57e75bc
3
  size 499741936