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
2b24129
•
1 Parent(s): 5dd0b51

Training in progress epoch 307

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: 0.7633
18
  - Train Accuracy: 0.1206
19
- - Validation Loss: 0.8223
20
- - Validation Accuracy: 0.1194
21
- - Epoch: 306
22
 
23
  ## Model description
24
 
@@ -351,6 +351,7 @@ The following hyperparameters were used during training:
351
  | 0.7651 | 0.1205 | 0.7954 | 0.1213 | 304 |
352
  | 0.7640 | 0.1206 | 0.7861 | 0.1206 | 305 |
353
  | 0.7633 | 0.1206 | 0.8223 | 0.1194 | 306 |
 
354
 
355
 
356
  ### 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: 0.7632
18
  - Train Accuracy: 0.1206
19
+ - Validation Loss: 0.8037
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 307
22
 
23
  ## Model description
24
 
 
351
  | 0.7651 | 0.1205 | 0.7954 | 0.1213 | 304 |
352
  | 0.7640 | 0.1206 | 0.7861 | 0.1206 | 305 |
353
  | 0.7633 | 0.1206 | 0.8223 | 0.1194 | 306 |
354
+ | 0.7632 | 0.1206 | 0.8037 | 0.1201 | 307 |
355
 
356
 
357
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae8b4c506899b2d88523b9ad8aa98e449ae58fe5ca1375bac4f242484f520170
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968dc2c6e733889d9a46810b1367443b8c741f421b5e74e29ec0529924b7e027
3
  size 499741936