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
0288302
•
1 Parent(s): a295c51

Training in progress epoch 170

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: 0.8558
18
  - Train Accuracy: 0.1182
19
- - Validation Loss: 0.8481
20
- - Validation Accuracy: 0.1176
21
- - Epoch: 169
22
 
23
  ## Model description
24
 
@@ -214,6 +214,7 @@ The following hyperparameters were used during training:
214
  | 0.8580 | 0.1181 | 0.8853 | 0.1177 | 167 |
215
  | 0.8573 | 0.1181 | 0.8691 | 0.1181 | 168 |
216
  | 0.8558 | 0.1182 | 0.8481 | 0.1176 | 169 |
 
217
 
218
 
219
  ### 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: 0.8541
18
  - Train Accuracy: 0.1182
19
+ - Validation Loss: 0.8652
20
+ - Validation Accuracy: 0.1187
21
+ - Epoch: 170
22
 
23
  ## Model description
24
 
 
214
  | 0.8580 | 0.1181 | 0.8853 | 0.1177 | 167 |
215
  | 0.8573 | 0.1181 | 0.8691 | 0.1181 | 168 |
216
  | 0.8558 | 0.1182 | 0.8481 | 0.1176 | 169 |
217
+ | 0.8541 | 0.1182 | 0.8652 | 0.1187 | 170 |
218
 
219
 
220
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b691c15a6d195aac8f24c885921de3c85c2476a05dfb05b1176c1edd3d6587a
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0a4bb3a33c333888f4b465cb0359ba48af4f7c8fb5669fb8ac50a8fd730e03
3
  size 499741936