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
1838e98
•
1 Parent(s): 38b423c

Training in progress epoch 145

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.8863
18
- - Train Accuracy: 0.1174
19
- - Validation Loss: 0.8921
20
- - Validation Accuracy: 0.1184
21
- - Epoch: 144
22
 
23
  ## Model description
24
 
@@ -189,6 +189,7 @@ The following hyperparameters were used during training:
189
  | 0.8894 | 0.1173 | 0.9033 | 0.1173 | 142 |
190
  | 0.8869 | 0.1174 | 0.8853 | 0.1184 | 143 |
191
  | 0.8863 | 0.1174 | 0.8921 | 0.1184 | 144 |
 
192
 
193
 
194
  ### 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: 0.8848
18
+ - Train Accuracy: 0.1175
19
+ - Validation Loss: 0.8848
20
+ - Validation Accuracy: 0.1177
21
+ - Epoch: 145
22
 
23
  ## Model description
24
 
 
189
  | 0.8894 | 0.1173 | 0.9033 | 0.1173 | 142 |
190
  | 0.8869 | 0.1174 | 0.8853 | 0.1184 | 143 |
191
  | 0.8863 | 0.1174 | 0.8921 | 0.1184 | 144 |
192
+ | 0.8848 | 0.1175 | 0.8848 | 0.1177 | 145 |
193
 
194
 
195
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95ca0d4fffb1a7d0821dfdb6cf4b219612e01c5f3c3aa1a05ffdd372a6bed270
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c65cca2a4e2bf78dfe9f241725ac31e8daf3964f590fde2c831f66d95a26303
3
  size 499741936