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
8423f8a
•
1 Parent(s): a097edd

Training in progress epoch 117

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: 0.9317
18
- - Train Accuracy: 0.1163
19
- - Validation Loss: 0.9277
20
  - Validation Accuracy: 0.1169
21
- - Epoch: 116
22
 
23
  ## Model description
24
 
@@ -161,6 +161,7 @@ The following hyperparameters were used during training:
161
  | 0.9362 | 0.1161 | 0.9048 | 0.1176 | 114 |
162
  | 0.9345 | 0.1162 | 0.9082 | 0.1169 | 115 |
163
  | 0.9317 | 0.1163 | 0.9277 | 0.1169 | 116 |
 
164
 
165
 
166
  ### 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: 0.9295
18
+ - Train Accuracy: 0.1164
19
+ - Validation Loss: 0.9292
20
  - Validation Accuracy: 0.1169
21
+ - Epoch: 117
22
 
23
  ## Model description
24
 
 
161
  | 0.9362 | 0.1161 | 0.9048 | 0.1176 | 114 |
162
  | 0.9345 | 0.1162 | 0.9082 | 0.1169 | 115 |
163
  | 0.9317 | 0.1163 | 0.9277 | 0.1169 | 116 |
164
+ | 0.9295 | 0.1164 | 0.9292 | 0.1169 | 117 |
165
 
166
 
167
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8f42fa1b4539d4d57681b7c4e1a1a505c6c1aacfa49ac5866887b816ed678a
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd2e3c536ecb025084a9fac84da16e985c20c9c9750681822f3dac90d642ddd
3
  size 499741936