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
a0d4609
·
1 Parent(s): 35f86e5

Training in progress epoch 205

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: 0.8237
18
  - Train Accuracy: 0.1190
19
- - Validation Loss: 0.8491
20
- - Validation Accuracy: 0.1184
21
- - Epoch: 204
22
 
23
  ## Model description
24
 
@@ -249,6 +249,7 @@ The following hyperparameters were used during training:
249
  | 0.8247 | 0.1190 | 0.8491 | 0.1194 | 202 |
250
  | 0.8245 | 0.1190 | 0.8389 | 0.1191 | 203 |
251
  | 0.8237 | 0.1190 | 0.8491 | 0.1184 | 204 |
 
252
 
253
 
254
  ### 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: 0.8229
18
  - Train Accuracy: 0.1190
19
+ - Validation Loss: 0.8525
20
+ - Validation Accuracy: 0.1193
21
+ - Epoch: 205
22
 
23
  ## Model description
24
 
 
249
  | 0.8247 | 0.1190 | 0.8491 | 0.1194 | 202 |
250
  | 0.8245 | 0.1190 | 0.8389 | 0.1191 | 203 |
251
  | 0.8237 | 0.1190 | 0.8491 | 0.1184 | 204 |
252
+ | 0.8229 | 0.1190 | 0.8525 | 0.1193 | 205 |
253
 
254
 
255
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1838c1c08e7f20b9af6cf1f8f5295465bac9ff1e7074bfba7bed5ef965cf6b16
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4686f6437eae90491ea904fc8d63341ce72a57620f8c94de4af7eadcf9023c45
3
  size 499741936