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
6f372d8
•
1 Parent(s): 60f74a2

Training in progress epoch 198

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: 0.8294
18
  - Train Accuracy: 0.1189
19
- - Validation Loss: 0.8345
20
- - Validation Accuracy: 0.1197
21
- - Epoch: 197
22
 
23
  ## Model description
24
 
@@ -242,6 +242,7 @@ The following hyperparameters were used during training:
242
  | 0.8314 | 0.1188 | 0.8472 | 0.1202 | 195 |
243
  | 0.8307 | 0.1188 | 0.8584 | 0.1186 | 196 |
244
  | 0.8294 | 0.1189 | 0.8345 | 0.1197 | 197 |
 
245
 
246
 
247
  ### 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: 0.8285
18
  - Train Accuracy: 0.1189
19
+ - Validation Loss: 0.8491
20
+ - Validation Accuracy: 0.1181
21
+ - Epoch: 198
22
 
23
  ## Model description
24
 
 
242
  | 0.8314 | 0.1188 | 0.8472 | 0.1202 | 195 |
243
  | 0.8307 | 0.1188 | 0.8584 | 0.1186 | 196 |
244
  | 0.8294 | 0.1189 | 0.8345 | 0.1197 | 197 |
245
+ | 0.8285 | 0.1189 | 0.8491 | 0.1181 | 198 |
246
 
247
 
248
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e08541c1fa1f68bbf9b7341f79a99146012e55c67a062c1f9bc245cb2cc5be13
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31ea7f7b36d0842a0b50dba2c1bdac762eb35d9281833f2db3739274881779a
3
  size 499741936