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
db864f0
·
1 Parent(s): 960f68b

Training in progress epoch 280

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: 0.7762
18
  - Train Accuracy: 0.1202
19
- - Validation Loss: 0.8154
20
- - Validation Accuracy: 0.1194
21
- - Epoch: 279
22
 
23
  ## Model description
24
 
@@ -324,6 +324,7 @@ The following hyperparameters were used during training:
324
  | 0.7777 | 0.1202 | 0.8301 | 0.1194 | 277 |
325
  | 0.7771 | 0.1202 | 0.8164 | 0.1207 | 278 |
326
  | 0.7762 | 0.1202 | 0.8154 | 0.1194 | 279 |
 
327
 
328
 
329
  ### 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: 0.7757
18
  - Train Accuracy: 0.1202
19
+ - Validation Loss: 0.8242
20
+ - Validation Accuracy: 0.1196
21
+ - Epoch: 280
22
 
23
  ## Model description
24
 
 
324
  | 0.7777 | 0.1202 | 0.8301 | 0.1194 | 277 |
325
  | 0.7771 | 0.1202 | 0.8164 | 0.1207 | 278 |
326
  | 0.7762 | 0.1202 | 0.8154 | 0.1194 | 279 |
327
+ | 0.7757 | 0.1202 | 0.8242 | 0.1196 | 280 |
328
 
329
 
330
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eb08d32ef7ad7ebce8d21390f5f8d1e0959035e37366d42365acade912799da
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfabcc228353e19df855870a2c0f80b332647fd14ba7912e2670f3ede80a9f84
3
  size 499741936