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
77f395a
•
1 Parent(s): 1a89347

Training in progress epoch 249

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: 0.7933
18
  - Train Accuracy: 0.1198
19
- - Validation Loss: 0.8242
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 248
22
 
23
  ## Model description
24
 
@@ -293,6 +293,7 @@ The following hyperparameters were used during training:
293
  | 0.7944 | 0.1198 | 0.8389 | 0.1184 | 246 |
294
  | 0.7927 | 0.1198 | 0.8184 | 0.1187 | 247 |
295
  | 0.7933 | 0.1198 | 0.8242 | 0.1199 | 248 |
 
296
 
297
 
298
  ### 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: 0.7935
18
  - Train Accuracy: 0.1198
19
+ - Validation Loss: 0.8369
20
+ - Validation Accuracy: 0.1192
21
+ - Epoch: 249
22
 
23
  ## Model description
24
 
 
293
  | 0.7944 | 0.1198 | 0.8389 | 0.1184 | 246 |
294
  | 0.7927 | 0.1198 | 0.8184 | 0.1187 | 247 |
295
  | 0.7933 | 0.1198 | 0.8242 | 0.1199 | 248 |
296
+ | 0.7935 | 0.1198 | 0.8369 | 0.1192 | 249 |
297
 
298
 
299
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d153b201e573a983c73794e96e158430710efd63c4c0d8e3115245faa5e29
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cdc5edff18501f807d22c44531d7ff755d99f1580791282e9f9551340492e9
3
  size 499741936