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
4f3d37a
•
1 Parent(s): e9b5bdb

Training in progress epoch 292

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: 0.7703
18
  - Train Accuracy: 0.1204
19
- - Validation Loss: 0.8057
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 291
22
 
23
  ## Model description
24
 
@@ -336,6 +336,7 @@ The following hyperparameters were used during training:
336
  | 0.7719 | 0.1203 | 0.8359 | 0.1205 | 289 |
337
  | 0.7713 | 0.1203 | 0.8145 | 0.1204 | 290 |
338
  | 0.7703 | 0.1204 | 0.8057 | 0.1202 | 291 |
 
339
 
340
 
341
  ### 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: 0.7698
18
  - Train Accuracy: 0.1204
19
+ - Validation Loss: 0.8174
20
+ - Validation Accuracy: 0.1204
21
+ - Epoch: 292
22
 
23
  ## Model description
24
 
 
336
  | 0.7719 | 0.1203 | 0.8359 | 0.1205 | 289 |
337
  | 0.7713 | 0.1203 | 0.8145 | 0.1204 | 290 |
338
  | 0.7703 | 0.1204 | 0.8057 | 0.1202 | 291 |
339
+ | 0.7698 | 0.1204 | 0.8174 | 0.1204 | 292 |
340
 
341
 
342
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf0e6cc5982393ab5a2cac7bd97c435b72c7b778bd8707cdcb512a9baafa2f65
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc37ceeac9a3c243f54a691cb9133717d9137cfb855b1deca12d2bcfe456e2c2
3
  size 499741936