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
626ac8f
•
1 Parent(s): ee36f2c

Training in progress epoch 272

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.7809
18
- - Train Accuracy: 0.1201
19
- - Validation Loss: 0.8330
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 271
22
 
23
  ## Model description
24
 
@@ -316,6 +316,7 @@ The following hyperparameters were used during training:
316
  | 0.7818 | 0.1201 | 0.8350 | 0.1199 | 269 |
317
  | 0.7812 | 0.1201 | 0.8223 | 0.1184 | 270 |
318
  | 0.7809 | 0.1201 | 0.8330 | 0.1202 | 271 |
 
319
 
320
 
321
  ### 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: 0.7794
18
+ - Train Accuracy: 0.1202
19
+ - Validation Loss: 0.8193
20
+ - Validation Accuracy: 0.1196
21
+ - Epoch: 272
22
 
23
  ## Model description
24
 
 
316
  | 0.7818 | 0.1201 | 0.8350 | 0.1199 | 269 |
317
  | 0.7812 | 0.1201 | 0.8223 | 0.1184 | 270 |
318
  | 0.7809 | 0.1201 | 0.8330 | 0.1202 | 271 |
319
+ | 0.7794 | 0.1202 | 0.8193 | 0.1196 | 272 |
320
 
321
 
322
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:432b8586e0d6570972689c7b16ab82e2db913801dbd1ff4c38d593d37d84cf38
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2c33e4d812f5dcad78e9f32ee648005bdce3fd1edd751c5b2ae73725677e08
3
  size 499741936