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
b037906
•
1 Parent(s): 993370a

Training in progress epoch 287

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: 0.7733
18
  - Train Accuracy: 0.1204
19
- - Validation Loss: 0.8125
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 286
22
 
23
  ## Model description
24
 
@@ -331,6 +331,7 @@ The following hyperparameters were used during training:
331
  | 0.7746 | 0.1203 | 0.8105 | 0.1193 | 284 |
332
  | 0.7733 | 0.1203 | 0.8223 | 0.1206 | 285 |
333
  | 0.7733 | 0.1204 | 0.8125 | 0.1199 | 286 |
 
334
 
335
 
336
  ### 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: 0.7720
18
  - Train Accuracy: 0.1204
19
+ - Validation Loss: 0.8228
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 287
22
 
23
  ## Model description
24
 
 
331
  | 0.7746 | 0.1203 | 0.8105 | 0.1193 | 284 |
332
  | 0.7733 | 0.1203 | 0.8223 | 0.1206 | 285 |
333
  | 0.7733 | 0.1204 | 0.8125 | 0.1199 | 286 |
334
+ | 0.7720 | 0.1204 | 0.8228 | 0.1201 | 287 |
335
 
336
 
337
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:404d25b80984c4f0af024d833320e94fd2712245826d5849c535c1d502210b75
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab38a94282e6d787fcbfd99840622641e31dceee085cbb98827502f68211a78
3
  size 499741936