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
6087163
·
1 Parent(s): 79c4c65

Training in progress epoch 270

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: 0.7818
18
  - Train Accuracy: 0.1201
19
- - Validation Loss: 0.8350
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 269
22
 
23
  ## Model description
24
 
@@ -314,6 +314,7 @@ The following hyperparameters were used during training:
314
  | 0.7833 | 0.1200 | 0.8291 | 0.1194 | 267 |
315
  | 0.7821 | 0.1201 | 0.8335 | 0.1195 | 268 |
316
  | 0.7818 | 0.1201 | 0.8350 | 0.1199 | 269 |
 
317
 
318
 
319
  ### 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: 0.7812
18
  - Train Accuracy: 0.1201
19
+ - Validation Loss: 0.8223
20
+ - Validation Accuracy: 0.1184
21
+ - Epoch: 270
22
 
23
  ## Model description
24
 
 
314
  | 0.7833 | 0.1200 | 0.8291 | 0.1194 | 267 |
315
  | 0.7821 | 0.1201 | 0.8335 | 0.1195 | 268 |
316
  | 0.7818 | 0.1201 | 0.8350 | 0.1199 | 269 |
317
+ | 0.7812 | 0.1201 | 0.8223 | 0.1184 | 270 |
318
 
319
 
320
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4402def3f25c052a1dd745e1f9a9f3e0c19c948a6f6be25f725ceb2d622053f9
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c1dd72cd22e03cfefe4de26e51ecc32759ee9b586a4cedac73c07993e74696
3
  size 499741936