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
0580de8
•
1 Parent(s): 4b3fdb5

Training in progress epoch 344

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: 0.7485
18
  - Train Accuracy: 0.1210
19
- - Validation Loss: 0.8091
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 343
22
 
23
  ## Model description
24
 
@@ -388,6 +388,7 @@ The following hyperparameters were used during training:
388
  | 0.7493 | 0.1209 | 0.8145 | 0.1204 | 341 |
389
  | 0.7491 | 0.1210 | 0.8062 | 0.1209 | 342 |
390
  | 0.7485 | 0.1210 | 0.8091 | 0.1199 | 343 |
 
391
 
392
 
393
  ### 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: 0.7480
18
  - Train Accuracy: 0.1210
19
+ - Validation Loss: 0.8101
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 344
22
 
23
  ## Model description
24
 
 
388
  | 0.7493 | 0.1209 | 0.8145 | 0.1204 | 341 |
389
  | 0.7491 | 0.1210 | 0.8062 | 0.1209 | 342 |
390
  | 0.7485 | 0.1210 | 0.8091 | 0.1199 | 343 |
391
+ | 0.7480 | 0.1210 | 0.8101 | 0.1201 | 344 |
392
 
393
 
394
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:779b612f4e25fefc8466188e2d696444593fb5c791df60670d98c68783267936
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c31e30fd76b163b9f59181e7de8792366630b4a28784d762322d1f91bfad01
3
  size 499741936