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
841eec0
•
1 Parent(s): 3a44e2d

Training in progress epoch 368

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: 0.7398
18
  - Train Accuracy: 0.1212
19
- - Validation Loss: 0.8037
20
- - Validation Accuracy: 0.1196
21
- - Epoch: 367
22
 
23
  ## Model description
24
 
@@ -412,6 +412,7 @@ The following hyperparameters were used during training:
412
  | 0.7412 | 0.1212 | 0.7896 | 0.1207 | 365 |
413
  | 0.7404 | 0.1212 | 0.8071 | 0.1208 | 366 |
414
  | 0.7398 | 0.1212 | 0.8037 | 0.1196 | 367 |
 
415
 
416
 
417
  ### 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: 0.7389
18
  - Train Accuracy: 0.1212
19
+ - Validation Loss: 0.7949
20
+ - Validation Accuracy: 0.1194
21
+ - Epoch: 368
22
 
23
  ## Model description
24
 
 
412
  | 0.7412 | 0.1212 | 0.7896 | 0.1207 | 365 |
413
  | 0.7404 | 0.1212 | 0.8071 | 0.1208 | 366 |
414
  | 0.7398 | 0.1212 | 0.8037 | 0.1196 | 367 |
415
+ | 0.7389 | 0.1212 | 0.7949 | 0.1194 | 368 |
416
 
417
 
418
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ff8a9723f088907453e464ac8074ed5051fc84ea3eb95864f9e3f4ca1f99789
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4039565cddf241b4b2696e8aba2272184a6043f962eba00d2b283b8c9731eb69
3
  size 499741936