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
b8d2e7d
•
1 Parent(s): f77f0e1

Training in progress epoch 313

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: 0.7614
18
- - Train Accuracy: 0.1206
19
- - Validation Loss: 0.8203
20
  - Validation Accuracy: 0.1201
21
- - Epoch: 312
22
 
23
  ## Model description
24
 
@@ -357,6 +357,7 @@ The following hyperparameters were used during training:
357
  | 0.7612 | 0.1206 | 0.8296 | 0.1203 | 310 |
358
  | 0.7613 | 0.1206 | 0.8105 | 0.1195 | 311 |
359
  | 0.7614 | 0.1206 | 0.8203 | 0.1201 | 312 |
 
360
 
361
 
362
  ### 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: 0.7606
18
+ - Train Accuracy: 0.1207
19
+ - Validation Loss: 0.7900
20
  - Validation Accuracy: 0.1201
21
+ - Epoch: 313
22
 
23
  ## Model description
24
 
 
357
  | 0.7612 | 0.1206 | 0.8296 | 0.1203 | 310 |
358
  | 0.7613 | 0.1206 | 0.8105 | 0.1195 | 311 |
359
  | 0.7614 | 0.1206 | 0.8203 | 0.1201 | 312 |
360
+ | 0.7606 | 0.1207 | 0.7900 | 0.1201 | 313 |
361
 
362
 
363
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1670805b9719ff51d209d91c6d44c74f58fcac2f942f8a529be64c6bd5eeb146
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c9dcc265fa9f6b214e1bbdd3e15f21118574a698d5a4305e72429ef7be3620
3
  size 499741936