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
1c74141
•
1 Parent(s): eb87f20

Training in progress epoch 283

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: 0.7751
18
  - Train Accuracy: 0.1203
19
- - Validation Loss: 0.8193
20
- - Validation Accuracy: 0.1197
21
- - Epoch: 282
22
 
23
  ## Model description
24
 
@@ -327,6 +327,7 @@ The following hyperparameters were used during training:
327
  | 0.7757 | 0.1202 | 0.8242 | 0.1196 | 280 |
328
  | 0.7751 | 0.1203 | 0.8140 | 0.1215 | 281 |
329
  | 0.7751 | 0.1203 | 0.8193 | 0.1197 | 282 |
 
330
 
331
 
332
  ### 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: 0.7746
18
  - Train Accuracy: 0.1203
19
+ - Validation Loss: 0.8008
20
+ - Validation Accuracy: 0.1186
21
+ - Epoch: 283
22
 
23
  ## Model description
24
 
 
327
  | 0.7757 | 0.1202 | 0.8242 | 0.1196 | 280 |
328
  | 0.7751 | 0.1203 | 0.8140 | 0.1215 | 281 |
329
  | 0.7751 | 0.1203 | 0.8193 | 0.1197 | 282 |
330
+ | 0.7746 | 0.1203 | 0.8008 | 0.1186 | 283 |
331
 
332
 
333
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ec1fea4a3bf91a64464948ba43b51a4a557af51c317d762732dfbb0eaba66f
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9669d3a4ad9fbc5a1a01be45d68f228fdc862e70f583ebbd8ada8be70ba2d8
3
  size 499741936