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
17ab57e
·
1 Parent(s): 5d4b56e

Training in progress epoch 235

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: 0.8023
18
  - Train Accuracy: 0.1196
19
- - Validation Loss: 0.8384
20
- - Validation Accuracy: 0.1187
21
- - Epoch: 234
22
 
23
  ## Model description
24
 
@@ -279,6 +279,7 @@ The following hyperparameters were used during training:
279
  | 0.8037 | 0.1195 | 0.8159 | 0.1201 | 232 |
280
  | 0.8024 | 0.1196 | 0.8213 | 0.1186 | 233 |
281
  | 0.8023 | 0.1196 | 0.8384 | 0.1187 | 234 |
 
282
 
283
 
284
  ### 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: 0.8011
18
  - Train Accuracy: 0.1196
19
+ - Validation Loss: 0.8262
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 235
22
 
23
  ## Model description
24
 
 
279
  | 0.8037 | 0.1195 | 0.8159 | 0.1201 | 232 |
280
  | 0.8024 | 0.1196 | 0.8213 | 0.1186 | 233 |
281
  | 0.8023 | 0.1196 | 0.8384 | 0.1187 | 234 |
282
+ | 0.8011 | 0.1196 | 0.8262 | 0.1201 | 235 |
283
 
284
 
285
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0411e124a2241874ec53d8306ad4d945318549bc50b172d6d52f9505160f93cb
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e8eca90d2a9323864e6be3167d3a8f6a3cae4bd8e65a2be10865c8574e203c
3
  size 499741936