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
494cc84
•
1 Parent(s): 8e1dfe1

Training in progress epoch 213

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: 0.8177
18
  - Train Accuracy: 0.1192
19
- - Validation Loss: 0.8408
20
- - Validation Accuracy: 0.1185
21
- - Epoch: 212
22
 
23
  ## Model description
24
 
@@ -257,6 +257,7 @@ The following hyperparameters were used during training:
257
  | 0.8195 | 0.1191 | 0.8672 | 0.1181 | 210 |
258
  | 0.8188 | 0.1191 | 0.8267 | 0.1197 | 211 |
259
  | 0.8177 | 0.1192 | 0.8408 | 0.1185 | 212 |
 
260
 
261
 
262
  ### 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: 0.8167
18
  - Train Accuracy: 0.1192
19
+ - Validation Loss: 0.8447
20
+ - Validation Accuracy: 0.1191
21
+ - Epoch: 213
22
 
23
  ## Model description
24
 
 
257
  | 0.8195 | 0.1191 | 0.8672 | 0.1181 | 210 |
258
  | 0.8188 | 0.1191 | 0.8267 | 0.1197 | 211 |
259
  | 0.8177 | 0.1192 | 0.8408 | 0.1185 | 212 |
260
+ | 0.8167 | 0.1192 | 0.8447 | 0.1191 | 213 |
261
 
262
 
263
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55d3c09dd5cec683b7b8276d3a5efcec1c5649d3ebee2fa87597d9377d277298
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089b6808c9f6e2791baa0670b09e628b698769a1d9f662ce963492921bbc3d52
3
  size 499741936