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
6eecd14
·
1 Parent(s): 2d41754

Training in progress epoch 208

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.8213
18
- - Train Accuracy: 0.1190
19
- - Validation Loss: 0.8511
20
- - Validation Accuracy: 0.1206
21
- - Epoch: 207
22
 
23
  ## Model description
24
 
@@ -252,6 +252,7 @@ The following hyperparameters were used during training:
252
  | 0.8229 | 0.1190 | 0.8525 | 0.1193 | 205 |
253
  | 0.8215 | 0.1190 | 0.8345 | 0.1199 | 206 |
254
  | 0.8213 | 0.1190 | 0.8511 | 0.1206 | 207 |
 
255
 
256
 
257
  ### 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: 0.8204
18
+ - Train Accuracy: 0.1191
19
+ - Validation Loss: 0.8296
20
+ - Validation Accuracy: 0.1195
21
+ - Epoch: 208
22
 
23
  ## Model description
24
 
 
252
  | 0.8229 | 0.1190 | 0.8525 | 0.1193 | 205 |
253
  | 0.8215 | 0.1190 | 0.8345 | 0.1199 | 206 |
254
  | 0.8213 | 0.1190 | 0.8511 | 0.1206 | 207 |
255
+ | 0.8204 | 0.1191 | 0.8296 | 0.1195 | 208 |
256
 
257
 
258
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40d101698868e3a5e64290b00a3c158c148a4512a43a6fd8b24fbcb1d986a207
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f2a88812bff74ccb245e6d220a891459be43219d764933c3818645598a4358
3
  size 499741936