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
7a6ed70
•
1 Parent(s): 8354ff1

Training in progress epoch 232

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: 0.8049
18
  - Train Accuracy: 0.1195
19
- - Validation Loss: 0.8369
20
- - Validation Accuracy: 0.1191
21
- - Epoch: 231
22
 
23
  ## Model description
24
 
@@ -276,6 +276,7 @@ The following hyperparameters were used during training:
276
  | 0.8045 | 0.1195 | 0.8159 | 0.1199 | 229 |
277
  | 0.8045 | 0.1195 | 0.8350 | 0.1187 | 230 |
278
  | 0.8049 | 0.1195 | 0.8369 | 0.1191 | 231 |
 
279
 
280
 
281
  ### 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: 0.8037
18
  - Train Accuracy: 0.1195
19
+ - Validation Loss: 0.8159
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 232
22
 
23
  ## Model description
24
 
 
276
  | 0.8045 | 0.1195 | 0.8159 | 0.1199 | 229 |
277
  | 0.8045 | 0.1195 | 0.8350 | 0.1187 | 230 |
278
  | 0.8049 | 0.1195 | 0.8369 | 0.1191 | 231 |
279
+ | 0.8037 | 0.1195 | 0.8159 | 0.1201 | 232 |
280
 
281
 
282
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:311a297fcfc656c5f6f266f6bc240cbf2a332cbf3c9b41022f097f4193889476
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21a09247d888d1a3c3c4d702009934394910d99dfceb6c5b4a592c4aeada117
3
  size 499741936