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
74a9bed
•
1 Parent(s): d4ada39

Training in progress epoch 161

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  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: 0.8656
18
  - Train Accuracy: 0.1180
19
- - Validation Loss: 0.8594
20
  - Validation Accuracy: 0.1188
21
- - Epoch: 160
22
 
23
  ## Model description
24
 
@@ -205,6 +205,7 @@ The following hyperparameters were used during training:
205
  | 0.8675 | 0.1179 | 0.8804 | 0.1197 | 158 |
206
  | 0.8670 | 0.1179 | 0.8462 | 0.1192 | 159 |
207
  | 0.8656 | 0.1180 | 0.8594 | 0.1188 | 160 |
 
208
 
209
 
210
  ### 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: 0.8649
18
  - Train Accuracy: 0.1180
19
+ - Validation Loss: 0.8535
20
  - Validation Accuracy: 0.1188
21
+ - Epoch: 161
22
 
23
  ## Model description
24
 
 
205
  | 0.8675 | 0.1179 | 0.8804 | 0.1197 | 158 |
206
  | 0.8670 | 0.1179 | 0.8462 | 0.1192 | 159 |
207
  | 0.8656 | 0.1180 | 0.8594 | 0.1188 | 160 |
208
+ | 0.8649 | 0.1180 | 0.8535 | 0.1188 | 161 |
209
 
210
 
211
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06d4c86aa91d5231e9a7bbae0f5c59f2b40cac5091f6206ba0044e7d540f8fe5
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d70a01cfce13091ccd7b52de5a7b09c4e62d517d4f58306a39d38d9a761e7c46
3
  size 499741936