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
a149e87
·
1 Parent(s): eda5439

Training in progress epoch 102

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: 0.9660
18
- - Train Accuracy: 0.1154
19
  - Validation Loss: 0.9507
20
- - Validation Accuracy: 0.1169
21
- - Epoch: 101
22
 
23
  ## Model description
24
 
@@ -146,6 +146,7 @@ The following hyperparameters were used during training:
146
  | 0.9712 | 0.1153 | 0.9375 | 0.1159 | 99 |
147
  | 0.9678 | 0.1154 | 0.9453 | 0.1166 | 100 |
148
  | 0.9660 | 0.1154 | 0.9507 | 0.1169 | 101 |
 
149
 
150
 
151
  ### 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: 0.9636
18
+ - Train Accuracy: 0.1155
19
  - Validation Loss: 0.9507
20
+ - Validation Accuracy: 0.1161
21
+ - Epoch: 102
22
 
23
  ## Model description
24
 
 
146
  | 0.9712 | 0.1153 | 0.9375 | 0.1159 | 99 |
147
  | 0.9678 | 0.1154 | 0.9453 | 0.1166 | 100 |
148
  | 0.9660 | 0.1154 | 0.9507 | 0.1169 | 101 |
149
+ | 0.9636 | 0.1155 | 0.9507 | 0.1161 | 102 |
150
 
151
 
152
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6fd4eeaa1044a8029556e6feeb7d3029d4c004850e3413290d8d88f592b2d8d
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4ca600336b352a09fe3b86e714fe23c4b25411f195b2775a5c6e59c5033a57
3
  size 499741936