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
6899740
•
1 Parent(s): af2e5fe

Training in progress epoch 150

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: 0.8794
18
- - Train Accuracy: 0.1175
19
- - Validation Loss: 0.8774
20
- - Validation Accuracy: 0.1181
21
- - Epoch: 149
22
 
23
  ## Model description
24
 
@@ -194,6 +194,7 @@ The following hyperparameters were used during training:
194
  | 0.8822 | 0.1175 | 0.8945 | 0.1181 | 147 |
195
  | 0.8804 | 0.1176 | 0.8843 | 0.1177 | 148 |
196
  | 0.8794 | 0.1175 | 0.8774 | 0.1181 | 149 |
 
197
 
198
 
199
  ### 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: 0.8780
18
+ - Train Accuracy: 0.1176
19
+ - Validation Loss: 0.875
20
+ - Validation Accuracy: 0.1178
21
+ - Epoch: 150
22
 
23
  ## Model description
24
 
 
194
  | 0.8822 | 0.1175 | 0.8945 | 0.1181 | 147 |
195
  | 0.8804 | 0.1176 | 0.8843 | 0.1177 | 148 |
196
  | 0.8794 | 0.1175 | 0.8774 | 0.1181 | 149 |
197
+ | 0.8780 | 0.1176 | 0.875 | 0.1178 | 150 |
198
 
199
 
200
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f0ddf3b728f0de2e8638832b369a9ee7d658b32e0187192281ebf75a16b559e
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422a7ab6f603ff61183e556b572e784afc12416f7e1aaac6cd7b089e0e834edd
3
  size 499741936