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
2a11383
•
1 Parent(s): bd16236

Training in progress epoch 178

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: 0.8478
18
  - Train Accuracy: 0.1184
19
- - Validation Loss: 0.8594
20
- - Validation Accuracy: 0.1191
21
- - Epoch: 177
22
 
23
  ## Model description
24
 
@@ -222,6 +222,7 @@ The following hyperparameters were used during training:
222
  | 0.8496 | 0.1183 | 0.8452 | 0.1188 | 175 |
223
  | 0.8487 | 0.1184 | 0.8545 | 0.1183 | 176 |
224
  | 0.8478 | 0.1184 | 0.8594 | 0.1191 | 177 |
 
225
 
226
 
227
  ### 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: 0.8466
18
  - Train Accuracy: 0.1184
19
+ - Validation Loss: 0.8608
20
+ - Validation Accuracy: 0.1187
21
+ - Epoch: 178
22
 
23
  ## Model description
24
 
 
222
  | 0.8496 | 0.1183 | 0.8452 | 0.1188 | 175 |
223
  | 0.8487 | 0.1184 | 0.8545 | 0.1183 | 176 |
224
  | 0.8478 | 0.1184 | 0.8594 | 0.1191 | 177 |
225
+ | 0.8466 | 0.1184 | 0.8608 | 0.1187 | 178 |
226
 
227
 
228
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6bef3feb3b32d8f7064e7c88c032f2725e64ba55d490057b17efece58ed4a9d
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d99473e9ce8ac444f96afc54ae7b468c63c9030371cb491fa31a44a14a18c9
3
  size 499741936