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
8c494d1
•
1 Parent(s): fa7dd86

Training in progress epoch 200

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: 0.8275
18
  - Train Accuracy: 0.1189
19
- - Validation Loss: 0.8472
20
- - Validation Accuracy: 0.1193
21
- - Epoch: 199
22
 
23
  ## Model description
24
 
@@ -244,6 +244,7 @@ The following hyperparameters were used during training:
244
  | 0.8294 | 0.1189 | 0.8345 | 0.1197 | 197 |
245
  | 0.8285 | 0.1189 | 0.8491 | 0.1181 | 198 |
246
  | 0.8275 | 0.1189 | 0.8472 | 0.1193 | 199 |
 
247
 
248
 
249
  ### 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: 0.8265
18
  - Train Accuracy: 0.1189
19
+ - Validation Loss: 0.8521
20
+ - Validation Accuracy: 0.1185
21
+ - Epoch: 200
22
 
23
  ## Model description
24
 
 
244
  | 0.8294 | 0.1189 | 0.8345 | 0.1197 | 197 |
245
  | 0.8285 | 0.1189 | 0.8491 | 0.1181 | 198 |
246
  | 0.8275 | 0.1189 | 0.8472 | 0.1193 | 199 |
247
+ | 0.8265 | 0.1189 | 0.8521 | 0.1185 | 200 |
248
 
249
 
250
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8f4daf0ad7969e92791a49dfabb7cc9a425b7f3db8fb92de62aefff1ef34db7
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74bd6f066a032e1d22c4c7a76106bb2716bdef6c1f1045373f9fa1eb3f3aad5
3
  size 499741936