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
034a094
•
1 Parent(s): 8cb5957

Training in progress epoch 324

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: 0.7556
18
  - Train Accuracy: 0.1208
19
- - Validation Loss: 0.7949
20
- - Validation Accuracy: 0.1207
21
- - Epoch: 323
22
 
23
  ## Model description
24
 
@@ -368,6 +368,7 @@ The following hyperparameters were used during training:
368
  | 0.7572 | 0.1207 | 0.8232 | 0.1196 | 321 |
369
  | 0.7565 | 0.1207 | 0.8018 | 0.1192 | 322 |
370
  | 0.7556 | 0.1208 | 0.7949 | 0.1207 | 323 |
 
371
 
372
 
373
  ### 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: 0.7555
18
  - Train Accuracy: 0.1208
19
+ - Validation Loss: 0.8105
20
+ - Validation Accuracy: 0.1200
21
+ - Epoch: 324
22
 
23
  ## Model description
24
 
 
368
  | 0.7572 | 0.1207 | 0.8232 | 0.1196 | 321 |
369
  | 0.7565 | 0.1207 | 0.8018 | 0.1192 | 322 |
370
  | 0.7556 | 0.1208 | 0.7949 | 0.1207 | 323 |
371
+ | 0.7555 | 0.1208 | 0.8105 | 0.1200 | 324 |
372
 
373
 
374
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6a8517027f228deae65a8c80106e7dd6c8efdb796aee5a1d43f11a28ab58318
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312c902a7fb21fed8b65add69b55ec04f40d83522f21473b06fb5d6aef7ee434
3
  size 499741936