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
4dc4b7a
•
1 Parent(s): 75e2c75

Training in progress epoch 356

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: 0.7437
18
  - Train Accuracy: 0.1211
19
- - Validation Loss: 0.8018
20
- - Validation Accuracy: 0.1207
21
- - Epoch: 355
22
 
23
  ## Model description
24
 
@@ -400,6 +400,7 @@ The following hyperparameters were used during training:
400
  | 0.7449 | 0.1211 | 0.7969 | 0.1201 | 353 |
401
  | 0.7441 | 0.1211 | 0.7905 | 0.1210 | 354 |
402
  | 0.7437 | 0.1211 | 0.8018 | 0.1207 | 355 |
 
403
 
404
 
405
  ### 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: 0.7439
18
  - Train Accuracy: 0.1211
19
+ - Validation Loss: 0.8013
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 356
22
 
23
  ## Model description
24
 
 
400
  | 0.7449 | 0.1211 | 0.7969 | 0.1201 | 353 |
401
  | 0.7441 | 0.1211 | 0.7905 | 0.1210 | 354 |
402
  | 0.7437 | 0.1211 | 0.8018 | 0.1207 | 355 |
403
+ | 0.7439 | 0.1211 | 0.8013 | 0.1203 | 356 |
404
 
405
 
406
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83e96ce54a495390f9f91c09607c05bf7a202b04409b9f94fc7a69b43aed5391
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705d92f79c46411da313e2005c45965dd6063f42d0c7cf218384fd6b21841687
3
  size 499741936