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
c660e50
•
1 Parent(s): 167fdc2

Training in progress epoch 438

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: 0.7187
18
  - Train Accuracy: 0.1218
19
- - Validation Loss: 0.7910
20
- - Validation Accuracy: 0.1214
21
- - Epoch: 437
22
 
23
  ## Model description
24
 
@@ -482,6 +482,7 @@ The following hyperparameters were used during training:
482
  | 0.7185 | 0.1218 | 0.7866 | 0.1211 | 435 |
483
  | 0.7185 | 0.1218 | 0.7881 | 0.1220 | 436 |
484
  | 0.7187 | 0.1218 | 0.7910 | 0.1214 | 437 |
 
485
 
486
 
487
  ### 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: 0.7180
18
  - Train Accuracy: 0.1218
19
+ - Validation Loss: 0.7949
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 438
22
 
23
  ## Model description
24
 
 
482
  | 0.7185 | 0.1218 | 0.7866 | 0.1211 | 435 |
483
  | 0.7185 | 0.1218 | 0.7881 | 0.1220 | 436 |
484
  | 0.7187 | 0.1218 | 0.7910 | 0.1214 | 437 |
485
+ | 0.7180 | 0.1218 | 0.7949 | 0.1201 | 438 |
486
 
487
 
488
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32f54ba954bf3f62d1060b6f9faa950caaaadfc70f234296ca44c80e41ca58bc
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95da845ca233ce0416bd86beb3fb00858c0cc846d0929c558810aa70de800f94
3
  size 499741936