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
6fbcbe9
•
1 Parent(s): 27cc7a7

Training in progress epoch 457

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: 0.7144
18
  - Train Accuracy: 0.1219
19
- - Validation Loss: 0.7793
20
- - Validation Accuracy: 0.1211
21
- - Epoch: 456
22
 
23
  ## Model description
24
 
@@ -501,6 +501,7 @@ The following hyperparameters were used during training:
501
  | 0.7146 | 0.1219 | 0.7886 | 0.1210 | 454 |
502
  | 0.7150 | 0.1219 | 0.7920 | 0.1218 | 455 |
503
  | 0.7144 | 0.1219 | 0.7793 | 0.1211 | 456 |
 
504
 
505
 
506
  ### 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: 0.7143
18
  - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7676
20
+ - Validation Accuracy: 0.1209
21
+ - Epoch: 457
22
 
23
  ## Model description
24
 
 
501
  | 0.7146 | 0.1219 | 0.7886 | 0.1210 | 454 |
502
  | 0.7150 | 0.1219 | 0.7920 | 0.1218 | 455 |
503
  | 0.7144 | 0.1219 | 0.7793 | 0.1211 | 456 |
504
+ | 0.7143 | 0.1219 | 0.7676 | 0.1209 | 457 |
505
 
506
 
507
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c41dbb6327c79e7df581f82fdcf4e04a79e771b7e56a5b5e54e503b776cc483b
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9053999e7c1ef5354c1388f09efc1266f13eae8ff26dc92e0678d28e970132a3
3
  size 499741936