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
d1b8b3f
•
1 Parent(s): 0386b56

Training in progress epoch 461

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: 0.7137
18
  - Train Accuracy: 0.1219
19
- - Validation Loss: 0.7886
20
- - Validation Accuracy: 0.1227
21
- - Epoch: 460
22
 
23
  ## Model description
24
 
@@ -505,6 +505,7 @@ The following hyperparameters were used during training:
505
  | 0.7140 | 0.1219 | 0.7920 | 0.1210 | 458 |
506
  | 0.7143 | 0.1219 | 0.7925 | 0.1203 | 459 |
507
  | 0.7137 | 0.1219 | 0.7886 | 0.1227 | 460 |
 
508
 
509
 
510
  ### 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: 0.7135
18
  - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7964
20
+ - Validation Accuracy: 0.1206
21
+ - Epoch: 461
22
 
23
  ## Model description
24
 
 
505
  | 0.7140 | 0.1219 | 0.7920 | 0.1210 | 458 |
506
  | 0.7143 | 0.1219 | 0.7925 | 0.1203 | 459 |
507
  | 0.7137 | 0.1219 | 0.7886 | 0.1227 | 460 |
508
+ | 0.7135 | 0.1219 | 0.7964 | 0.1206 | 461 |
509
 
510
 
511
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dbb74e55ddae025f31ba9b93c5bea12b8a7153dba4df7b7949232c4d6c6befb
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90397ec5a252f54b5748ef8c7397a626dd63f837bccb32134d186e3abe016fa
3
  size 499741936