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
bae355f
·
1 Parent(s): ec7a3f4

Training in progress epoch 358

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: 0.8130
20
- - Validation Accuracy: 0.1204
21
- - Epoch: 357
22
 
23
  ## Model description
24
 
@@ -402,6 +402,7 @@ The following hyperparameters were used during training:
402
  | 0.7437 | 0.1211 | 0.8018 | 0.1207 | 355 |
403
  | 0.7439 | 0.1211 | 0.8013 | 0.1203 | 356 |
404
  | 0.7437 | 0.1211 | 0.8130 | 0.1204 | 357 |
 
405
 
406
 
407
  ### 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: 0.7426
18
  - Train Accuracy: 0.1211
19
+ - Validation Loss: 0.8013
20
+ - Validation Accuracy: 0.1205
21
+ - Epoch: 358
22
 
23
  ## Model description
24
 
 
402
  | 0.7437 | 0.1211 | 0.8018 | 0.1207 | 355 |
403
  | 0.7439 | 0.1211 | 0.8013 | 0.1203 | 356 |
404
  | 0.7437 | 0.1211 | 0.8130 | 0.1204 | 357 |
405
+ | 0.7426 | 0.1211 | 0.8013 | 0.1205 | 358 |
406
 
407
 
408
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbb3fe5a63a649d02c3396150171976103404931e347c63806ada0e6ca10a9d8
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b00748dd77dc947171a458b278bbf7d2ca90ffd6428039eb2ee6ad2cd803a9c
3
  size 499741936