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
665a997
•
1 Parent(s): 888bf5d

Training in progress epoch 447

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: 0.7165
18
  - Train Accuracy: 0.1218
19
- - Validation Loss: 0.7979
20
- - Validation Accuracy: 0.1208
21
- - Epoch: 446
22
 
23
  ## Model description
24
 
@@ -491,6 +491,7 @@ The following hyperparameters were used during training:
491
  | 0.7170 | 0.1218 | 0.7935 | 0.1206 | 444 |
492
  | 0.7171 | 0.1218 | 0.7959 | 0.1204 | 445 |
493
  | 0.7165 | 0.1218 | 0.7979 | 0.1208 | 446 |
 
494
 
495
 
496
  ### 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: 0.7164
18
  - Train Accuracy: 0.1218
19
+ - Validation Loss: 0.7930
20
+ - Validation Accuracy: 0.1215
21
+ - Epoch: 447
22
 
23
  ## Model description
24
 
 
491
  | 0.7170 | 0.1218 | 0.7935 | 0.1206 | 444 |
492
  | 0.7171 | 0.1218 | 0.7959 | 0.1204 | 445 |
493
  | 0.7165 | 0.1218 | 0.7979 | 0.1208 | 446 |
494
+ | 0.7164 | 0.1218 | 0.7930 | 0.1215 | 447 |
495
 
496
 
497
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb6e53621f5c94e6c8795406da1713521dbd2525cdf7fa617be90a6aaced16e2
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e761fe74e336b913c836505bf2c2e5cc17ad09549f56acd463f2dcd6bbe6bb5
3
  size 499741936