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
d2c0360
•
1 Parent(s): 475f0d7

Training in progress epoch 425

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: 0.7222
18
  - Train Accuracy: 0.1217
19
- - Validation Loss: 0.7910
20
- - Validation Accuracy: 0.1204
21
- - Epoch: 424
22
 
23
  ## Model description
24
 
@@ -469,6 +469,7 @@ The following hyperparameters were used during training:
469
  | 0.7235 | 0.1216 | 0.7949 | 0.1191 | 422 |
470
  | 0.7226 | 0.1216 | 0.7925 | 0.1203 | 423 |
471
  | 0.7222 | 0.1217 | 0.7910 | 0.1204 | 424 |
 
472
 
473
 
474
  ### 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: 0.7220
18
  - Train Accuracy: 0.1217
19
+ - Validation Loss: 0.7720
20
+ - Validation Accuracy: 0.1211
21
+ - Epoch: 425
22
 
23
  ## Model description
24
 
 
469
  | 0.7235 | 0.1216 | 0.7949 | 0.1191 | 422 |
470
  | 0.7226 | 0.1216 | 0.7925 | 0.1203 | 423 |
471
  | 0.7222 | 0.1217 | 0.7910 | 0.1204 | 424 |
472
+ | 0.7220 | 0.1217 | 0.7720 | 0.1211 | 425 |
473
 
474
 
475
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c0e5353416e842527f1c580a11ab5c18a865eff102e7d575be3c9e09d653353
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87382c8300ccce8459601f413f3b6e7600503aa6ab1d4692780de3d8e18c907
3
  size 499741936