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
5393bbb
•
1 Parent(s): dbbd0b5

Training in progress epoch 482

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: 0.7094
18
  - Train Accuracy: 0.1221
19
- - Validation Loss: 0.7798
20
- - Validation Accuracy: 0.1214
21
- - Epoch: 481
22
 
23
  ## Model description
24
 
@@ -526,6 +526,7 @@ The following hyperparameters were used during training:
526
  | 0.7096 | 0.1220 | 0.8027 | 0.1201 | 479 |
527
  | 0.7094 | 0.1221 | 0.7861 | 0.1204 | 480 |
528
  | 0.7094 | 0.1221 | 0.7798 | 0.1214 | 481 |
 
529
 
530
 
531
  ### 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: 0.7097
18
  - Train Accuracy: 0.1221
19
+ - Validation Loss: 0.7837
20
+ - Validation Accuracy: 0.1205
21
+ - Epoch: 482
22
 
23
  ## Model description
24
 
 
526
  | 0.7096 | 0.1220 | 0.8027 | 0.1201 | 479 |
527
  | 0.7094 | 0.1221 | 0.7861 | 0.1204 | 480 |
528
  | 0.7094 | 0.1221 | 0.7798 | 0.1214 | 481 |
529
+ | 0.7097 | 0.1221 | 0.7837 | 0.1205 | 482 |
530
 
531
 
532
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76af32ef974c101686507e7cf57ef8603c0a3b7522d3ebe3cb9a7c7b2dada0d6
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d2f1127fbc07f6df8cf1091a073afb9d91ce6b3ce05813053d20a85ae78b65
3
  size 499741936