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
67e62d7
•
1 Parent(s): fa60e3b

Training in progress epoch 493

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: 0.7075
18
  - Train Accuracy: 0.1221
19
- - Validation Loss: 0.7793
20
- - Validation Accuracy: 0.1210
21
- - Epoch: 492
22
 
23
  ## Model description
24
 
@@ -537,6 +537,7 @@ The following hyperparameters were used during training:
537
  | 0.7083 | 0.1221 | 0.7905 | 0.1205 | 490 |
538
  | 0.7084 | 0.1221 | 0.7842 | 0.1212 | 491 |
539
  | 0.7075 | 0.1221 | 0.7793 | 0.1210 | 492 |
 
540
 
541
 
542
  ### 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: 0.7074
18
  - Train Accuracy: 0.1221
19
+ - Validation Loss: 0.7749
20
+ - Validation Accuracy: 0.1215
21
+ - Epoch: 493
22
 
23
  ## Model description
24
 
 
537
  | 0.7083 | 0.1221 | 0.7905 | 0.1205 | 490 |
538
  | 0.7084 | 0.1221 | 0.7842 | 0.1212 | 491 |
539
  | 0.7075 | 0.1221 | 0.7793 | 0.1210 | 492 |
540
+ | 0.7074 | 0.1221 | 0.7749 | 0.1215 | 493 |
541
 
542
 
543
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:347b393867dd2823f5d895380334ab1e90a0bf59408c77790af9769d8c36a252
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c901d5962ad293f5a142b30144f6410bd3784570dab46efcb123ffb761a98d5e
3
  size 499741936