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
24757ee
•
1 Parent(s): a4981a4

Training in progress epoch 364

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: 0.7404
18
  - Train Accuracy: 0.1212
19
- - Validation Loss: 0.8052
20
- - Validation Accuracy: 0.1207
21
- - Epoch: 363
22
 
23
  ## Model description
24
 
@@ -408,6 +408,7 @@ The following hyperparameters were used during training:
408
  | 0.7417 | 0.1212 | 0.7964 | 0.1199 | 361 |
409
  | 0.7408 | 0.1212 | 0.8027 | 0.1203 | 362 |
410
  | 0.7404 | 0.1212 | 0.8052 | 0.1207 | 363 |
 
411
 
412
 
413
  ### 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: 0.7402
18
  - Train Accuracy: 0.1212
19
+ - Validation Loss: 0.7993
20
+ - Validation Accuracy: 0.1204
21
+ - Epoch: 364
22
 
23
  ## Model description
24
 
 
408
  | 0.7417 | 0.1212 | 0.7964 | 0.1199 | 361 |
409
  | 0.7408 | 0.1212 | 0.8027 | 0.1203 | 362 |
410
  | 0.7404 | 0.1212 | 0.8052 | 0.1207 | 363 |
411
+ | 0.7402 | 0.1212 | 0.7993 | 0.1204 | 364 |
412
 
413
 
414
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b44da8490de16bfd3de9ea7b61f66f05371d4a06e0bfb268b1de31ae143e714d
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab1e4bddca934bdb07e8acb7baa70b61565c893d55fb0936ea617341b2464c9
3
  size 499741936