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
7cce8b4
•
1 Parent(s): bf91fd4

Training in progress epoch 475

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: 0.7106
18
  - Train Accuracy: 0.1220
19
- - Validation Loss: 0.7695
20
- - Validation Accuracy: 0.1209
21
- - Epoch: 474
22
 
23
  ## Model description
24
 
@@ -519,6 +519,7 @@ The following hyperparameters were used during training:
519
  | 0.7115 | 0.1219 | 0.7861 | 0.1214 | 472 |
520
  | 0.7111 | 0.1220 | 0.7744 | 0.1215 | 473 |
521
  | 0.7106 | 0.1220 | 0.7695 | 0.1209 | 474 |
 
522
 
523
 
524
  ### 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: 0.7109
18
  - Train Accuracy: 0.1220
19
+ - Validation Loss: 0.7573
20
+ - Validation Accuracy: 0.1208
21
+ - Epoch: 475
22
 
23
  ## Model description
24
 
 
519
  | 0.7115 | 0.1219 | 0.7861 | 0.1214 | 472 |
520
  | 0.7111 | 0.1220 | 0.7744 | 0.1215 | 473 |
521
  | 0.7106 | 0.1220 | 0.7695 | 0.1209 | 474 |
522
+ | 0.7109 | 0.1220 | 0.7573 | 0.1208 | 475 |
523
 
524
 
525
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c35a1c8638e665b7bf65b131c53e68780159e8c63ada0dfd90da97569e0398b1
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3329e53da839e1eccb54d553367a1a65f68b69d173ecfe8a397038879caabeaf
3
  size 499741936