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
4951b6b
•
1 Parent(s): 7b053d4

Training in progress epoch 470

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: 0.7114
18
  - Train Accuracy: 0.1220
19
- - Validation Loss: 0.7847
20
- - Validation Accuracy: 0.1208
21
- - Epoch: 469
22
 
23
  ## Model description
24
 
@@ -514,6 +514,7 @@ The following hyperparameters were used during training:
514
  | 0.7129 | 0.1219 | 0.7812 | 0.1214 | 467 |
515
  | 0.7118 | 0.1219 | 0.8052 | 0.1217 | 468 |
516
  | 0.7114 | 0.1220 | 0.7847 | 0.1208 | 469 |
 
517
 
518
 
519
  ### 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: 0.7107
18
  - Train Accuracy: 0.1220
19
+ - Validation Loss: 0.7646
20
+ - Validation Accuracy: 0.1219
21
+ - Epoch: 470
22
 
23
  ## Model description
24
 
 
514
  | 0.7129 | 0.1219 | 0.7812 | 0.1214 | 467 |
515
  | 0.7118 | 0.1219 | 0.8052 | 0.1217 | 468 |
516
  | 0.7114 | 0.1220 | 0.7847 | 0.1208 | 469 |
517
+ | 0.7107 | 0.1220 | 0.7646 | 0.1219 | 470 |
518
 
519
 
520
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f076faad492af478d6c917986ea5890f0e2c33f6728a35787d835bdde06696fd
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4edebae8010f1c96d82b3d26e43228d098ca656ee5c5ffee1f8ac095c4e27e91
3
  size 499741936