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
40e6ee1
·
1 Parent(s): ff6a030

Training in progress epoch 427

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.7218
18
- - Train Accuracy: 0.1216
19
- - Validation Loss: 0.7979
20
- - Validation Accuracy: 0.1207
21
- - Epoch: 426
22
 
23
  ## Model description
24
 
@@ -471,6 +471,7 @@ The following hyperparameters were used during training:
471
  | 0.7222 | 0.1217 | 0.7910 | 0.1204 | 424 |
472
  | 0.7220 | 0.1217 | 0.7720 | 0.1211 | 425 |
473
  | 0.7218 | 0.1216 | 0.7979 | 0.1207 | 426 |
 
474
 
475
 
476
  ### 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: 0.7205
18
+ - Train Accuracy: 0.1217
19
+ - Validation Loss: 0.7798
20
+ - Validation Accuracy: 0.1205
21
+ - Epoch: 427
22
 
23
  ## Model description
24
 
 
471
  | 0.7222 | 0.1217 | 0.7910 | 0.1204 | 424 |
472
  | 0.7220 | 0.1217 | 0.7720 | 0.1211 | 425 |
473
  | 0.7218 | 0.1216 | 0.7979 | 0.1207 | 426 |
474
+ | 0.7205 | 0.1217 | 0.7798 | 0.1205 | 427 |
475
 
476
 
477
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0d714ff562ed434bb1ffe3f5def24d2c8a70683f7d47e006b5e54151716e432
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c97fff27b12029376aaaa2e4a7593dc07cd7d1e07983532a2bb6f00f257fd26d
3
  size 499741936