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
eb833bd
·
1 Parent(s): 4302597

Training in progress epoch 263

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: 0.7859
18
  - Train Accuracy: 0.1200
19
- - Validation Loss: 0.8228
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 262
22
 
23
  ## Model description
24
 
@@ -307,6 +307,7 @@ The following hyperparameters were used during training:
307
  | 0.7857 | 0.1200 | 0.8379 | 0.1198 | 260 |
308
  | 0.7859 | 0.1200 | 0.8174 | 0.1204 | 261 |
309
  | 0.7859 | 0.1200 | 0.8228 | 0.1199 | 262 |
 
310
 
311
 
312
  ### 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: 0.7844
18
  - Train Accuracy: 0.1200
19
+ - Validation Loss: 0.8237
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 263
22
 
23
  ## Model description
24
 
 
307
  | 0.7857 | 0.1200 | 0.8379 | 0.1198 | 260 |
308
  | 0.7859 | 0.1200 | 0.8174 | 0.1204 | 261 |
309
  | 0.7859 | 0.1200 | 0.8228 | 0.1199 | 262 |
310
+ | 0.7844 | 0.1200 | 0.8237 | 0.1201 | 263 |
311
 
312
 
313
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:782f691f3f78603ba99244807fd011ad8294e22088414e484ff7ca4501a8a54e
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88138b561b7c370ad9ed99f1a0ad9c90e8ac00f5f588561c26f66356b8e08cb7
3
  size 499741936