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
8e2bc5a
·
1 Parent(s): dc19d01

Training in progress epoch 259

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: 0.7872
18
- - Train Accuracy: 0.1199
19
- - Validation Loss: 0.8188
20
  - Validation Accuracy: 0.1198
21
- - Epoch: 258
22
 
23
  ## Model description
24
 
@@ -303,6 +303,7 @@ The following hyperparameters were used during training:
303
  | 0.7884 | 0.1200 | 0.8379 | 0.1204 | 256 |
304
  | 0.7882 | 0.1199 | 0.8271 | 0.1194 | 257 |
305
  | 0.7872 | 0.1199 | 0.8188 | 0.1198 | 258 |
 
306
 
307
 
308
  ### 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: 0.7866
18
+ - Train Accuracy: 0.1200
19
+ - Validation Loss: 0.8174
20
  - Validation Accuracy: 0.1198
21
+ - Epoch: 259
22
 
23
  ## Model description
24
 
 
303
  | 0.7884 | 0.1200 | 0.8379 | 0.1204 | 256 |
304
  | 0.7882 | 0.1199 | 0.8271 | 0.1194 | 257 |
305
  | 0.7872 | 0.1199 | 0.8188 | 0.1198 | 258 |
306
+ | 0.7866 | 0.1200 | 0.8174 | 0.1198 | 259 |
307
 
308
 
309
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db431608690e16703f9b01b72e34960a99f0027e25974b7146f4ff2239325b2e
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e45d2354d14ddcd6c157572cfbdb2fd9f6a30275158abed46a5c11c9d12933
3
  size 499741936