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
08b894d
•
1 Parent(s): ac9bba3

Training in progress epoch 265

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: 0.7844
18
- - Train Accuracy: 0.1200
19
- - Validation Loss: 0.8311
20
- - Validation Accuracy: 0.1185
21
- - Epoch: 264
22
 
23
  ## Model description
24
 
@@ -309,6 +309,7 @@ The following hyperparameters were used during training:
309
  | 0.7859 | 0.1200 | 0.8228 | 0.1199 | 262 |
310
  | 0.7844 | 0.1200 | 0.8237 | 0.1201 | 263 |
311
  | 0.7844 | 0.1200 | 0.8311 | 0.1185 | 264 |
 
312
 
313
 
314
  ### 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: 0.7834
18
+ - Train Accuracy: 0.1201
19
+ - Validation Loss: 0.8193
20
+ - Validation Accuracy: 0.1193
21
+ - Epoch: 265
22
 
23
  ## Model description
24
 
 
309
  | 0.7859 | 0.1200 | 0.8228 | 0.1199 | 262 |
310
  | 0.7844 | 0.1200 | 0.8237 | 0.1201 | 263 |
311
  | 0.7844 | 0.1200 | 0.8311 | 0.1185 | 264 |
312
+ | 0.7834 | 0.1201 | 0.8193 | 0.1193 | 265 |
313
 
314
 
315
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89f298f3e191195c0c5720939b406edea8455b1557425c6b03204f01e48f0f44
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:914d5265d3c61abc1be7ecbdb887d982a9e2371e636457eb9e056976bbfa8336
3
  size 499741936