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
8977bdb
•
1 Parent(s): 1cbefdd

Training in progress epoch 268

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: 0.7833
18
- - Train Accuracy: 0.1200
19
- - Validation Loss: 0.8291
20
- - Validation Accuracy: 0.1194
21
- - Epoch: 267
22
 
23
  ## Model description
24
 
@@ -312,6 +312,7 @@ The following hyperparameters were used during training:
312
  | 0.7834 | 0.1201 | 0.8193 | 0.1193 | 265 |
313
  | 0.7834 | 0.1201 | 0.8276 | 0.1191 | 266 |
314
  | 0.7833 | 0.1200 | 0.8291 | 0.1194 | 267 |
 
315
 
316
 
317
  ### 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: 0.7821
18
+ - Train Accuracy: 0.1201
19
+ - Validation Loss: 0.8335
20
+ - Validation Accuracy: 0.1195
21
+ - Epoch: 268
22
 
23
  ## Model description
24
 
 
312
  | 0.7834 | 0.1201 | 0.8193 | 0.1193 | 265 |
313
  | 0.7834 | 0.1201 | 0.8276 | 0.1191 | 266 |
314
  | 0.7833 | 0.1200 | 0.8291 | 0.1194 | 267 |
315
+ | 0.7821 | 0.1201 | 0.8335 | 0.1195 | 268 |
316
 
317
 
318
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:686971190db58b22b5b9d95266a3f2ae1abfab347fa1f494adc190b6dda5ce35
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e77d2733c9e61fb6f24bdd2bf35117fc4704d5a1a74d96c4eda4047ad00b3cb
3
  size 499741936