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
4ee333d
•
1 Parent(s): aa410af

Training in progress epoch 486

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: 0.7092
18
- - Train Accuracy: 0.1220
19
- - Validation Loss: 0.7954
20
- - Validation Accuracy: 0.1219
21
- - Epoch: 485
22
 
23
  ## Model description
24
 
@@ -530,6 +530,7 @@ The following hyperparameters were used during training:
530
  | 0.7096 | 0.1220 | 0.7793 | 0.1210 | 483 |
531
  | 0.7082 | 0.1220 | 0.7627 | 0.1217 | 484 |
532
  | 0.7092 | 0.1220 | 0.7954 | 0.1219 | 485 |
 
533
 
534
 
535
  ### 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: 0.7086
18
+ - Train Accuracy: 0.1221
19
+ - Validation Loss: 0.7837
20
+ - Validation Accuracy: 0.1206
21
+ - Epoch: 486
22
 
23
  ## Model description
24
 
 
530
  | 0.7096 | 0.1220 | 0.7793 | 0.1210 | 483 |
531
  | 0.7082 | 0.1220 | 0.7627 | 0.1217 | 484 |
532
  | 0.7092 | 0.1220 | 0.7954 | 0.1219 | 485 |
533
+ | 0.7086 | 0.1221 | 0.7837 | 0.1206 | 486 |
534
 
535
 
536
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33eec821e41e7297cf08f0a1f934968d6cf17048adc51de825c8b7ba2cf41161
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4768cb6902ce210126d903c57cc4cd98787e00042ec967d221be9bf73182b
3
  size 499741936