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
7e02855
•
1 Parent(s): 2ede84a

Training in progress epoch 408

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: 0.7275
18
- - Train Accuracy: 0.1215
19
- - Validation Loss: 0.7842
20
- - Validation Accuracy: 0.1204
21
- - Epoch: 407
22
 
23
  ## Model description
24
 
@@ -452,6 +452,7 @@ The following hyperparameters were used during training:
452
  | 0.7266 | 0.1215 | 0.7891 | 0.1208 | 405 |
453
  | 0.7276 | 0.1216 | 0.7808 | 0.1209 | 406 |
454
  | 0.7275 | 0.1215 | 0.7842 | 0.1204 | 407 |
 
455
 
456
 
457
  ### 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: 0.7266
18
+ - Train Accuracy: 0.1216
19
+ - Validation Loss: 0.7930
20
+ - Validation Accuracy: 0.1210
21
+ - Epoch: 408
22
 
23
  ## Model description
24
 
 
452
  | 0.7266 | 0.1215 | 0.7891 | 0.1208 | 405 |
453
  | 0.7276 | 0.1216 | 0.7808 | 0.1209 | 406 |
454
  | 0.7275 | 0.1215 | 0.7842 | 0.1204 | 407 |
455
+ | 0.7266 | 0.1216 | 0.7930 | 0.1210 | 408 |
456
 
457
 
458
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a51a16081779cf8761271b01a6932be1c57078012475900e727de1d013274a
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93388d6a7dc9d246e7a00a17e388eafcd5679830194046ffc287121d37b2ec2a
3
  size 499741936