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
45caf86
·
1 Parent(s): 3749f8c

Training in progress epoch 489

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: 0.7079
18
  - Train Accuracy: 0.1221
19
- - Validation Loss: 0.7876
20
- - Validation Accuracy: 0.1206
21
- - Epoch: 488
22
 
23
  ## Model description
24
 
@@ -533,6 +533,7 @@ The following hyperparameters were used during training:
533
  | 0.7086 | 0.1221 | 0.7837 | 0.1206 | 486 |
534
  | 0.7087 | 0.1221 | 0.7856 | 0.1213 | 487 |
535
  | 0.7079 | 0.1221 | 0.7876 | 0.1206 | 488 |
 
536
 
537
 
538
  ### 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: 0.7082
18
  - Train Accuracy: 0.1221
19
+ - Validation Loss: 0.7778
20
+ - Validation Accuracy: 0.1210
21
+ - Epoch: 489
22
 
23
  ## Model description
24
 
 
533
  | 0.7086 | 0.1221 | 0.7837 | 0.1206 | 486 |
534
  | 0.7087 | 0.1221 | 0.7856 | 0.1213 | 487 |
535
  | 0.7079 | 0.1221 | 0.7876 | 0.1206 | 488 |
536
+ | 0.7082 | 0.1221 | 0.7778 | 0.1210 | 489 |
537
 
538
 
539
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a34b6a379265abfde5b7ddc560d216a0328cda98c9cf6c9cda5e7fd46d76828
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f246da5c05ac0330bd355f0c45edf25e635d24b36e2880d3059615c0c3079e85
3
  size 499741936