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
4fb1e49
·
1 Parent(s): dbbc034

Training in progress epoch 479

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: 0.7101
18
  - Train Accuracy: 0.1220
19
- - Validation Loss: 0.7881
20
- - Validation Accuracy: 0.1206
21
- - Epoch: 478
22
 
23
  ## Model description
24
 
@@ -523,6 +523,7 @@ The following hyperparameters were used during training:
523
  | 0.7099 | 0.1220 | 0.8003 | 0.1201 | 476 |
524
  | 0.7107 | 0.1220 | 0.7725 | 0.1222 | 477 |
525
  | 0.7101 | 0.1220 | 0.7881 | 0.1206 | 478 |
 
526
 
527
 
528
  ### 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: 0.7096
18
  - Train Accuracy: 0.1220
19
+ - Validation Loss: 0.8027
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 479
22
 
23
  ## Model description
24
 
 
523
  | 0.7099 | 0.1220 | 0.8003 | 0.1201 | 476 |
524
  | 0.7107 | 0.1220 | 0.7725 | 0.1222 | 477 |
525
  | 0.7101 | 0.1220 | 0.7881 | 0.1206 | 478 |
526
+ | 0.7096 | 0.1220 | 0.8027 | 0.1201 | 479 |
527
 
528
 
529
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7552f6a822aeb9d7a5a306568b58aed49bfccc003cb1f44fe41269446291a545
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe739b700e98c1b44e77627bd3e72ed9286439370c4af9a096787372998b31a
3
  size 499741936