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
7087cca
·
1 Parent(s): 8a14282

Training in progress epoch 31

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: 1.9204
18
- - Train Accuracy: 0.0940
19
- - Validation Loss: 1.7549
20
- - Validation Accuracy: 0.0982
21
- - Epoch: 30
22
 
23
  ## Model description
24
 
@@ -75,6 +75,7 @@ The following hyperparameters were used during training:
75
  | 2.3780 | 0.0844 | 2.0498 | 0.0922 | 28 |
76
  | 2.0789 | 0.0907 | 1.8604 | 0.0958 | 29 |
77
  | 1.9204 | 0.0940 | 1.7549 | 0.0982 | 30 |
 
78
 
79
 
80
  ### 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: 1.8162
18
+ - Train Accuracy: 0.0961
19
+ - Validation Loss: 1.6836
20
+ - Validation Accuracy: 0.0983
21
+ - Epoch: 31
22
 
23
  ## Model description
24
 
 
75
  | 2.3780 | 0.0844 | 2.0498 | 0.0922 | 28 |
76
  | 2.0789 | 0.0907 | 1.8604 | 0.0958 | 29 |
77
  | 1.9204 | 0.0940 | 1.7549 | 0.0982 | 30 |
78
+ | 1.8162 | 0.0961 | 1.6836 | 0.0983 | 31 |
79
 
80
 
81
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa1b89860f5bd4cc18f6642fc1ac979b6fa66814421ff8a1c22cce1499804f75
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac443dd95b41bef856cd16669c9936aed4cedbc76436a86190b87dca5e0f827
3
  size 499741936