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
bf13a11
·
1 Parent(s): cfbc33e

Training in progress epoch 129

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: 0.9095
18
  - Train Accuracy: 0.1168
19
- - Validation Loss: 0.8945
20
- - Validation Accuracy: 0.1173
21
- - Epoch: 128
22
 
23
  ## Model description
24
 
@@ -173,6 +173,7 @@ The following hyperparameters were used during training:
173
  | 0.9135 | 0.1168 | 0.9160 | 0.1169 | 126 |
174
  | 0.9116 | 0.1167 | 0.8940 | 0.1180 | 127 |
175
  | 0.9095 | 0.1168 | 0.8945 | 0.1173 | 128 |
 
176
 
177
 
178
  ### 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: 0.9081
18
  - Train Accuracy: 0.1168
19
+ - Validation Loss: 0.9126
20
+ - Validation Accuracy: 0.1166
21
+ - Epoch: 129
22
 
23
  ## Model description
24
 
 
173
  | 0.9135 | 0.1168 | 0.9160 | 0.1169 | 126 |
174
  | 0.9116 | 0.1167 | 0.8940 | 0.1180 | 127 |
175
  | 0.9095 | 0.1168 | 0.8945 | 0.1173 | 128 |
176
+ | 0.9081 | 0.1168 | 0.9126 | 0.1166 | 129 |
177
 
178
 
179
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b17e7e729705d050975564a8a59a207c895c67ae000356da9a3c4215e38d8be8
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37bfdd9b013b220184707fa1ae09cbccc77e2c3a8a8f319d123f77a11d4991e8
3
  size 499741936