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
bd69aeb
•
1 Parent(s): efe0918

Training in progress epoch 223

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: 0.8095
18
  - Train Accuracy: 0.1194
19
- - Validation Loss: 0.8340
20
- - Validation Accuracy: 0.1195
21
- - Epoch: 222
22
 
23
  ## Model description
24
 
@@ -267,6 +267,7 @@ The following hyperparameters were used during training:
267
  | 0.8118 | 0.1193 | 0.8198 | 0.1183 | 220 |
268
  | 0.8115 | 0.1193 | 0.8164 | 0.1200 | 221 |
269
  | 0.8095 | 0.1194 | 0.8340 | 0.1195 | 222 |
 
270
 
271
 
272
  ### 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: 0.8090
18
  - Train Accuracy: 0.1194
19
+ - Validation Loss: 0.8071
20
+ - Validation Accuracy: 0.1208
21
+ - Epoch: 223
22
 
23
  ## Model description
24
 
 
267
  | 0.8118 | 0.1193 | 0.8198 | 0.1183 | 220 |
268
  | 0.8115 | 0.1193 | 0.8164 | 0.1200 | 221 |
269
  | 0.8095 | 0.1194 | 0.8340 | 0.1195 | 222 |
270
+ | 0.8090 | 0.1194 | 0.8071 | 0.1208 | 223 |
271
 
272
 
273
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28d1646e59c4471a9cb57916f5838310064f98ea64aebe30ff8e7786bce133f1
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c57de2cc475be34f6db916f928f1e3ff043ca4c0eda79c536b9aca2a53f5083
3
  size 499741936