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
e41d7fa
•
1 Parent(s): 76e9084

Training in progress epoch 330

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: 0.7540
18
- - Train Accuracy: 0.1208
19
- - Validation Loss: 0.7949
20
- - Validation Accuracy: 0.1209
21
- - Epoch: 329
22
 
23
  ## Model description
24
 
@@ -374,6 +374,7 @@ The following hyperparameters were used during training:
374
  | 0.7544 | 0.1208 | 0.8022 | 0.1208 | 327 |
375
  | 0.7542 | 0.1208 | 0.8096 | 0.1203 | 328 |
376
  | 0.7540 | 0.1208 | 0.7949 | 0.1209 | 329 |
 
377
 
378
 
379
  ### 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: 0.7536
18
+ - Train Accuracy: 0.1209
19
+ - Validation Loss: 0.8184
20
+ - Validation Accuracy: 0.1205
21
+ - Epoch: 330
22
 
23
  ## Model description
24
 
 
374
  | 0.7544 | 0.1208 | 0.8022 | 0.1208 | 327 |
375
  | 0.7542 | 0.1208 | 0.8096 | 0.1203 | 328 |
376
  | 0.7540 | 0.1208 | 0.7949 | 0.1209 | 329 |
377
+ | 0.7536 | 0.1209 | 0.8184 | 0.1205 | 330 |
378
 
379
 
380
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c466c59ea722d5c2b9bf6c912d369702c0f953c35a4436c72ef427f77c4252f
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db378aea1abb6deafc8e892a750cc31fc3ff09c84ee5875aab816ba481319882
3
  size 499741936