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
e753d9c
•
1 Parent(s): 8f932c6

Training in progress epoch 290

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: 0.7719
18
  - Train Accuracy: 0.1203
19
- - Validation Loss: 0.8359
20
- - Validation Accuracy: 0.1205
21
- - Epoch: 289
22
 
23
  ## Model description
24
 
@@ -334,6 +334,7 @@ The following hyperparameters were used during training:
334
  | 0.7720 | 0.1204 | 0.8228 | 0.1201 | 287 |
335
  | 0.7721 | 0.1204 | 0.8164 | 0.1203 | 288 |
336
  | 0.7719 | 0.1203 | 0.8359 | 0.1205 | 289 |
 
337
 
338
 
339
  ### 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: 0.7713
18
  - Train Accuracy: 0.1203
19
+ - Validation Loss: 0.8145
20
+ - Validation Accuracy: 0.1204
21
+ - Epoch: 290
22
 
23
  ## Model description
24
 
 
334
  | 0.7720 | 0.1204 | 0.8228 | 0.1201 | 287 |
335
  | 0.7721 | 0.1204 | 0.8164 | 0.1203 | 288 |
336
  | 0.7719 | 0.1203 | 0.8359 | 0.1205 | 289 |
337
+ | 0.7713 | 0.1203 | 0.8145 | 0.1204 | 290 |
338
 
339
 
340
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b9d204f11d32afc8043d29de3f57417e9a8a43ce68fadff069e82683f6701ab
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8aabb15ed6fadf86a948e93d01c103dea1f765f0d1e25a8216896d73f02761
3
  size 499741936