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
d330b99
•
1 Parent(s): 9f0f3ec

Training in progress epoch 413

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: 0.7258
18
- - Train Accuracy: 0.1216
19
- - Validation Loss: 0.7979
20
- - Validation Accuracy: 0.1211
21
- - Epoch: 412
22
 
23
  ## Model description
24
 
@@ -457,6 +457,7 @@ The following hyperparameters were used during training:
457
  | 0.7258 | 0.1216 | 0.8071 | 0.1217 | 410 |
458
  | 0.7253 | 0.1216 | 0.7920 | 0.1198 | 411 |
459
  | 0.7258 | 0.1216 | 0.7979 | 0.1211 | 412 |
 
460
 
461
 
462
  ### 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: 0.7256
18
+ - Train Accuracy: 0.1215
19
+ - Validation Loss: 0.8066
20
+ - Validation Accuracy: 0.1200
21
+ - Epoch: 413
22
 
23
  ## Model description
24
 
 
457
  | 0.7258 | 0.1216 | 0.8071 | 0.1217 | 410 |
458
  | 0.7253 | 0.1216 | 0.7920 | 0.1198 | 411 |
459
  | 0.7258 | 0.1216 | 0.7979 | 0.1211 | 412 |
460
+ | 0.7256 | 0.1215 | 0.8066 | 0.1200 | 413 |
461
 
462
 
463
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8d2d977710532c3386519c6a1528404ea1a7f933a4a7561d22387e10f3b8b39
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456b83a73832486f5eea8f58aa95707428c5db254ffd34d5d0fcb515718908d2
3
  size 499741936