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
2457194
•
1 Parent(s): 06f5541

Training in progress epoch 353

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: 0.7453
18
  - Train Accuracy: 0.1211
19
- - Validation Loss: 0.8091
20
- - Validation Accuracy: 0.1197
21
- - Epoch: 352
22
 
23
  ## Model description
24
 
@@ -397,6 +397,7 @@ The following hyperparameters were used during training:
397
  | 0.7460 | 0.1210 | 0.8184 | 0.1206 | 350 |
398
  | 0.7446 | 0.1211 | 0.8047 | 0.1199 | 351 |
399
  | 0.7453 | 0.1211 | 0.8091 | 0.1197 | 352 |
 
400
 
401
 
402
  ### 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: 0.7449
18
  - Train Accuracy: 0.1211
19
+ - Validation Loss: 0.7969
20
+ - Validation Accuracy: 0.1201
21
+ - Epoch: 353
22
 
23
  ## Model description
24
 
 
397
  | 0.7460 | 0.1210 | 0.8184 | 0.1206 | 350 |
398
  | 0.7446 | 0.1211 | 0.8047 | 0.1199 | 351 |
399
  | 0.7453 | 0.1211 | 0.8091 | 0.1197 | 352 |
400
+ | 0.7449 | 0.1211 | 0.7969 | 0.1201 | 353 |
401
 
402
 
403
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaa55913bdc1bd1c474332b7b441a3a757351ca1d5506442b8f8d319db45370e
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a1da7ecc2cb6f06e1127cfd64059e8c4d517d68ea950887986904896d29095
3
  size 499741936