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
c4b1b46
•
1 Parent(s): 26ca335

Training in progress epoch 328

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: 0.7544
18
  - Train Accuracy: 0.1208
19
- - Validation Loss: 0.8022
20
- - Validation Accuracy: 0.1208
21
- - Epoch: 327
22
 
23
  ## Model description
24
 
@@ -372,6 +372,7 @@ The following hyperparameters were used during training:
372
  | 0.7555 | 0.1208 | 0.7925 | 0.1208 | 325 |
373
  | 0.7553 | 0.1208 | 0.7847 | 0.1201 | 326 |
374
  | 0.7544 | 0.1208 | 0.8022 | 0.1208 | 327 |
 
375
 
376
 
377
  ### 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: 0.7542
18
  - Train Accuracy: 0.1208
19
+ - Validation Loss: 0.8096
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 328
22
 
23
  ## Model description
24
 
 
372
  | 0.7555 | 0.1208 | 0.7925 | 0.1208 | 325 |
373
  | 0.7553 | 0.1208 | 0.7847 | 0.1201 | 326 |
374
  | 0.7544 | 0.1208 | 0.8022 | 0.1208 | 327 |
375
+ | 0.7542 | 0.1208 | 0.8096 | 0.1203 | 328 |
376
 
377
 
378
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f724dc2b9d215907742f542e1a9c6b67ed982922fc7f1df7a94dd9b6518e458c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c60db6e7f6f8ba372f4c9cd48902f1063847d6d23915209f11f7547f7b35d2
3
  size 499741936