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
dd9456b
·
1 Parent(s): 286efe3

Training in progress epoch 372

Browse files
Files changed (2) hide show
  1. README.md +5 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
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: 0.7380
18
- - Train Accuracy: 0.1212
19
- - Validation Loss: 0.7983
20
- - Validation Accuracy: 0.1207
21
- - Epoch: 371
22
 
23
  ## Model description
24
 
@@ -416,6 +416,7 @@ The following hyperparameters were used during training:
416
  | 0.7399 | 0.1212 | 0.8125 | 0.1211 | 369 |
417
  | 0.7389 | 0.1212 | 0.8101 | 0.1201 | 370 |
418
  | 0.7380 | 0.1212 | 0.7983 | 0.1207 | 371 |
 
419
 
420
 
421
  ### Framework versions
 
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: 0.7380
18
+ - Train Accuracy: 0.1213
19
+ - Validation Loss: 0.7969
20
+ - Validation Accuracy: 0.1210
21
+ - Epoch: 372
22
 
23
  ## Model description
24
 
 
416
  | 0.7399 | 0.1212 | 0.8125 | 0.1211 | 369 |
417
  | 0.7389 | 0.1212 | 0.8101 | 0.1201 | 370 |
418
  | 0.7380 | 0.1212 | 0.7983 | 0.1207 | 371 |
419
+ | 0.7380 | 0.1213 | 0.7969 | 0.1210 | 372 |
420
 
421
 
422
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6911c7634a707130495af077b522fa9e129354f3e1716771f8f8d50cb3fb1ee7
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f6068c9b2e5987a816c510a41bd3b25afa5c9dac7f053bc0ef173ca3bb15d0
3
  size 499741936