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
0721e10
•
1 Parent(s): 6b34e6e

Training in progress epoch 449

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: 0.7164
18
  - Train Accuracy: 0.1219
19
- - Validation Loss: 0.8003
20
- - Validation Accuracy: 0.1210
21
- - Epoch: 448
22
 
23
  ## Model description
24
 
@@ -493,6 +493,7 @@ The following hyperparameters were used during training:
493
  | 0.7165 | 0.1218 | 0.7979 | 0.1208 | 446 |
494
  | 0.7164 | 0.1218 | 0.7930 | 0.1215 | 447 |
495
  | 0.7164 | 0.1219 | 0.8003 | 0.1210 | 448 |
 
496
 
497
 
498
  ### 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: 0.7157
18
  - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7764
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 449
22
 
23
  ## Model description
24
 
 
493
  | 0.7165 | 0.1218 | 0.7979 | 0.1208 | 446 |
494
  | 0.7164 | 0.1218 | 0.7930 | 0.1215 | 447 |
495
  | 0.7164 | 0.1219 | 0.8003 | 0.1210 | 448 |
496
+ | 0.7157 | 0.1219 | 0.7764 | 0.1203 | 449 |
497
 
498
 
499
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bacfa9bb64385630f756979a3bbd3f2afc3b006f65242ee5ad5856dc48cd004
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60403c660dba26ff27f65b54a442e3036518edf1916765a0bbb677c6a15a328
3
  size 499741936