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
45d108d
·
1 Parent(s): f9edd26

Training in progress epoch 340

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: 0.7493
18
  - Train Accuracy: 0.1209
19
- - Validation Loss: 0.7969
20
- - Validation Accuracy: 0.1209
21
- - Epoch: 339
22
 
23
  ## Model description
24
 
@@ -384,6 +384,7 @@ The following hyperparameters were used during training:
384
  | 0.7504 | 0.1210 | 0.7974 | 0.1217 | 337 |
385
  | 0.7506 | 0.1210 | 0.7910 | 0.1206 | 338 |
386
  | 0.7493 | 0.1209 | 0.7969 | 0.1209 | 339 |
 
387
 
388
 
389
  ### 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: 0.7498
18
  - Train Accuracy: 0.1209
19
+ - Validation Loss: 0.8105
20
+ - Validation Accuracy: 0.1205
21
+ - Epoch: 340
22
 
23
  ## Model description
24
 
 
384
  | 0.7504 | 0.1210 | 0.7974 | 0.1217 | 337 |
385
  | 0.7506 | 0.1210 | 0.7910 | 0.1206 | 338 |
386
  | 0.7493 | 0.1209 | 0.7969 | 0.1209 | 339 |
387
+ | 0.7498 | 0.1209 | 0.8105 | 0.1205 | 340 |
388
 
389
 
390
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b2830aa3a0cb19c40b606ecdb8ff11101d7e2bb7df5a8377505799815c06ce7
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4716f368d72eed8621f8a36f728888e11c72e48bf127786d871f63754a6c697
3
  size 499741936