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
60772d8
·
1 Parent(s): af47315

Training in progress epoch 342

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.8145
20
- - Validation Accuracy: 0.1204
21
- - Epoch: 341
22
 
23
  ## Model description
24
 
@@ -386,6 +386,7 @@ The following hyperparameters were used during training:
386
  | 0.7493 | 0.1209 | 0.7969 | 0.1209 | 339 |
387
  | 0.7498 | 0.1209 | 0.8105 | 0.1205 | 340 |
388
  | 0.7493 | 0.1209 | 0.8145 | 0.1204 | 341 |
 
389
 
390
 
391
  ### 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: 0.7491
18
+ - Train Accuracy: 0.1210
19
+ - Validation Loss: 0.8062
20
+ - Validation Accuracy: 0.1209
21
+ - Epoch: 342
22
 
23
  ## Model description
24
 
 
386
  | 0.7493 | 0.1209 | 0.7969 | 0.1209 | 339 |
387
  | 0.7498 | 0.1209 | 0.8105 | 0.1205 | 340 |
388
  | 0.7493 | 0.1209 | 0.8145 | 0.1204 | 341 |
389
+ | 0.7491 | 0.1210 | 0.8062 | 0.1209 | 342 |
390
 
391
 
392
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46d4d1fcf123da6c266cd54125e5bf5e981b9b5050db385010dff87c448bd356
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5cae6365e89774b26d13361efbf18bb1852a2dd7d8aee801133425dbcfc641
3
  size 499741936