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
8a472c8
·
1 Parent(s): 8934991

Training in progress epoch 454

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: 0.7153
18
- - Train Accuracy: 0.1218
19
- - Validation Loss: 0.7817
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 453
22
 
23
  ## Model description
24
 
@@ -498,6 +498,7 @@ The following hyperparameters were used during training:
498
  | 0.7150 | 0.1219 | 0.8047 | 0.1212 | 451 |
499
  | 0.7147 | 0.1219 | 0.7847 | 0.1208 | 452 |
500
  | 0.7153 | 0.1218 | 0.7817 | 0.1199 | 453 |
 
501
 
502
 
503
  ### 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: 0.7146
18
+ - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7886
20
+ - Validation Accuracy: 0.1210
21
+ - Epoch: 454
22
 
23
  ## Model description
24
 
 
498
  | 0.7150 | 0.1219 | 0.8047 | 0.1212 | 451 |
499
  | 0.7147 | 0.1219 | 0.7847 | 0.1208 | 452 |
500
  | 0.7153 | 0.1218 | 0.7817 | 0.1199 | 453 |
501
+ | 0.7146 | 0.1219 | 0.7886 | 0.1210 | 454 |
502
 
503
 
504
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cca3f0b428bbc340f8d4ee5f2f840f38a949a00e1c5cad6973cf231843c1d30
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a604b4e6492e789f749a28ae44a5edb4420a82e3b6aac5a5e60751b371d6dce
3
  size 499741936