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
0e4be21
•
1 Parent(s): f026820

Training in progress epoch 472

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: 0.7111
18
- - Train Accuracy: 0.1220
19
- - Validation Loss: 0.7939
20
- - Validation Accuracy: 0.1204
21
- - Epoch: 471
22
 
23
  ## Model description
24
 
@@ -516,6 +516,7 @@ The following hyperparameters were used during training:
516
  | 0.7114 | 0.1220 | 0.7847 | 0.1208 | 469 |
517
  | 0.7107 | 0.1220 | 0.7646 | 0.1219 | 470 |
518
  | 0.7111 | 0.1220 | 0.7939 | 0.1204 | 471 |
 
519
 
520
 
521
  ### 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: 0.7115
18
+ - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7861
20
+ - Validation Accuracy: 0.1214
21
+ - Epoch: 472
22
 
23
  ## Model description
24
 
 
516
  | 0.7114 | 0.1220 | 0.7847 | 0.1208 | 469 |
517
  | 0.7107 | 0.1220 | 0.7646 | 0.1219 | 470 |
518
  | 0.7111 | 0.1220 | 0.7939 | 0.1204 | 471 |
519
+ | 0.7115 | 0.1219 | 0.7861 | 0.1214 | 472 |
520
 
521
 
522
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dab8ca4d2a3518e9424e9fce802250fe813423d9c4967a3483c1aa5cc5c47aa
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54509b4d08c0e7b58960b74b08045808780e11cd4ee48b0e151affb1857b4926
3
  size 499741936