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
7512c52
•
1 Parent(s): ddbf3d8

Training in progress epoch 400

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: 0.7288
18
  - Train Accuracy: 0.1215
19
- - Validation Loss: 0.8115
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 399
22
 
23
  ## Model description
24
 
@@ -444,6 +444,7 @@ The following hyperparameters were used during training:
444
  | 0.7306 | 0.1214 | 0.7817 | 0.1212 | 397 |
445
  | 0.7293 | 0.1215 | 0.7827 | 0.1207 | 398 |
446
  | 0.7288 | 0.1215 | 0.8115 | 0.1202 | 399 |
 
447
 
448
 
449
  ### 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: 0.7296
18
  - Train Accuracy: 0.1215
19
+ - Validation Loss: 0.7998
20
+ - Validation Accuracy: 0.1206
21
+ - Epoch: 400
22
 
23
  ## Model description
24
 
 
444
  | 0.7306 | 0.1214 | 0.7817 | 0.1212 | 397 |
445
  | 0.7293 | 0.1215 | 0.7827 | 0.1207 | 398 |
446
  | 0.7288 | 0.1215 | 0.8115 | 0.1202 | 399 |
447
+ | 0.7296 | 0.1215 | 0.7998 | 0.1206 | 400 |
448
 
449
 
450
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad5b20091cd5e9c07b8a13167ee11d44a1e52775addf667c696d15c56f03309f
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1cb46afeb971db42f5fb46497c6c385cdf41dd03efcffb184d0b2eac17db9d
3
  size 499741936