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
806e3b8
•
1 Parent(s): 7122df8

Training in progress epoch 431

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: 0.7195
18
  - Train Accuracy: 0.1217
19
- - Validation Loss: 0.7871
20
- - Validation Accuracy: 0.1215
21
- - Epoch: 430
22
 
23
  ## Model description
24
 
@@ -475,6 +475,7 @@ The following hyperparameters were used during training:
475
  | 0.7215 | 0.1217 | 0.7954 | 0.1218 | 428 |
476
  | 0.7210 | 0.1217 | 0.7817 | 0.1208 | 429 |
477
  | 0.7195 | 0.1217 | 0.7871 | 0.1215 | 430 |
 
478
 
479
 
480
  ### 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: 0.7206
18
  - Train Accuracy: 0.1217
19
+ - Validation Loss: 0.7778
20
+ - Validation Accuracy: 0.1211
21
+ - Epoch: 431
22
 
23
  ## Model description
24
 
 
475
  | 0.7215 | 0.1217 | 0.7954 | 0.1218 | 428 |
476
  | 0.7210 | 0.1217 | 0.7817 | 0.1208 | 429 |
477
  | 0.7195 | 0.1217 | 0.7871 | 0.1215 | 430 |
478
+ | 0.7206 | 0.1217 | 0.7778 | 0.1211 | 431 |
479
 
480
 
481
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5af804eaaf49bbdfbcdbca02a381db36dbb36f8103b07cdb62aff60b6703ab7
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07f0a3237990ed0e127a22d801af6404e21e7b377b31f028301ef1df4a1e4ce5
3
  size 499741936