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
6a5e079
•
1 Parent(s): 9089efb

Training in progress epoch 388

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: 0.7337
18
  - Train Accuracy: 0.1214
19
- - Validation Loss: 0.7856
20
- - Validation Accuracy: 0.1201
21
- - Epoch: 387
22
 
23
  ## Model description
24
 
@@ -432,6 +432,7 @@ The following hyperparameters were used during training:
432
  | 0.7339 | 0.1214 | 0.7871 | 0.1210 | 385 |
433
  | 0.7334 | 0.1214 | 0.7856 | 0.1205 | 386 |
434
  | 0.7337 | 0.1214 | 0.7856 | 0.1201 | 387 |
 
435
 
436
 
437
  ### 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: 0.7330
18
  - Train Accuracy: 0.1214
19
+ - Validation Loss: 0.7817
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 388
22
 
23
  ## Model description
24
 
 
432
  | 0.7339 | 0.1214 | 0.7871 | 0.1210 | 385 |
433
  | 0.7334 | 0.1214 | 0.7856 | 0.1205 | 386 |
434
  | 0.7337 | 0.1214 | 0.7856 | 0.1201 | 387 |
435
+ | 0.7330 | 0.1214 | 0.7817 | 0.1203 | 388 |
436
 
437
 
438
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4b2518a49d5db5f6fa82e76fd650ffa4a0e889e374c20cb18114991eced6c03
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00f2df017ec038821159e8b7e88b75bbd3ffe3ffe6da69607a2cb8827183f24
3
  size 499741936