vaibhav9
/

hangman-bert-mini

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

vaibhav9 commited on Sep 27, 2023

Commit

0266a0d

·

1 Parent(s): 71d5db8

End of training

Files changed (2) hide show

README.md +4 -4
pytorch_model.bin +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5320
 ## Model description
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6029        | 1.0   | 2609 | 1.5589          |
-| 1.5918        | 2.0   | 5218 | 1.5463          |
-| 1.5866        | 3.0   | 7827 | 1.5320          |
 ### Framework versions

 This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.7439
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.8086        | 1.0   | 2609 | 1.7571          |
+| 1.803         | 2.0   | 5218 | 1.7628          |
+| 1.7955        | 3.0   | 7827 | 1.7439          |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537824158b7c633599f53db4b42aab60f50062c29707ceaea2520a338a7f2b2d
 size 44831439

 version https://git-lfs.github.com/spec/v1
+oid sha256:58ff6cf9edb1089ac638a241f479f8168e961fab555a07b96b64ad6c516ee5f9
 size 44831439