Docty
/

question_and_answer

Question Answering

generated_from_keras_callback

Model card Files Files and versions Community

Docty commited on Feb 1

Commit

451cf91

·

1 Parent(s): caa8fc1

Training in progress epoch 3

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4089
 - Validation Loss: 0.6306
-- Epoch: 2
 ## Model description
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 1.2112     | 0.6667          | 0     |
 | 0.5043     | 0.6306          | 1     |
 | 0.4089     | 0.6306          | 2     |
 ### Framework versions

 This model is a fine-tuned version of [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.4124
 - Validation Loss: 0.6306
+- Epoch: 3
 ## Model description
 | 1.2112     | 0.6667          | 0     |
 | 0.5043     | 0.6306          | 1     |
 | 0.4089     | 0.6306          | 2     |
+| 0.4124     | 0.6306          | 3     |
 ### Framework versions