atrytone
/

minilm-uncased-squad2-finetuned-squad-12-trainedfor-3

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

atrytone commited on Jan 28, 2023

Commit

bba6580

·

1 Parent(s): 1cbef9f

update model card README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [deepset/minilm-uncased-squad2](https://huggingface.co/deepset/minilm-uncased-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6607
 ## Model description
@@ -38,16 +38,16 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
 - num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6841        | 1.0   | 578  | 0.6561          |
-| 0.6406        | 2.0   | 1156 | 0.6518          |
-| 0.6156        | 3.0   | 1734 | 0.6607          |
 ### Framework versions

 This model is a fine-tuned version of [deepset/minilm-uncased-squad2](https://huggingface.co/deepset/minilm-uncased-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6609
 ## Model description
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
 - num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 0.6853        | 1.0   | 578  | 0.6597          |
+| 0.6374        | 2.0   | 1156 | 0.6548          |
+| 0.6119        | 3.0   | 1734 | 0.6609          |
 ### Framework versions