DeepDream2045
/

f69fe91d-907e-4874-ab9e-1a7a67cec459

Generated from Trainer

Model card Files Files and versions

DeepDream2045 commited on Dec 15, 2024

Commit

3971683

·

verified ·

1 Parent(s): b6ad951

End of training

Files changed (2) hide show

README.md +3 -3
adapter_model.bin +1 -1

README.md CHANGED Viewed

@@ -105,7 +105,7 @@ xformers_attention: true
 This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7643
 ## Model description
@@ -143,8 +143,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.7304        | 0.0181 | 1    | 3.1888          |
-| 1.4634        | 0.4535 | 25   | 0.9610          |
-| 1.0176        | 0.9070 | 50   | 0.7643          |
 ### Framework versions

 This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.7738
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.7304        | 0.0181 | 1    | 3.1888          |
+| 1.4272        | 0.4535 | 25   | 0.9794          |
+| 1.0303        | 0.9070 | 50   | 0.7738          |
 ### Framework versions

adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd40e360ccfb92a28b2b9be4932c3da4e983b4d63e822ed3f59aa7d2f196712
 size 4532162

 version https://git-lfs.github.com/spec/v1
+oid sha256:962a911ea7dc10ae200c7d27810348816e301432464c0b1e7b700804d7bd1517
 size 4532162