End of training

README.md

@@ -91,7 +91,7 @@ wandb_entity: null
 wandb_mode: online
 wandb_name: null
 wandb_project: Gradients-On-Demand
-wandb_run: d8km
+wandb_run: htga
 wandb_runid: null
 warmup_steps: 10
 weight_decay: 0.0
@@ -105,7 +105,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [defog/llama-3-sqlcoder-8b](https://huggingface.co/defog/llama-3-sqlcoder-8b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5428
+- Loss: 1.5405
 
 ## Model description
 
@@ -143,9 +143,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 2.2598        | 0.0187 | 1    | 2.2258          |
-| 2.2203        | 0.0561 | 3    | 2.2072          |
-| 2.1188        | 0.1121 | 6    | 1.8779          |
-| 1.718         | 0.1682 | 9    | 1.5428          |
+| 2.2198        | 0.0561 | 3    | 2.2064          |
+| 2.1182        | 0.1121 | 6    | 1.8800          |
+| 1.7179        | 0.1682 | 9    | 1.5405          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe603355606854777405a7eed7ba52bef77cea4907c1018d789127eb147ed3b1
+oid sha256:abd4b276c4e2de891da8ab9d673e4dfdf048992593ba8e1a36e61fa5f0940f34
 size 84047370