End of training

README.md

@@ -25,13 +25,7 @@ chat_template: llama3
 dataset_prepared_path: null
 datasets:
 - path: mhenrichsen/alpaca_2k_test
-  type:
-    field_input: input
-    field_instruction: instruction
-    field_output: output
-    field_system: text
-    system_format: '{system}'
-    system_prompt: you are helpful
+  type: alpaca
 debug: null
 deepspeed: null
 early_stopping_patience: null
@@ -96,7 +90,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4253
+- Loss: 1.0050
 
 ## Model description
 
@@ -130,10 +124,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 6.0039        | 0.0042 | 1    | 5.7351          |
-| 6.0484        | 0.0126 | 3    | 5.6486          |
-| 4.8758        | 0.0253 | 6    | 3.8893          |
-| 1.3682        | 0.0379 | 9    | 0.4253          |
+| 4.8197        | 0.0042 | 1    | 4.6394          |
+| 4.6489        | 0.0126 | 3    | 4.5547          |
+| 4.0712        | 0.0253 | 6    | 2.9871          |
+| 1.3689        | 0.0379 | 9    | 1.0050          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5f1f3db3449ac4064e08005aafebb4800d250142238c83063af55fd3fefffd
+oid sha256:a0f5480285728eabc395dd7b2f6aa5f5e8e8ad30c8acb9171dd1a5c5b6cae604
 size 982663982