End of training

README.md

@@ -28,8 +28,6 @@ datasets:
   path: mhenrichsen/alpaca_2k_test
   type:
     field_input: input
-    field_instruction: instruction
-    format: '{instruction} {input}'
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -100,7 +98,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8990
+- Loss: 0.8871
 
 ## Model description
 
@@ -134,10 +132,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.3929        | 0.0021 | 1    | 1.6407          |
-| 0.9241        | 0.2505 | 119  | 0.9293          |
-| 1.0752        | 0.5011 | 238  | 0.9037          |
-| 1.0348        | 0.7516 | 357  | 0.8990          |
+| 1.3828        | 0.0021 | 1    | 1.6319          |
+| 0.9245        | 0.2505 | 119  | 0.9034          |
+| 1.067         | 0.5011 | 238  | 0.8903          |
+| 1.0438        | 0.7516 | 357  | 0.8871          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5dd50c01dca2fe240e4cb973e51015152cbb67a8d44c765a48d653c87db6418
+oid sha256:39be84ffd930a25e916443902d892d39b2f5a9e36541cd5e5462bfa579bfec7b
 size 167934026