DONE

README.md

@@ -3,7 +3,7 @@ license: llama3
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: meta-llama/Meta-Llama-3-8B
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 model-index:
 - name: results_007
   results: []
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results_007
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.0495
+- Loss: 20.6308
 
 ## Model description
 
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 9.7186        | 1.0   | 1    | 9.5162          |
-| 9.7186        | 2.0   | 2    | 9.3422          |
-| 9.7186        | 3.0   | 3    | 9.1934          |
-| 9.7186        | 4.0   | 4    | 9.0970          |
-| 9.7186        | 5.0   | 5    | 9.0495          |
+| 21.2839       | 1.0   | 1    | 20.8364         |
+| 21.2839       | 2.0   | 2    | 20.9702         |
+| 21.2839       | 3.0   | 3    | 20.7513         |
+| 21.2839       | 4.0   | 4    | 20.7336         |
+| 21.2839       | 5.0   | 5    | 20.6308         |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5332ae7dc88225b28542c2e334ad674409bbe4df8e9a610469100e026f1450
+oid sha256:af8d113fb43a654f5aed5cb2492bd25bd5443a1d1f1e8a0b334126597ecfc2e5
 size 13648432