Upload 7 files

README.md

@@ -21,7 +21,7 @@ base_model: NousResearch/Llama-2-7b-hf
 bf16: false
 dataset_prepared_path: null
 datasets:
-- path: caffeinatedcherrychic/test-dataset-io
+- path: caffeinatedcherrychic/cidds-agg-alpaca-iio
  type: alpaca
 debug: null
 deepspeed: null
@@ -83,7 +83,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7530
+- Loss: 0.6372
 
 ## Model description
 
@@ -116,7 +116,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8802 | 0.0 | 20 | 0.7530 |
+| 0.7917 | 0.0 | 20 | 0.6372 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
  "rank_pattern": {},
  "revision": null,
  "target_modules": [
- "o_proj",
- "up_proj",
+ "k_proj",
  "q_proj",
+ "up_proj",
+ "o_proj",
  "down_proj",
  "v_proj",
- "gate_proj",
- "k_proj"
+ "gate_proj"
  ],
  "task_type": "CAUSAL_LM",
  "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0cd794280ba4be814605b8e350c940212b9825d39954d62b6e4429064869c7
+oid sha256:4fe6016748a4649511c7cb4545e38323bffc0ff088bb42b33e6373b9a5be77d3
 size 319977674