Training in progress, step 2

README.md

@@ -1,18 +1,17 @@
 ---
 base_model: Qwen/Qwen2.5-0.5B-Instruct
-datasets: trl-lib/Capybara
 library_name: transformers
 model_name: Qwen2.5-0.5B-Instruct
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
 # Model Card for Qwen2.5-0.5B-Instruct
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the [trl-lib/Capybara](https://huggingface.co/datasets/trl-lib/Capybara) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -29,12 +29,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj",
     "down_proj",
-    "up_proj"
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61bb83466c70604821c5d201100ef61424744d874ede0895308a512bc7a3e17f
+oid sha256:8c95112ab5037f2940d1255da6f26ba2b752205a53e0641738becdcef4349614
 size 70430032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab3879cb08abf33f556c7003081e0f964ca5f4cde0ca6b83525b9d48326cf415
+oid sha256:bce58871d858bf2ce54c4aa3f22e8532d01f0458641fca8e9f984311db36b18c
 size 6161