Training in progress, step 50

README.md

@@ -27,14 +27,15 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/0b6v7xuv) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/g6zfeh4a) 
+
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.28.0
+- TRL: 0.29.0
 - Transformers: 5.2.0
 - Pytorch: 2.10.0+cu128
 - Datasets: 4.0.0

adapter_config.json

@@ -18,7 +18,7 @@
   "loftq_config": {},
   "lora_alpha": 8,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -30,8 +30,8 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05af5583a63d4e952b108de3edf0b0ad46be48c50ad346e5f84857c35ecde1a
+oid sha256:a61daa1399bbc743282fd2754041abd5997758fc997c2900e705a831af4ce8c2
 size 5071040

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adbc83b8fc704a6a56308798467ddb8b274b083f9cedee2438d5ee3e87635d01
+oid sha256:7a392a9e7f82ea8de586f47e98377e27c28ee661d8a50836c651a3874c36c1c6
 size 5649