EdBerg/outputs3

README.md

@@ -27,7 +27,7 @@ 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/harpermia882/huggingface/runs/fd35eu7c)
+[<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/harpermia882/huggingface/runs/2ozfkl7x)
 
 This model was trained with SFT.
 
@@ -37,7 +37,7 @@ This model was trained with SFT.
 - Transformers: 4.46.1
 - Pytorch: 2.5.0+cu121
 - Datasets: 3.1.0
-- Tokenizers: 0.20.1
+- Tokenizers: 0.20.2
 
 ## Citations
 

adapter_config.json

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
     "k_proj",
-    "up_proj",
+    "down_proj",
+    "o_proj",
     "v_proj",
-    "gate_proj",
-    "down_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9723223850d1699b4a267110a3bd2e13d48ba0ce2e231a4eebfb026c08f794
+oid sha256:ca82dee9989875690883d45341c662ae3c462780baa2e32fc0558beac6a23303
 size 83945296

runs/Nov04_21-47-10_d08e16fde931/events.out.tfevents.1730756831.d08e16fde931.616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7292951af5f8870a1c0e8e9502f30d047ddc788fbbe4e60f266a3bdf06fc346
+size 216734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a85db06373a484e891e0b612e00e391ff0be2ed59db2b3a337f7c3d000f5dcd
+oid sha256:84c00571f16f20957549a11b7999f2bd150abc60e2f944f5d9bb60e60c5b0558
 size 5496