CalebMaresca/llama381binstruct_summarize_short

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/ccm7752-new-york-university/huggingface/runs/2czjcp4x) 
+[<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/ccm7752-new-york-university/huggingface/runs/c3u7ri20) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "gate_proj",
     "v_proj",
-    "o_proj",
     "k_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
-    "q_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
-size 40
+oid sha256:373fc5b30d83ee59085f4d5e1cfc5d867ed18826d6f3a3ae8121b00f3ad99fd1
+size 167832240

runs/Mar07_21-20-43_14748e5d6bb0/events.out.tfevents.1741382447.14748e5d6bb0.442.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c0a2580ce02b1ff58c3c143c3f125d531aca23e00ad10bd1b5d7a0b1a442b6
+size 26945

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6738f37260caa94b22bb93b436e3e16b954b19836ee365c8296eefe6569d01fd
+oid sha256:02da369ac6aeb389e67e6e60fef647b028a5063868f2700de79a1d8191ba6f64
 size 5624