FlamingNeuron/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/mayhem-sensory-0e-boffo/huggingface/runs/40p5ir7x) 
+[<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/mayhem-sensory-0e-boffo/huggingface/runs/ket3fh19) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
+    "up_proj",
     "down_proj",
-    "k_proj",
+    "o_proj",
     "v_proj",
     "gate_proj",
-    "up_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
-size 40
+oid sha256:b407df1b2973946b12fb32835ddfaa02ce7cdd2404d0d9eb34e7793e81f6047a
+size 167832240

runs/Apr17_16-53-37_87e046dd5b81/events.out.tfevents.1744908835.87e046dd5b81.443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab110bbb53c3b426c376d1ad9ef3eb4616f0106758f7f7c7c7266722b05af7b1
+size 29636

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9ff6d46096e8739e6c2af05bd3e589f5563d40a65df252cca2137f5fc2ce35
+oid sha256:a957fb8ff87a2ce8a9ae81eb92496286e52ccfe4c64ca3a983b6148e4134c5b4
 size 5688