Training in progress, epoch 1

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/akashmaggon/huggingface/runs/ibi7atcf) 
+[<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/akashmaggon/huggingface/runs/vwtu3tke) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -21,17 +21,17 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
-    "up_proj",
+    "k_proj",
     "o_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj"
+    "q_proj",
+    "up_proj",
+    "down_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:c8cf25926f5b8005fa5734ad40f82b08961959856a17925fe5000d235dc295de
-size 128524896
+oid sha256:e6fae620f21f6cae1290cf0283db75346782e254463ecf96246ed8e2476bb2d1
+size 256976504

runs/Sep29_12-38-34_a0f1a9a72185/events.out.tfevents.1759149522.a0f1a9a72185.5589.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f1ba5ad3522bb8e9bc5a6752a77e6241be493512278536fc08a720c54f76d6
+size 7326

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72391c1f63a15922731949f6f581aa53fa410546050aac164a1966c98b6658b
+oid sha256:d167512ad49d54237e571550e51eab74fa0434049cbcd33f0ce94702525bc0cc
 size 6225