Training in progress, step 100

README.md

@@ -28,7 +28,7 @@ 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/cneuralnets-ai4bharat/Nepali-distillation_2/runs/ghyna7eg) 
+[<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/cneuralnets-ai4bharat/Nepali-distillation_2/runs/0n5om7b9) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
+    "v_proj",
     "o_proj",
+    "q_proj",
     "down_proj",
+    "gate_proj",
     "up_proj",
-    "k_proj",
-    "v_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 sha256:88db4a88bed32ccd724066d9fc6aa9bfb39d168ed24e83983f15877d5e93688d
+oid sha256:d0483f95fd82730b4a237dc9ca4841dca1b1a363d1ff5c895d93698332a6ec13
 size 12208024

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b7cf9c11a2b335a36695efea2c34025c59d539e7c4abade27cc05d88892c0f
+oid sha256:9288a0289698ffd9d9383af723c4613ebae1553c4b98e2fe2571f151a5e40fd3
 size 6161