Training in progress, step 100

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: Nepali_8b_8b_D1
 tags:
 - generated_from_trainer
-- unsloth
 - trl
 - sft
+- unsloth
 licence: license
 ---
 
@@ -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_1/runs/m8plqx9a) 
+[<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_1/runs/lbj2zyuq) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
+    "o_proj",
     "down_proj",
-    "up_proj",
-    "gate_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "gate_proj",
+    "up_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:b2b9e8bcdb50b035d659ae305ae7a76f3e732df2322245f1a4737c356dd96b5d
+oid sha256:26000ca560a40da178328e70f5afc6ab21fe4401c7084d5d70ad135d23c074c6
 size 21030376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f840e695c89979ae2739870738a39d637a7e3c68f2c9037d11d8febd3dd69c
+oid sha256:156354872c257a47d807d5011e33f80efa52f61c7f02155cd47d106f5cab1771
 size 6161