Training in progress, step 100

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: manipuri_8b_8b_D2
 tags:
 - generated_from_trainer
-- sft
 - unsloth
 - trl
+- sft
 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/manipuri-distillation_2/runs/zors7j2n) 
+[<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/manipuri-distillation_2/runs/j49d6qfs) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -26,12 +26,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "gate_proj",
+    "v_proj",
+    "up_proj",
     "down_proj",
-    "o_proj",
     "q_proj",
-    "v_proj",
-    "up_proj"
+    "gate_proj",
+    "o_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 sha256:8d22466591b28a5e8687b6008c8f2f0f8caa8a039a828c54966936a58b3df52a
+oid sha256:b8971f9c64abfcee3609d879936d6430fe5315252ad6ca757cacbc973346a61d
 size 21030376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1d1b0f9008cc17a114a316ae8c31ef7a68ba88d24b41fb389d3fd5033a74cd
+oid sha256:6e5b654b0089657c1f1b641a44bed9c10d325aee2ca1c66a62cbfd0f8e66c8e6
 size 6161