End of training

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/huggingface/huggingface/runs/n9cx8n8q)
+[<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/huggingface/huggingface/runs/w9teg96o)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -14,19 +14,22 @@
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head",
+    "embed_token"
+  ],
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "q_proj",
     "o_proj",
+    "down_proj",
+    "k_proj",
     "gate_proj",
+    "q_proj",
     "v_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953bde2ae844316ed0006dd66569ee5586906d07f4edda889d0161fa413f3614
-size 35237104
+oid sha256:4b9bd0c0ed65dabdc615b387d8d655f26034386215360a81f45907e55aed31f4
+size 579776696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629691662c2d795783ab20456c379ef99ae6bfc3e3a62380efd9fe367f14b2ae
+oid sha256:b0465fcd08c656bf6b3d567a372125b82206898f0644dbd3a98ab52ef5923068
 size 5496