Training in progress, step 5

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/ruoxue2-stony-brook-university/qwen2-vl-2b-person-30000-subject/runs/7cej549o) 
+[<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/ruoxue2-stony-brook-university/qwen2-vl-2b-person-30000-subject/runs/hlx5xg5l) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -19,16 +19,16 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "embed_tokens"
+    "embed_tokens",
+    "lm_head"
   ],
   "peft_type": "LORA",
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
-    "lm_head"
+    "v_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 sha256:1cc52d8f3914289818e74d9b58d7addb548c0b5a6f478468ecaea31912871d2c
-size 942780936
+oid sha256:fa60d5bc6a4488dc41f8630ec5819ef2c118885aad165be19bb9880ac14408ac
+size 937869552

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9571637ca1700c120f9f33d4bbe4e6461e570da8f784f608d68f3ab88576c3ca
+oid sha256:22bb9a6a08585b701878db8cdabba5e10cb5802697101f922352473da05e7d96
 size 5880