Training in progress, step 68

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: Qwen/Qwen2-VL-7B-instruct
+base_model: Qwen/Qwen2-VL-7B-Instruct
 library_name: transformers
 model_name: stage1_vision_adapter
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for stage1_vision_adapter
 
-This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-instruct).
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -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/deep-learning-rabbit/ft_qwen2vl/runs/4skzi688) 
+[<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/deep-learning-rabbit/ft_qwen2vl/runs/wvfrp5hv) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-instruct",
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -30,8 +30,8 @@
   "revision": null,
   "target_modules": [
     "qkv",
-    "proj",
     "fc2",
+    "proj",
     "fc1"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46378a9a6ae59c1fe5fccf629d8500240b5d199dd00b5964f48418914b36ef09
-size 21084048
+oid sha256:e6fa4254a9603c0a6cb64f5d5dec5d94ae7492eeadc8febee6dc1627578e91c1
+size 10558984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f6f0a8b577f676b134e0059a8a1396aa54ac2214c97784e1303bf790fae8c0
+oid sha256:c9bae46e0fda82bc971aa837250b68cfd017325f6fc15218e75556ad094b2cfe
 size 6289