Training in progress, step 5

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: Qwen/Qwen2.5-VL-7B-Instruct
+base_model: Qwen/Qwen2.5-VL-3B-Instruct
 library_name: transformers
 model_name: checkpoints
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for checkpoints
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -29,8 +29,88 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "model.language_model.layers.27.self_attn.o_proj",
+    "model.language_model.layers.26.self_attn.k_proj",
+    "model.visual.merger.mlp.2",
+    "model.language_model.layers.24.self_attn.k_proj",
+    "model.language_model.layers.27.self_attn.v_proj",
+    "model.language_model.layers.16.self_attn.q_proj",
+    "model.language_model.layers.20.self_attn.q_proj",
+    "model.language_model.layers.31.self_attn.k_proj",
+    "model.language_model.layers.29.self_attn.o_proj",
+    "model.language_model.layers.28.self_attn.o_proj",
+    "model.language_model.layers.18.self_attn.o_proj",
+    "model.language_model.layers.33.self_attn.k_proj",
+    "model.language_model.layers.23.self_attn.k_proj",
+    "model.language_model.layers.22.self_attn.v_proj",
+    "model.language_model.layers.29.self_attn.q_proj",
+    "model.language_model.layers.20.self_attn.v_proj",
+    "model.language_model.layers.34.self_attn.o_proj",
+    "model.language_model.layers.16.self_attn.v_proj",
+    "model.language_model.layers.18.self_attn.k_proj",
+    "model.language_model.layers.28.self_attn.v_proj",
+    "model.language_model.layers.26.self_attn.q_proj",
+    "model.language_model.layers.34.self_attn.k_proj",
+    "model.language_model.layers.31.self_attn.v_proj",
+    "model.language_model.layers.35.self_attn.k_proj",
+    "model.language_model.layers.25.self_attn.q_proj",
+    "model.language_model.layers.16.self_attn.o_proj",
+    "model.language_model.layers.34.self_attn.v_proj",
+    "model.language_model.layers.23.self_attn.v_proj",
+    "model.visual.merger.mlp.0",
+    "model.language_model.layers.33.self_attn.v_proj",
+    "model.language_model.layers.19.self_attn.q_proj",
+    "model.language_model.layers.21.self_attn.v_proj",
+    "model.language_model.layers.28.self_attn.q_proj",
+    "model.language_model.layers.19.self_attn.o_proj",
+    "model.language_model.layers.26.self_attn.v_proj",
+    "model.language_model.layers.19.self_attn.k_proj",
+    "model.language_model.layers.33.self_attn.q_proj",
+    "model.language_model.layers.34.self_attn.q_proj",
+    "model.language_model.layers.30.self_attn.q_proj",
+    "model.language_model.layers.31.self_attn.q_proj",
+    "model.language_model.layers.29.self_attn.v_proj",
+    "model.language_model.layers.20.self_attn.o_proj",
+    "model.language_model.layers.22.self_attn.o_proj",
+    "model.language_model.layers.23.self_attn.o_proj",
+    "model.language_model.layers.17.self_attn.o_proj",
+    "model.language_model.layers.32.self_attn.o_proj",
+    "model.language_model.layers.28.self_attn.k_proj",
+    "model.language_model.layers.24.self_attn.v_proj",
+    "model.language_model.layers.21.self_attn.o_proj",
+    "model.language_model.layers.19.self_attn.v_proj",
+    "model.language_model.layers.17.self_attn.k_proj",
+    "model.language_model.layers.26.self_attn.o_proj",
+    "model.language_model.layers.29.self_attn.k_proj",
+    "model.language_model.layers.30.self_attn.v_proj",
+    "model.language_model.layers.22.self_attn.q_proj",
+    "model.language_model.layers.31.self_attn.o_proj",
+    "model.language_model.layers.32.self_attn.q_proj",
+    "model.language_model.layers.32.self_attn.v_proj",
+    "model.language_model.layers.30.self_attn.k_proj",
+    "model.language_model.layers.25.self_attn.k_proj",
+    "model.language_model.layers.27.self_attn.k_proj",
+    "model.language_model.layers.18.self_attn.v_proj",
+    "model.language_model.layers.23.self_attn.q_proj",
+    "model.language_model.layers.18.self_attn.q_proj",
+    "model.language_model.layers.20.self_attn.k_proj",
+    "model.language_model.layers.17.self_attn.q_proj",
+    "model.language_model.layers.27.self_attn.q_proj",
+    "model.language_model.layers.35.self_attn.o_proj",
+    "model.language_model.layers.35.self_attn.v_proj",
+    "model.language_model.layers.21.self_attn.k_proj",
+    "model.language_model.layers.25.self_attn.v_proj",
+    "model.language_model.layers.22.self_attn.k_proj",
+    "model.language_model.layers.35.self_attn.q_proj",
+    "model.language_model.layers.30.self_attn.o_proj",
+    "model.language_model.layers.24.self_attn.o_proj",
+    "model.language_model.layers.17.self_attn.v_proj",
+    "model.language_model.layers.32.self_attn.k_proj",
+    "model.language_model.layers.25.self_attn.o_proj",
+    "model.language_model.layers.21.self_attn.q_proj",
+    "model.language_model.layers.24.self_attn.q_proj",
+    "model.language_model.layers.16.self_attn.k_proj",
+    "model.language_model.layers.33.self_attn.o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af0bfcaeef931a21f4a0efca4e04c515f38ae9d88ddcbaba99e604eb88d5a385
-size 5062776
+oid sha256:e16f24e6448a1cd7abe28c347acc69a0d03e73a5ff6c1a6ef142885f7c0dcace
+size 8773032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee49500b607025fadc055d7d9b83b5de1dedb3698f7682d7d84bb78569bcda3
+oid sha256:19dde3eac01ad7a1ec7a88defa611ee1d129ecd272cdc27e71cd6b93ae569476
 size 5585