Training in progress, step 50

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: number
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -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/3dsmile/huggingface/runs/jakraxed) 
+ 
 
 
 
@@ -35,8 +35,8 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.29.0
-- Transformers: 5.2.0
+- TRL: 0.29.1
+- Transformers: 5.4.0
 - Pytorch: 2.10.0+cu128
 - Datasets: 4.0.0
 - Tokenizers: 0.22.2

adapter_config.json

@@ -29,8 +29,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93da403f150557498a5ad0469603399c70725754a50e293f89efb676457d0fa5
+oid sha256:5aa82cf9717696a08251b642e581761d9bb0c73b0d3db1320b88a4fe30ee4f7a
 size 5071040

processor_config.json

@@ -1,6 +1,5 @@
 {
   "image_processor": {
-    "data_format": "channels_first",
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
@@ -10,7 +9,7 @@
       0.5,
       0.5
     ],
-    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_processor_type": "Qwen2VLImageProcessor",
     "image_std": [
       0.5,
       0.5,
@@ -28,8 +27,6 @@
   },
   "processor_class": "Qwen3VLProcessor",
   "video_processor": {
-    "data_format": "channels_first",
-    "default_to_square": true,
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab5119290ef739338f8821ed9a10f587abc0eb8c8ef9e9516369bbe2c814ea74
+oid sha256:1f9255623a6f7f550f0efc0716d29ab04e883c72e25f798bc07edaff9eb82b8a
 size 5649