Training in progress, step 50

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "up_proj",
     "v_proj",
     "q_proj",
+    "up_proj",
+    "k_proj",
     "gate_proj",
-    "k_proj"
+    "o_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7f4db7bc95b8b810d8dd8a480790dd5edc7dab753540020f24153ea90849d6
-size 465602056
+oid sha256:a7eda4d3c5a49cb6a6e4fd0cafc1d8d40c95aea20b19eb2b2088888cd5021d6c
+size 465605896

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 1003520,
+      "shortest_edge": 200704
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e71421c5d4e5b01c8be19a0ed8c9b91f9fd257ed0b17b39182561f48376ca9
-size 19989441
+oid sha256:547a658514e17c019c67b63c1c8ad0b57239d96b04f20cf1fa421827961631a5
+size 19989511

tokenizer_config.json

@@ -10,6 +10,8 @@
   "errors": "replace",
   "image_token": "<|image_pad|>",
   "is_local": false,
+  "max_pixels": 1003520,
+  "min_pixels": 200704,
   "model_max_length": 262144,
   "model_specific_special_tokens": {
     "audio_bos_token": "<|audio_start|>",
@@ -22,6 +24,7 @@
   },
   "pad_token": "<|endoftext|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",
   "unk_token": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a052334b997c70c9cf37a68048837b5963c1cfe3ed4ba0cbc019c9637e06afb5
+oid sha256:5a7e51573c2bab70b9769f9dd729f213e8b46816dd29dad43560afaea488b0ab
 size 6904