Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
+  "base_model_name_or_path": "google/gemma-3-4b-pt",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,10 +26,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
+    "o_proj",
     "v_proj",
-    "o_proj"
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0ca6e1242cfb7e27adc7a12b37d824ff5fc881bd42b36f867340b6e8ecff7d
-size 1274194024
+oid sha256:b8784e43e9af5ca4935b6ed46947b19e5584d6ec7e2975f795a2fcf218148b59
+size 2732673600

added_tokens.json

@@ -1,24 +1,3 @@
 {
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
+  "<image_soft_token>": 262144
 }

chat_template.jinja

@@ -1,7 +1,47 @@
-{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
-You are a helpful assistant.<|im_end|>
-{% endif %}<|im_start|>{{ message['role'] }}
-{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
-{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
-{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
-{% endif %}
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

preprocessor_config.json

@@ -1,29 +1,29 @@
 {
-  "do_convert_rgb": true,
+  "do_convert_rgb": null,
   "do_normalize": true,
+  "do_pan_and_scan": null,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
+    0.5,
+    0.5,
+    0.5
   ],
-  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
   "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
+    0.5,
+    0.5,
+    0.5
   ],
-  "max_pixels": 12845056,
-  "merge_size": 2,
-  "min_pixels": 3136,
-  "patch_size": 14,
-  "processor_class": "Qwen2_5_VLProcessor",
-  "resample": 3,
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "longest_edge": 12845056,
-    "shortest_edge": 3136
-  },
-  "temporal_patch_size": 2
+    "height": 896,
+    "width": 896
+  }
 }

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -1,28 +1,30 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<eos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "image_token": "<image_soft_token>",
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108be8466113b809cb350fde467c9edac456f64f2b372714a251656b385879d4
+oid sha256:b1c6794ee4ee13b41bada75e127b4d953fd4de86c90d9fe7d3ae8e5d01dd9522
 size 5688