Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-4b-pt",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "out_proj",
+    "fc1",
+    "down_proj",
+    "lm_head",
+    "fc2",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9eef0263f5d5e7ab01b8d38ae8b0fca9dd139a25ac12cb8bbeadb7277e7555
+size 1513565088

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "\n{% set image_token = '<start_of_image>' %} {# Standard PaliGemma image token #}\n{% for message in messages %}\n    {%- if message['role'] == 'user' -%}\n        {{ 'user\n' }}\n        {#- Check if there are image content parts -#}\n        {%- set has_images = message['content'] | selectattr('type', 'equalto', 'image') | list | length > 0 %}\n        {#- Extract text content -#}\n        {%- set text_content = message['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | join(' ') %}\n\n        {#- If images exist, typically place the image token(s) first, followed by a newline #}\n        {{ image_token + '\n' }} {# Add the image placeholder token #}\n        {{- text_content -}} {# Add the text content #}\n\n    {%- elif message['role'] == 'assistant' or message['role'] == 'model' -%}\n        {{ 'model\n' }}\n        {#- Extract text content for the model's response -#}\n        {%- set text_content = message['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | join(' ') %}\n        {{- text_content -}}\n\n    {%- else -%}\n        {# Optional: Handle unexpected roles, maybe just print role and content #}\n        {{ message['role'] + '\n' }}\n        {%- for content in message['content'] -%}\n            {%- if content['type'] == 'text' %}{{ content['text'] }}{% endif -%}\n            {%- if content['type'] == 'image' %}{{ image_token }}{% endif -%}\n        {%- endfor -%}\n    {%- endif -%}\n    {{ '\n' }} {# Add a newline to separate turns #}\n{% endfor %}\n{%- if add_generation_prompt %}\n    {{ 'model\n' }} {# Prompt for the model to generate its response #}\n{% endif %}\n"
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "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": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

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

runs/Apr07_16-18-29_40616/events.out.tfevents.1744010321.40616.240792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07361cb8ae7238b4436c8d9229bbc1821f437c1a053114d673bcea3985a1f315
+size 20067

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
+size 33384722

tokenizer.model

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

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36427d4172ae4c5e279b663c8c9e82215ab962da6aaca5e8b0e9430df10e244
+size 5624