Training in progress, epoch 0

config.json

@@ -28,9 +28,48 @@
   },
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
-  "tie_word_embeddings": true,
+  "text_config": {
+    "architectures": [
+      "Qwen2VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_vl_text",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.52.0.dev0",
   "use_cache": false,
   "use_sliding_window": false,
   "video_token_id": 151656,
@@ -41,6 +80,7 @@
     "hidden_size": 1536,
     "in_channels": 3,
     "in_chans": 3,
+    "initializer_range": 0.02,
     "mlp_ratio": 4,
     "model_type": "qwen2_vl",
     "num_heads": 16,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937f773eac63060c6ea90f13c9b425c9ede4ad846a4b7ff338a687e478ccc588
-size 3269845616
+oid sha256:d28a886119824ad565f6c16158e46d575945133d36e77f139bd430d5725ee8cc
+size 3269852072

tokenizer_config.json

@@ -130,7 +130,6 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf1ceb89bbd5d14abd1325fdd46e1ef1c3b8617db96d1d6d4c935e7caeff3a7
+oid sha256:c96d362fcf26f2b05f2a797bef3d6079376660bbbea529242c6249f3aeeba8de
 size 7096