Upload folder using huggingface_hub

.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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</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
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "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 %}"
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/mnt/localssd/models/Qwen2.5-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "model_type": "qwen2_5_vl",
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.49.0",
+  "use_cache": false
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d235f8fb105c7eaa7f483e4e7c35dde0502dff8d8a1198a4f6d2f9232b0df5c2
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f062cc6d1075638cd9e21e4ffc977cbce1d109fee1d9ec40e4f935ce3924747c
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3beb88b676758d158434bc4f31291a43609dccf9b5a3a72eb3d926e6d85175
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fdffe3562c0c9406204f897e22ab6ac2fe06325608ab38316a004897f66276
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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|>"
+  ],
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,793 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.857142857142857,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "advantages_interactive_phase": 0.0,
+      "clip_ratio": 0.0018634893640410155,
+      "clue_civilian_adjusted_reward_mean": 0.05918297689717122,
+      "clue_civilian_advantage_adjustment": -0.03942813421393988,
+      "clue_civilian_baseline": 0.03942813421393988,
+      "clue_civilian_raw_reward_mean": 0.09861111111111111,
+      "clue_civilian_votes_avg": 0.7916666666666666,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 1.75,
+      "clue_spy_adjusted_reward": -0.17754892994163418,
+      "clue_spy_advantage_adjustment": 0.11828440339169918,
+      "clue_spy_baseline": -0.11828440339169917,
+      "clue_spy_raw_reward": -0.29583333333333334,
+      "clue_spy_votes_received": 3.75,
+      "clue_suspicion_potential_psi": 2.9583333333333335,
+      "clue_total_valid_votes": 6.125,
+      "completion_length": 423.421875,
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.7974071502685547,
+      "kl": 0.0005228519439697266,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 0.0001,
+      "loss_interactive_phase": 7.833498330001021e-05,
+      "reward": 0.20273437504686748,
+      "reward_original_clue_max": 0.17544670874508858,
+      "reward_original_clue_mean": 1.8746987252502012e-10,
+      "reward_original_clue_min": -0.30561266275121457,
+      "reward_original_clue_std": 0.19967558891689363,
+      "reward_original_decision_max": 1.7925,
+      "reward_original_decision_mean": 0.8109375000000001,
+      "reward_original_decision_min": -0.5512499999999999,
+      "reward_original_decision_std": 0.9495301425690702,
+      "reward_original_overall_mean": 0.40546875009373495,
+      "reward_original_overall_std": 0.9913047843321547,
+      "reward_std": 0.9633595642022483,
+      "step": 1
+    },
+    {
+      "advantages_interactive_phase": -8.556526154279709e-09,
+      "clip_ratio": 0.002335783210583031,
+      "clue_civilian_adjusted_reward_mean": -0.006861256941324185,
+      "clue_civilian_advantage_adjustment": -0.05963903471910197,
+      "clue_civilian_baseline": 0.05963903471910197,
+      "clue_civilian_raw_reward_mean": 0.052777777777777785,
+      "clue_civilian_votes_avg": 1.2916666666666667,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 1.25,
+      "clue_spy_adjusted_reward": 0.02058376732518095,
+      "clue_spy_advantage_adjustment": 0.17891710065851432,
+      "clue_spy_baseline": -0.1789171006585143,
+      "clue_spy_raw_reward": -0.15833333333333335,
+      "clue_spy_votes_received": 2.875,
+      "clue_suspicion_potential_psi": 1.5833333333333335,
+      "clue_total_valid_votes": 6.75,
+      "completion_length": 285.25,
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.8082046508789062,
+      "kl": 0.0005023479461669922,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.0001,
+      "loss_interactive_phase": 7.536940393038094e-05,
+      "reward": 0.10300780800306249,
+      "reward_original_clue_max": 0.19334198559682764,
+      "reward_original_clue_mean": -8.746979013492251e-10,
+      "reward_original_clue_min": -0.29009201414260616,
+      "reward_original_clue_std": 0.19705596697482888,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.4120312500000001,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.229970198569032,
+      "reward_original_overall_mean": 0.20601562456265113,
+      "reward_original_overall_std": 1.0020081985538272,
+      "reward_std": 0.8735654869946374,
+      "step": 2
+    },
+    {
+      "advantages_interactive_phase": 4.6566128730773926e-08,
+      "clip_ratio": 0.0036435330111999065,
+      "clue_civilian_adjusted_reward_mean": 0.001498594028077338,
+      "clue_civilian_advantage_adjustment": -0.029056961527478224,
+      "clue_civilian_baseline": 0.029056961527478227,
+      "clue_civilian_raw_reward_mean": 0.030555555555555565,
+      "clue_civilian_votes_avg": 1.7083333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": -0.004495785647248764,
+      "clue_spy_advantage_adjustment": 0.08717088101941789,
+      "clue_spy_baseline": -0.08717088101941789,
+      "clue_spy_raw_reward": -0.09166666666666666,
+      "clue_spy_votes_received": 2.625,
+      "clue_suspicion_potential_psi": 0.9166666666666666,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 446.484375,
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.554112195968628,
+      "kl": 0.0005366802215576172,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.0004,
+      "loss_interactive_phase": 0.00043194927275180817,
+      "reward": 0.057773460560375856,
+      "reward_original_clue_max": 0.21058345074729162,
+      "reward_original_clue_mean": -8.907541869905555e-10,
+      "reward_original_clue_min": -0.3764207294816445,
+      "reward_original_clue_std": 0.23299249148130835,
+      "reward_original_decision_max": 1.7925000000000002,
+      "reward_original_decision_mean": 0.23109375000000007,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.085506600498274,
+      "reward_original_overall_mean": 0.11554687455462298,
+      "reward_original_overall_std": 0.9672326088884007,
+      "reward_std": 1.0181387857068844,
+      "step": 3
+    },
+    {
+      "advantages_interactive_phase": 2.9976945370435715e-09,
+      "clip_ratio": 0.002281623412272893,
+      "clue_civilian_adjusted_reward_mean": 0.03536497522484616,
+      "clue_civilian_advantage_adjustment": -0.07713502477515387,
+      "clue_civilian_baseline": 0.07713502477515385,
+      "clue_civilian_raw_reward_mean": 0.11250000000000002,
+      "clue_civilian_votes_avg": 1.125,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.10609493015462855,
+      "clue_spy_advantage_adjustment": 0.23140506984537143,
+      "clue_spy_baseline": -0.23140506984537143,
+      "clue_spy_raw_reward": -0.3375,
+      "clue_spy_votes_received": 4.5,
+      "clue_suspicion_potential_psi": 3.3750000000000004,
+      "clue_total_valid_votes": 7.875,
+      "completion_length": 280.6484375,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.7840830087661743,
+      "kl": 0.0005328655242919922,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.0002,
+      "loss_interactive_phase": 0.00016839916224853368,
+      "reward": 0.24937500121884168,
+      "reward_original_clue_max": 0.15669697422618992,
+      "reward_original_clue_mean": -1.1200225196079938e-09,
+      "reward_original_clue_min": -0.2575575776689137,
+      "reward_original_clue_std": 0.16720348057350995,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 0.9975,
+      "reward_original_decision_min": -0.5512499999999999,
+      "reward_original_decision_std": 1.3083811300653312,
+      "reward_original_overall_mean": 0.4987499994399888,
+      "reward_original_overall_std": 1.2103413395713034,
+      "reward_std": 0.9428560946201414,
+      "step": 4
+    },
+    {
+      "advantages_interactive_phase": 1.3969838619232178e-08,
+      "clip_ratio": 0.0024555539712309837,
+      "clue_civilian_adjusted_reward_mean": 0.02328965785126698,
+      "clue_civilian_advantage_adjustment": -0.08087700881539968,
+      "clue_civilian_baseline": 0.08087700881539968,
+      "clue_civilian_raw_reward_mean": 0.10416666666666666,
+      "clue_civilian_votes_avg": 1.1250000000000002,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.375,
+      "clue_spy_adjusted_reward": -0.06986897416721828,
+      "clue_spy_advantage_adjustment": 0.2426310258327818,
+      "clue_spy_baseline": -0.24263102583278173,
+      "clue_spy_raw_reward": -0.3125,
+      "clue_spy_votes_received": 4.25,
+      "clue_suspicion_potential_psi": 3.125,
+      "clue_total_valid_votes": 7.625,
+      "completion_length": 413.890625,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.3878099918365479,
+      "kl": 0.0005576610565185547,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.0005,
+      "loss_interactive_phase": 0.000517467160079832,
+      "reward": 0.23226563194658076,
+      "reward_original_clue_max": 0.21555571150385638,
+      "reward_original_clue_mean": -1.533543309700791e-10,
+      "reward_original_clue_min": -0.37003479506476167,
+      "reward_original_clue_std": 0.23001506159699,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.9290625000000001,
+      "reward_original_decision_min": -0.05249999999999988,
+      "reward_original_decision_std": 0.9008207170594332,
+      "reward_original_overall_mean": 0.4645312499233229,
+      "reward_original_overall_std": 1.0956622262468276,
+      "reward_std": 0.8819076667065591,
+      "step": 5
+    },
+    {
+      "advantages_interactive_phase": 2.593151293694973e-08,
+      "clip_ratio": 0.0022167734132381156,
+      "clue_civilian_adjusted_reward_mean": -0.05706479682332055,
+      "clue_civilian_advantage_adjustment": -0.06678701904554278,
+      "clue_civilian_baseline": 0.06678701904554278,
+      "clue_civilian_raw_reward_mean": 0.009722222222222222,
+      "clue_civilian_votes_avg": 1.8333333333333335,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.375,
+      "clue_spy_adjusted_reward": 0.1711943907141766,
+      "clue_spy_advantage_adjustment": 0.20036105738084325,
+      "clue_spy_baseline": -0.20036105738084325,
+      "clue_spy_raw_reward": -0.02916666666666667,
+      "clue_spy_votes_received": 2.125,
+      "clue_suspicion_potential_psi": 0.2916666666666667,
+      "clue_total_valid_votes": 7.625,
+      "completion_length": 292.6640625,
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.8046058416366577,
+      "kl": 0.0005428791046142578,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.0001,
+      "loss_interactive_phase": 6.28332345513627e-05,
+      "reward": 0.0071484504810199224,
+      "reward_original_clue_max": 0.19892967100999515,
+      "reward_original_clue_mean": 6.105373758641397e-11,
+      "reward_original_clue_min": -0.27271583510110275,
+      "reward_original_clue_std": 0.17836741852431973,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.02859375000000007,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.325891362422743,
+      "reward_original_overall_mean": 0.014296875030526908,
+      "reward_original_overall_std": 1.0072236613283885,
+      "reward_std": 0.8759148769503003,
+      "step": 6
+    },
+    {
+      "advantages_interactive_phase": 2.60770320892334e-08,
+      "clip_ratio": 0.002304785492015071,
+      "clue_civilian_adjusted_reward_mean": 0.03881056627857306,
+      "clue_civilian_advantage_adjustment": -0.07091165594364918,
+      "clue_civilian_baseline": 0.07091165594364919,
+      "clue_civilian_raw_reward_mean": 0.10972222222222223,
+      "clue_civilian_votes_avg": 0.9583333333333333,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.625,
+      "clue_spy_adjusted_reward": -0.11643170495870281,
+      "clue_spy_advantage_adjustment": 0.2127349617079639,
+      "clue_spy_baseline": -0.2127349617079639,
+      "clue_spy_raw_reward": -0.3291666666666667,
+      "clue_spy_votes_received": 4.25,
+      "clue_suspicion_potential_psi": 3.291666666666667,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 464.40625,
+      "epoch": 1.0,
+      "grad_norm": 1.4001574516296387,
+      "kl": 0.0007524490356445312,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0001,
+      "loss_interactive_phase": 0.00014802347868680954,
+      "reward": 0.23695313765582962,
+      "reward_original_clue_max": 0.13752778510142732,
+      "reward_original_clue_mean": -1.5307459100191018e-09,
+      "reward_original_clue_min": -0.27099875595069856,
+      "reward_original_clue_std": 0.1675473646082055,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 0.9478125000000002,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.4679322374979336,
+      "reward_original_overall_mean": 0.47390624923462715,
+      "reward_original_overall_std": 1.2051032936983774,
+      "reward_std": 1.137074120661292,
+      "step": 7
+    },
+    {
+      "advantages_interactive_phase": 1.0943040251731873e-08,
+      "clip_ratio": 0.0022679592002532445,
+      "clue_civilian_adjusted_reward_mean": -0.016031408855832558,
+      "clue_civilian_advantage_adjustment": -0.07714251996694366,
+      "clue_civilian_baseline": 0.07714251996694367,
+      "clue_civilian_raw_reward_mean": 0.06111111111111111,
+      "clue_civilian_votes_avg": 1.4166666666666665,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": 0.048094219325201096,
+      "clue_spy_advantage_adjustment": 0.23142755265853443,
+      "clue_spy_baseline": -0.23142755265853443,
+      "clue_spy_raw_reward": -0.18333333333333335,
+      "clue_spy_votes_received": 3.25,
+      "clue_suspicion_potential_psi": 1.8333333333333335,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 325.875,
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.8383725881576538,
+      "kl": 0.0009479522705078125,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.0,
+      "loss_interactive_phase": 3.266143448854564e-05,
+      "reward": 0.12867188001887664,
+      "reward_original_clue_max": 0.1717749026924985,
+      "reward_original_clue_mean": -1.8105741430868988e-09,
+      "reward_original_clue_min": -0.29723497592984766,
+      "reward_original_clue_std": 0.1852377677192031,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.5146875,
+      "reward_original_decision_min": -0.4762499999999999,
+      "reward_original_decision_std": 1.192409132355428,
+      "reward_original_overall_mean": 0.257343749094713,
+      "reward_original_overall_std": 1.0899296054191416,
+      "reward_std": 0.8533073135439071,
+      "step": 8
+    },
+    {
+      "advantages_interactive_phase": 8.568167686462402e-08,
+      "clip_ratio": 0.0023259197478182614,
+      "clue_civilian_adjusted_reward_mean": -0.029266771100525505,
+      "clue_civilian_advantage_adjustment": -0.050100104433858844,
+      "clue_civilian_baseline": 0.05010010443385884,
+      "clue_civilian_raw_reward_mean": 0.020833333333333336,
+      "clue_civilian_votes_avg": 1.75,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.125,
+      "clue_spy_adjusted_reward": 0.08780030876920582,
+      "clue_spy_advantage_adjustment": 0.1503003087692058,
+      "clue_spy_baseline": -0.1503003087692058,
+      "clue_spy_raw_reward": -0.06250000000000003,
+      "clue_spy_votes_received": 2.375,
+      "clue_suspicion_potential_psi": 0.6250000000000001,
+      "clue_total_valid_votes": 7.625,
+      "completion_length": 473.21875,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 1.8215115070343018,
+      "kl": 0.001842498779296875,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 0.0001,
+      "loss_interactive_phase": 9.192087281917338e-05,
+      "reward": 0.026601605057565272,
+      "reward_original_clue_max": 0.24694495407103054,
+      "reward_original_clue_mean": -1.1330926750260234e-09,
+      "reward_original_clue_min": -0.3384114164023503,
+      "reward_original_clue_std": 0.2282574592500581,
+      "reward_original_decision_max": 1.6425,
+      "reward_original_decision_mean": 0.10640624999999998,
+      "reward_original_decision_min": -0.9750000000000001,
+      "reward_original_decision_std": 1.0511145404438063,
+      "reward_original_overall_mean": 0.05320312443345368,
+      "reward_original_overall_std": 0.9558180190214073,
+      "reward_std": 0.9456161666457135,
+      "step": 9
+    },
+    {
+      "advantages_interactive_phase": 1.932494342327118e-08,
+      "clip_ratio": 0.002800417976686731,
+      "clue_civilian_adjusted_reward_mean": 0.06457984112349752,
+      "clue_civilian_advantage_adjustment": -0.08264238109872472,
+      "clue_civilian_baseline": 0.08264238109872472,
+      "clue_civilian_raw_reward_mean": 0.14722222222222223,
+      "clue_civilian_votes_avg": 0.8333333333333334,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.125,
+      "clue_spy_adjusted_reward": -0.19373953509873437,
+      "clue_spy_advantage_adjustment": 0.24792713156793234,
+      "clue_spy_baseline": -0.24792713156793234,
+      "clue_spy_raw_reward": -0.4416666666666667,
+      "clue_spy_votes_received": 5.25,
+      "clue_suspicion_potential_psi": 4.416666666666666,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 306.078125,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7268203496932983,
+      "kl": 0.0027332305908203125,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.0004,
+      "loss_interactive_phase": 0.0004191627958789468,
+      "reward": 0.3335156339294566,
+      "reward_original_clue_max": 0.1670845851156116,
+      "reward_original_clue_mean": -2.9320604520710614e-09,
+      "reward_original_clue_min": -0.324274029989809,
+      "reward_original_clue_std": 0.200344125199865,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.3340625,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.3970003107878997,
+      "reward_original_overall_mean": 0.6670312485339698,
+      "reward_original_overall_std": 1.2634816915242302,
+      "reward_std": 1.0045614689811284,
+      "step": 10
+    },
+    {
+      "advantages_interactive_phase": 2.8870999813079834e-08,
+      "clip_ratio": 0.00239886613417184,
+      "clue_civilian_adjusted_reward_mean": -0.03352536121522622,
+      "clue_civilian_advantage_adjustment": -0.07658091677078177,
+      "clue_civilian_baseline": 0.07658091677078177,
+      "clue_civilian_raw_reward_mean": 0.043055555555555555,
+      "clue_civilian_votes_avg": 1.5833333333333337,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.375,
+      "clue_spy_adjusted_reward": 0.10057607587887998,
+      "clue_spy_advantage_adjustment": 0.2297427425455467,
+      "clue_spy_baseline": -0.2297427425455467,
+      "clue_spy_raw_reward": -0.12916666666666668,
+      "clue_spy_votes_received": 2.875,
+      "clue_suspicion_potential_psi": 1.2916666666666667,
+      "clue_total_valid_votes": 7.625,
+      "completion_length": 467.125,
+      "epoch": 1.5714285714285714,
+      "grad_norm": 1.5876327753067017,
+      "kl": 0.005084991455078125,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 0.0001,
+      "loss_interactive_phase": 9.683447569841519e-05,
+      "reward": 0.08660157645007502,
+      "reward_original_clue_max": 0.2384874901490317,
+      "reward_original_clue_mean": -1.941699663467883e-09,
+      "reward_original_clue_min": -0.32503768153123147,
+      "reward_original_clue_std": 0.21459404366620968,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.34640625000000014,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.2287494798437995,
+      "reward_original_overall_mean": 0.17320312402915022,
+      "reward_original_overall_std": 1.041561342088921,
+      "reward_std": 0.9884878430806314,
+      "step": 11
+    },
+    {
+      "advantages_interactive_phase": -5.296897143125534e-09,
+      "clip_ratio": 0.002376218224526383,
+      "clue_civilian_adjusted_reward_mean": 0.00989814147293805,
+      "clue_civilian_advantage_adjustment": -0.07760185852706196,
+      "clue_civilian_baseline": 0.07760185852706196,
+      "clue_civilian_raw_reward_mean": 0.0875,
+      "clue_civilian_votes_avg": 1.125,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.875,
+      "clue_spy_adjusted_reward": -0.029694428721677178,
+      "clue_spy_advantage_adjustment": 0.23280557127832285,
+      "clue_spy_baseline": -0.23280557127832285,
+      "clue_spy_raw_reward": -0.2625,
+      "clue_spy_votes_received": 3.75,
+      "clue_suspicion_potential_psi": 2.6249999999999996,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 299.2109375,
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.7784315943717957,
+      "kl": 0.006061553955078125,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.0003,
+      "loss_interactive_phase": 0.0003181805368512869,
+      "reward": 0.18867187208262254,
+      "reward_original_clue_max": 0.18385065628194514,
+      "reward_original_clue_mean": -1.0757157562716474e-09,
+      "reward_original_clue_min": -0.25198658164133986,
+      "reward_original_clue_std": 0.17365687301414184,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.7546875000000002,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.321324126308723,
+      "reward_original_overall_mean": 0.3773437494621422,
+      "reward_original_overall_std": 1.1002093373019268,
+      "reward_std": 0.9209775834420707,
+      "step": 12
+    },
+    {
+      "advantages_interactive_phase": 3.91155481338501e-08,
+      "clip_ratio": 0.0026791511772898957,
+      "clue_civilian_adjusted_reward_mean": 0.013927967676285829,
+      "clue_civilian_advantage_adjustment": -0.08746092121260307,
+      "clue_civilian_baseline": 0.08746092121260306,
+      "clue_civilian_raw_reward_mean": 0.1013888888888889,
+      "clue_civilian_votes_avg": 1.0833333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.625,
+      "clue_spy_adjusted_reward": -0.04178390831845199,
+      "clue_spy_advantage_adjustment": 0.2623827583482147,
+      "clue_spy_baseline": -0.2623827583482147,
+      "clue_spy_raw_reward": -0.3041666666666667,
+      "clue_spy_votes_received": 4.125,
+      "clue_suspicion_potential_psi": 3.0416666666666665,
+      "clue_total_valid_votes": 7.375,
+      "completion_length": 467.640625,
+      "epoch": 1.8571428571428572,
+      "grad_norm": 1.3934693336486816,
+      "kl": 0.01044464111328125,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 0.0004,
+      "loss_interactive_phase": 0.00038093607872724533,
+      "reward": 0.22371095672717445,
+      "reward_original_clue_max": 0.20029288375025087,
+      "reward_original_clue_mean": -1.3223986259323917e-09,
+      "reward_original_clue_min": -0.29481549105908367,
+      "reward_original_clue_std": 0.19133661945499214,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 0.89484375,
+      "reward_original_decision_min": -0.825,
+      "reward_original_decision_std": 1.310055180080139,
+      "reward_original_overall_mean": 0.44742187433880076,
+      "reward_original_overall_std": 1.1436246949289457,
+      "reward_std": 1.106334858529479,
+      "step": 13
+    },
+    {
+      "advantages_interactive_phase": 3.2247044146060944e-08,
+      "clip_ratio": 0.0023656768607906997,
+      "clue_civilian_adjusted_reward_mean": -0.049655365351200347,
+      "clue_civilian_advantage_adjustment": -0.07048869868453368,
+      "clue_civilian_baseline": 0.0704886986845337,
+      "clue_civilian_raw_reward_mean": 0.02083333333333334,
+      "clue_civilian_votes_avg": 1.5000000000000002,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 1.375,
+      "clue_spy_adjusted_reward": 0.14896609350806483,
+      "clue_spy_advantage_adjustment": 0.21146609350806483,
+      "clue_spy_baseline": -0.21146609350806483,
+      "clue_spy_raw_reward": -0.06249999999999999,
+      "clue_spy_votes_received": 2.125,
+      "clue_suspicion_potential_psi": 0.625,
+      "clue_total_valid_votes": 6.625,
+      "completion_length": 288.5859375,
+      "epoch": 2.0,
+      "grad_norm": 0.8066102266311646,
+      "kl": 0.0111846923828125,
+      "learning_rate": 5e-06,
+      "loss": 0.0006,
+      "loss_interactive_phase": 0.000611778799793683,
+      "reward": 0.025898453464426104,
+      "reward_original_clue_max": 0.26242470366338927,
+      "reward_original_clue_mean": -6.363840600320803e-10,
+      "reward_original_clue_min": -0.2729685698360408,
+      "reward_original_clue_std": 0.20724784514294434,
+      "reward_original_decision_max": 1.0950000000000002,
+      "reward_original_decision_mean": 0.10359375000000007,
+      "reward_original_decision_min": -0.4762499999999999,
+      "reward_original_decision_std": 0.6838385114895674,
+      "reward_original_overall_mean": 0.05179687468180806,
+      "reward_original_overall_std": 0.8096291865426096,
+      "reward_std": 0.7453861476489798,
+      "step": 14
+    },
+    {
+      "advantages_interactive_phase": 1.6763806343078613e-08,
+      "clip_ratio": 0.002168334409361705,
+      "clue_civilian_adjusted_reward_mean": -0.017857344380594605,
+      "clue_civilian_advantage_adjustment": -0.03452401104726128,
+      "clue_civilian_baseline": 0.03452401104726128,
+      "clue_civilian_raw_reward_mean": 0.016666666666666673,
+      "clue_civilian_votes_avg": 1.7499999999999998,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": 0.053572029338922515,
+      "clue_spy_advantage_adjustment": 0.10357202933892252,
+      "clue_spy_baseline": -0.10357202933892252,
+      "clue_spy_raw_reward": -0.05,
+      "clue_spy_votes_received": 2.25,
+      "clue_suspicion_potential_psi": 0.5,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 468.203125,
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.3421038389205933,
+      "kl": 0.0181732177734375,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0008,
+      "loss_interactive_phase": 0.0008238212176365778,
+      "reward": 0.02273438314422436,
+      "reward_original_clue_max": 0.18731897216898136,
+      "reward_original_clue_mean": -9.50715325692339e-10,
+      "reward_original_clue_min": -0.2692268830567751,
+      "reward_original_clue_std": 0.17955641394585323,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.09093750000000006,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.2548697778588656,
+      "reward_original_overall_mean": 0.045468749524642374,
+      "reward_original_overall_std": 0.9937842968598625,
+      "reward_std": 0.9645993428178439,
+      "step": 15
+    },
+    {
+      "advantages_interactive_phase": 2.270098775625229e-09,
+      "clip_ratio": 0.002054115197097417,
+      "clue_civilian_adjusted_reward_mean": -0.0028338794241449874,
+      "clue_civilian_advantage_adjustment": -0.030611657201922767,
+      "clue_civilian_baseline": 0.030611657201922767,
+      "clue_civilian_raw_reward_mean": 0.027777777777777776,
+      "clue_civilian_votes_avg": 1.5416666666666667,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 1.0,
+      "clue_spy_adjusted_reward": 0.008501637803475291,
+      "clue_spy_advantage_adjustment": 0.09183497113680864,
+      "clue_spy_baseline": -0.09183497113680865,
+      "clue_spy_raw_reward": -0.08333333333333334,
+      "clue_spy_votes_received": 2.375,
+      "clue_suspicion_potential_psi": 0.8333333333333334,
+      "clue_total_valid_votes": 7.0,
+      "completion_length": 275.125,
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.7850903868675232,
+      "kl": 0.0244598388671875,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.001,
+      "loss_interactive_phase": 0.0010270941420458257,
+      "reward": 0.045351563605739435,
+      "reward_original_clue_max": 0.1676480405203468,
+      "reward_original_clue_mean": -1.1723991688496888e-10,
+      "reward_original_clue_min": -0.21926755630398242,
+      "reward_original_clue_std": 0.15357384075954295,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.18140625000000005,
+      "reward_original_decision_min": -0.9000000000000001,
+      "reward_original_decision_std": 1.3118144469212671,
+      "reward_original_overall_mean": 0.0907031249413801,
+      "reward_original_overall_std": 1.0186333011595043,
+      "reward_std": 0.8487135706349032,
+      "step": 16
+    },
+    {
+      "advantages_interactive_phase": 2.514570951461792e-08,
+      "clip_ratio": 0.0019102254445897415,
+      "clue_civilian_adjusted_reward_mean": 0.06882066053365016,
+      "clue_civilian_advantage_adjustment": -0.05895711724412763,
+      "clue_civilian_baseline": 0.05895711724412763,
+      "clue_civilian_raw_reward_mean": 0.1277777777777778,
+      "clue_civilian_votes_avg": 0.9166666666666666,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": -0.20646198127124893,
+      "clue_spy_advantage_adjustment": 0.17687135206208443,
+      "clue_spy_baseline": -0.17687135206208443,
+      "clue_spy_raw_reward": -0.3833333333333334,
+      "clue_spy_votes_received": 4.75,
+      "clue_suspicion_potential_psi": 3.8333333333333335,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 394.09375,
+      "epoch": 2.4285714285714284,
+      "grad_norm": 1.7240030765533447,
+      "kl": 0.03399658203125,
+      "learning_rate": 6.071428571428571e-06,
+      "loss": 0.0016,
+      "loss_interactive_phase": 0.0016125904367072508,
+      "reward": 0.2875781375934611,
+      "reward_original_clue_max": 0.20678514922918734,
+      "reward_original_clue_mean": 8.242538682839973e-11,
+      "reward_original_clue_min": -0.4027598033001195,
+      "reward_original_clue_std": 0.25114777296201934,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.1503125,
+      "reward_original_decision_min": -0.05249999999999988,
+      "reward_original_decision_std": 0.8344790915295959,
+      "reward_original_overall_mean": 0.5751562500412127,
+      "reward_original_overall_std": 1.094775886069116,
+      "reward_std": 0.9482798058442161,
+      "step": 17
+    },
+    {
+      "advantages_interactive_phase": 1.2631062418222427e-08,
+      "clip_ratio": 0.002529568810132332,
+      "clue_civilian_adjusted_reward_mean": -0.017029911049686576,
+      "clue_civilian_advantage_adjustment": -0.0878632443830199,
+      "clue_civilian_baseline": 0.0878632443830199,
+      "clue_civilian_raw_reward_mean": 0.07083333333333333,
+      "clue_civilian_votes_avg": 1.2500000000000002,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.875,
+      "clue_spy_adjusted_reward": 0.05108973573591717,
+      "clue_spy_advantage_adjustment": 0.2635897357359172,
+      "clue_spy_baseline": -0.2635897357359172,
+      "clue_spy_raw_reward": -0.21250000000000002,
+      "clue_spy_votes_received": 3.375,
+      "clue_suspicion_potential_psi": 2.125,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 306.46875,
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.7146915793418884,
+      "kl": 0.02801513671875,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 0.0012,
+      "loss_interactive_phase": 0.0011510928088682704,
+      "reward": 0.1489453189772098,
+      "reward_original_clue_max": 0.2189921520150641,
+      "reward_original_clue_mean": 6.46714365219736e-10,
+      "reward_original_clue_min": -0.28089929838491334,
+      "reward_original_clue_std": 0.19312110381430628,
+      "reward_original_decision_max": 1.7925,
+      "reward_original_decision_mean": 0.5957812500000002,
+      "reward_original_decision_min": -0.47625,
+      "reward_original_decision_std": 1.0009038009688636,
+      "reward_original_overall_mean": 0.2978906253233572,
+      "reward_original_overall_std": 1.0077314694920716,
+      "reward_std": 0.8440019964029162,
+      "step": 18
+    },
+    {
+      "advantages_interactive_phase": 2.2351741790771484e-08,
+      "clip_ratio": 0.002893349708756432,
+      "clue_civilian_adjusted_reward_mean": 0.0016776696910085626,
+      "clue_civilian_advantage_adjustment": -0.078877885864547,
+      "clue_civilian_baseline": 0.078877885864547,
+      "clue_civilian_raw_reward_mean": 0.08055555555555557,
+      "clue_civilian_votes_avg": 1.2083333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.75,
+      "clue_spy_adjusted_reward": -0.005033007258676128,
+      "clue_spy_advantage_adjustment": 0.23663365940799053,
+      "clue_spy_baseline": -0.23663365940799053,
+      "clue_spy_raw_reward": -0.2416666666666667,
+      "clue_spy_votes_received": 3.625,
+      "clue_suspicion_potential_psi": 2.4166666666666665,
+      "clue_total_valid_votes": 7.25,
+      "completion_length": 437.875,
+      "epoch": 2.7142857142857144,
+      "grad_norm": 1.4541630744934082,
+      "kl": 0.045196533203125,
+      "learning_rate": 6.785714285714287e-06,
+      "loss": 0.0021,
+      "loss_interactive_phase": 0.002087649641907774,
+      "reward": 0.17308594878926778,
+      "reward_original_clue_max": 0.20095789975114906,
+      "reward_original_clue_mean": 4.5358739160505923e-10,
+      "reward_original_clue_min": -0.276746719719095,
+      "reward_original_clue_std": 0.19300974707692706,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.69234375,
+      "reward_original_decision_min": -0.4762499999999999,
+      "reward_original_decision_std": 1.1476309390317945,
+      "reward_original_overall_mean": 0.34617187522679377,
+      "reward_original_overall_std": 1.0768417004231448,
+      "reward_std": 1.006128029698324,
+      "step": 19
+    },
+    {
+      "advantages_interactive_phase": 2.9569491744041443e-08,
+      "clip_ratio": 0.0022259497418417595,
+      "clue_civilian_adjusted_reward_mean": 0.006911390664315264,
+      "clue_civilian_advantage_adjustment": -0.08197749822457363,
+      "clue_civilian_baseline": 0.08197749822457362,
+      "clue_civilian_raw_reward_mean": 0.08888888888888888,
+      "clue_civilian_votes_avg": 1.0833333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 1.0,
+      "clue_spy_adjusted_reward": -0.02073416946596162,
+      "clue_spy_advantage_adjustment": 0.24593249720070504,
+      "clue_spy_baseline": -0.24593249720070506,
+      "clue_spy_raw_reward": -0.26666666666666666,
+      "clue_spy_votes_received": 3.75,
+      "clue_suspicion_potential_psi": 2.6666666666666665,
+      "clue_total_valid_votes": 7.0,
+      "completion_length": 289.5703125,
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7347911596298218,
+      "kl": 0.039093017578125,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0016,
+      "loss_interactive_phase": 0.0015583366912323982,
+      "reward": 0.19101563994268245,
+      "reward_original_clue_max": 0.23070516273122516,
+      "reward_original_clue_mean": 6.317460534734087e-10,
+      "reward_original_clue_min": -0.2731542746725672,
+      "reward_original_clue_std": 0.20968935386685733,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.7640625000000001,
+      "reward_original_decision_min": -0.05249999999999988,
+      "reward_original_decision_std": 0.8058733220437151,
+      "reward_original_overall_mean": 0.38203125031587315,
+      "reward_original_overall_std": 1.0078142522261966,
+      "reward_std": 0.8109368409209663,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ad7a75d0e28099a77fe1ea732ab3608c6b7b67413f3989c9cfd840540b9c4b
+size 8977