commit 2dfaab5b40c81a0d8eadd7703dc4f128512e6195
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Jun 4 00:07:12 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: mlfoundations-cua-dev/qwen2_5vl_7b_easyr1_10k_hard_segui3b_easy_gta1-4MP
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..8df0cf4
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,56 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..267568e
--- /dev/null
+++ b/README.md
@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2_5vl_7b_easyr1_10k_hard_segui3b_easy_gta1-4MP_lr_1_0e-06_bs_1_epochs_1.0_max_pixels_4000000_deepspeed
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2_5vl_7b_easyr1_10k_hard_segui3b_easy_gta1-4MP_lr_1_0e-06_bs_1_epochs_1.0_max_pixels_4000000_deepspeed
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the easyr1-10k-hard-segui3b-easy-gta1-4MP dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..482ced4
--- /dev/null
+++ b/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
+}
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..f364bcb
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,9 @@
+{
+    "effective_tokens_per_sec": 210.0489103830877,
+    "epoch": 1.0,
+    "total_flos": 8.611551323462042e+17,
+    "train_loss": 0.6264356197357178,
+    "train_runtime": 11004.0234,
+    "train_samples_per_second": 0.909,
+    "train_steps_per_second": 0.114
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..6c22663
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..4d68017
--- /dev/null
+++ b/config.json
@@ -0,0 +1,105 @@
+{
+  "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,
+  "text_config": {
+    "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": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "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,
+    "torch_dtype": "bfloat16",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..273dbe0
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-to-text", "allow_remote": true}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..c110271
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "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": "4.52.4"
+}
diff --git a/merges.txt b/merges.txt
new file mode 100644
index 0000000..80c1a19
--- /dev/null
+++ b/merges.txt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853
diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors
new file mode 100644
index 0000000..5d1ff8b
--- /dev/null
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c19fe0c34c8a9ba16759a6a48689f9e4879286966679af37c7e97b4aa51872
+size 4968243304
diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors
new file mode 100644
index 0000000..cd246e8
--- /dev/null
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7caa1187f76e3bfe73cb95db0a5e05a8459f6a184eda4a466969c606cc054e
+size 4991495816
diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors
new file mode 100644
index 0000000..27396f9
--- /dev/null
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4937e3442a8e1eda7803549b48d72366362aa8d06e4a3bdf11b23df01172a31d
+size 4932751040
diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors
new file mode 100644
index 0000000..1e6a0c1
--- /dev/null
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1458c7052ce6017c13b2a985bf510422a0c2e7ab60932d32db55bd9b0e6a688c
+size 1691924384
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..6a84000
--- /dev/null
+++ b/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"
+  }
+}
diff --git a/preprocessor_config.json b/preprocessor_config.json
new file mode 100644
index 0000000..1c234b7
--- /dev/null
+++ b/preprocessor_config.json
@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..ac23c0a
--- /dev/null
+++ b/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
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..51ebb3b
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..230f071
--- /dev/null
+++ b/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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..f364bcb
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "effective_tokens_per_sec": 210.0489103830877,
+    "epoch": 1.0,
+    "total_flos": 8.611551323462042e+17,
+    "train_loss": 0.6264356197357178,
+    "train_runtime": 11004.0234,
+    "train_samples_per_second": 0.909,
+    "train_steps_per_second": 0.114
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..015c7da
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,126 @@
+{"current_steps": 10, "total_steps": 1250, "loss": 1.163, "lr": 7.2e-08, "epoch": 0.008, "percentage": 0.8, "elapsed_time": "0:01:36", "remaining_time": "3:20:21"}
+{"current_steps": 20, "total_steps": 1250, "loss": 1.1726, "lr": 1.5199999999999998e-07, "epoch": 0.016, "percentage": 1.6, "elapsed_time": "0:03:05", "remaining_time": "3:10:12"}
+{"current_steps": 30, "total_steps": 1250, "loss": 1.1791, "lr": 2.32e-07, "epoch": 0.024, "percentage": 2.4, "elapsed_time": "0:04:36", "remaining_time": "3:07:20"}
+{"current_steps": 40, "total_steps": 1250, "loss": 0.966, "lr": 3.12e-07, "epoch": 0.032, "percentage": 3.2, "elapsed_time": "0:05:55", "remaining_time": "2:59:15"}
+{"current_steps": 50, "total_steps": 1250, "loss": 0.8166, "lr": 3.92e-07, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:07:31", "remaining_time": "3:00:24"}
+{"current_steps": 60, "total_steps": 1250, "loss": 0.785, "lr": 4.7199999999999994e-07, "epoch": 0.048, "percentage": 4.8, "elapsed_time": "0:09:08", "remaining_time": "3:01:10"}
+{"current_steps": 70, "total_steps": 1250, "loss": 0.732, "lr": 5.520000000000001e-07, "epoch": 0.056, "percentage": 5.6, "elapsed_time": "0:10:41", "remaining_time": "3:00:15"}
+{"current_steps": 80, "total_steps": 1250, "loss": 0.7326, "lr": 6.319999999999999e-07, "epoch": 0.064, "percentage": 6.4, "elapsed_time": "0:11:56", "remaining_time": "2:54:42"}
+{"current_steps": 90, "total_steps": 1250, "loss": 0.7385, "lr": 7.119999999999999e-07, "epoch": 0.072, "percentage": 7.2, "elapsed_time": "0:13:02", "remaining_time": "2:48:09"}
+{"current_steps": 100, "total_steps": 1250, "loss": 0.7489, "lr": 7.92e-07, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:14:31", "remaining_time": "2:47:06"}
+{"current_steps": 110, "total_steps": 1250, "loss": 0.762, "lr": 8.72e-07, "epoch": 0.088, "percentage": 8.8, "elapsed_time": "0:15:57", "remaining_time": "2:45:24"}
+{"current_steps": 120, "total_steps": 1250, "loss": 0.6751, "lr": 9.52e-07, "epoch": 0.096, "percentage": 9.6, "elapsed_time": "0:17:29", "remaining_time": "2:44:43"}
+{"current_steps": 130, "total_steps": 1250, "loss": 0.6507, "lr": 9.999688075005433e-07, "epoch": 0.104, "percentage": 10.4, "elapsed_time": "0:19:03", "remaining_time": "2:44:08"}
+{"current_steps": 140, "total_steps": 1250, "loss": 0.6309, "lr": 9.996179365760233e-07, "epoch": 0.112, "percentage": 11.2, "elapsed_time": "0:20:28", "remaining_time": "2:42:20"}
+{"current_steps": 150, "total_steps": 1250, "loss": 0.6199, "lr": 9.988774786134233e-07, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:22:01", "remaining_time": "2:41:31"}
+{"current_steps": 160, "total_steps": 1250, "loss": 0.689, "lr": 9.977480109995883e-07, "epoch": 0.128, "percentage": 12.8, "elapsed_time": "0:23:26", "remaining_time": "2:39:40"}
+{"current_steps": 170, "total_steps": 1250, "loss": 0.7167, "lr": 9.962304144593893e-07, "epoch": 0.136, "percentage": 13.6, "elapsed_time": "0:25:03", "remaining_time": "2:39:11"}
+{"current_steps": 180, "total_steps": 1250, "loss": 0.613, "lr": 9.94325872368957e-07, "epoch": 0.144, "percentage": 14.4, "elapsed_time": "0:26:38", "remaining_time": "2:38:21"}
+{"current_steps": 190, "total_steps": 1250, "loss": 0.6538, "lr": 9.920358698329241e-07, "epoch": 0.152, "percentage": 15.2, "elapsed_time": "0:28:07", "remaining_time": "2:36:56"}
+{"current_steps": 200, "total_steps": 1250, "loss": 0.6899, "lr": 9.89362192526383e-07, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:29:23", "remaining_time": "2:34:18"}
+{"current_steps": 210, "total_steps": 1250, "loss": 0.6425, "lr": 9.863069253024717e-07, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:30:57", "remaining_time": "2:33:21"}
+{"current_steps": 220, "total_steps": 1250, "loss": 0.6299, "lr": 9.828724505666663e-07, "epoch": 0.176, "percentage": 17.6, "elapsed_time": "0:32:36", "remaining_time": "2:32:38"}
+{"current_steps": 230, "total_steps": 1250, "loss": 0.6225, "lr": 9.790614464190547e-07, "epoch": 0.184, "percentage": 18.4, "elapsed_time": "0:33:59", "remaining_time": "2:30:46"}
+{"current_steps": 240, "total_steps": 1250, "loss": 0.6294, "lr": 9.748768845660333e-07, "epoch": 0.192, "percentage": 19.2, "elapsed_time": "0:35:26", "remaining_time": "2:29:07"}
+{"current_steps": 250, "total_steps": 1250, "loss": 0.6153, "lr": 9.703220280030607e-07, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:36:45", "remaining_time": "2:27:03"}
+{"current_steps": 260, "total_steps": 1250, "loss": 0.6105, "lr": 9.65400428470271e-07, "epoch": 0.208, "percentage": 20.8, "elapsed_time": "0:38:18", "remaining_time": "2:25:50"}
+{"current_steps": 270, "total_steps": 1250, "loss": 0.6335, "lr": 9.601159236829351e-07, "epoch": 0.216, "percentage": 21.6, "elapsed_time": "0:39:55", "remaining_time": "2:24:55"}
+{"current_steps": 280, "total_steps": 1250, "loss": 0.6097, "lr": 9.544726343389243e-07, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:41:24", "remaining_time": "2:23:26"}
+{"current_steps": 290, "total_steps": 1250, "loss": 0.6641, "lr": 9.48474960905515e-07, "epoch": 0.232, "percentage": 23.2, "elapsed_time": "0:42:35", "remaining_time": "2:21:01"}
+{"current_steps": 300, "total_steps": 1250, "loss": 0.6193, "lr": 9.421275801880362e-07, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:44:02", "remaining_time": "2:19:27"}
+{"current_steps": 310, "total_steps": 1250, "loss": 0.6532, "lr": 9.354354416830376e-07, "epoch": 0.248, "percentage": 24.8, "elapsed_time": "0:45:46", "remaining_time": "2:18:49"}
+{"current_steps": 320, "total_steps": 1250, "loss": 0.6649, "lr": 9.284037637188213e-07, "epoch": 0.256, "percentage": 25.6, "elapsed_time": "0:47:10", "remaining_time": "2:17:05"}
+{"current_steps": 330, "total_steps": 1250, "loss": 0.6488, "lr": 9.210380293863461e-07, "epoch": 0.264, "percentage": 26.4, "elapsed_time": "0:48:47", "remaining_time": "2:16:02"}
+{"current_steps": 340, "total_steps": 1250, "loss": 0.6406, "lr": 9.133439822636777e-07, "epoch": 0.272, "percentage": 27.2, "elapsed_time": "0:50:09", "remaining_time": "2:14:14"}
+{"current_steps": 350, "total_steps": 1250, "loss": 0.6061, "lr": 9.0532762193732e-07, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:51:41", "remaining_time": "2:12:56"}
+{"current_steps": 360, "total_steps": 1250, "loss": 0.6225, "lr": 8.969951993239177e-07, "epoch": 0.288, "percentage": 28.8, "elapsed_time": "0:53:13", "remaining_time": "2:11:34"}
+{"current_steps": 370, "total_steps": 1250, "loss": 0.6385, "lr": 8.883532117959796e-07, "epoch": 0.296, "percentage": 29.6, "elapsed_time": "0:54:28", "remaining_time": "2:09:34"}
+{"current_steps": 380, "total_steps": 1250, "loss": 0.6633, "lr": 8.794083981154228e-07, "epoch": 0.304, "percentage": 30.4, "elapsed_time": "0:55:53", "remaining_time": "2:07:58"}
+{"current_steps": 390, "total_steps": 1250, "loss": 0.635, "lr": 8.70167733178889e-07, "epoch": 0.312, "percentage": 31.2, "elapsed_time": "0:57:00", "remaining_time": "2:05:42"}
+{"current_steps": 400, "total_steps": 1250, "loss": 0.6243, "lr": 8.606384225789303e-07, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:58:21", "remaining_time": "2:04:00"}
+{"current_steps": 410, "total_steps": 1250, "loss": 0.6319, "lr": 8.508278969853037e-07, "epoch": 0.328, "percentage": 32.8, "elapsed_time": "0:59:35", "remaining_time": "2:02:05"}
+{"current_steps": 420, "total_steps": 1250, "loss": 0.535, "lr": 8.407438063507599e-07, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "1:01:03", "remaining_time": "2:00:39"}
+{"current_steps": 430, "total_steps": 1250, "loss": 0.5109, "lr": 8.303940139458388e-07, "epoch": 0.344, "percentage": 34.4, "elapsed_time": "1:02:24", "remaining_time": "1:59:01"}
+{"current_steps": 440, "total_steps": 1250, "loss": 0.5803, "lr": 8.19786590227329e-07, "epoch": 0.352, "percentage": 35.2, "elapsed_time": "1:04:01", "remaining_time": "1:57:51"}
+{"current_steps": 450, "total_steps": 1250, "loss": 0.5606, "lr": 8.089298065451671e-07, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "1:05:47", "remaining_time": "1:56:58"}
+{"current_steps": 460, "total_steps": 1250, "loss": 0.6236, "lr": 7.97832128692689e-07, "epoch": 0.368, "percentage": 36.8, "elapsed_time": "1:07:08", "remaining_time": "1:55:18"}
+{"current_steps": 470, "total_steps": 1250, "loss": 0.5872, "lr": 7.865022103052576e-07, "epoch": 0.376, "percentage": 37.6, "elapsed_time": "1:08:48", "remaining_time": "1:54:10"}
+{"current_steps": 480, "total_steps": 1250, "loss": 0.5743, "lr": 7.7494888611242e-07, "epoch": 0.384, "percentage": 38.4, "elapsed_time": "1:10:20", "remaining_time": "1:52:50"}
+{"current_steps": 490, "total_steps": 1250, "loss": 0.6218, "lr": 7.631811650488488e-07, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "1:11:36", "remaining_time": "1:51:03"}
+{"current_steps": 500, "total_steps": 1250, "loss": 0.5576, "lr": 7.51208223229449e-07, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "1:12:50", "remaining_time": "1:49:15"}
+{"current_steps": 510, "total_steps": 1250, "loss": 0.6116, "lr": 7.390393967940962e-07, "epoch": 0.408, "percentage": 40.8, "elapsed_time": "1:14:24", "remaining_time": "1:47:58"}
+{"current_steps": 520, "total_steps": 1250, "loss": 0.5882, "lr": 7.266841746275976e-07, "epoch": 0.416, "percentage": 41.6, "elapsed_time": "1:15:56", "remaining_time": "1:46:36"}
+{"current_steps": 530, "total_steps": 1250, "loss": 0.6676, "lr": 7.141521909605451e-07, "epoch": 0.424, "percentage": 42.4, "elapsed_time": "1:17:27", "remaining_time": "1:45:13"}
+{"current_steps": 540, "total_steps": 1250, "loss": 0.5431, "lr": 7.014532178568313e-07, "epoch": 0.432, "percentage": 43.2, "elapsed_time": "1:18:53", "remaining_time": "1:43:43"}
+{"current_steps": 550, "total_steps": 1250, "loss": 0.615, "lr": 6.885971575936883e-07, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "1:20:18", "remaining_time": "1:42:12"}
+{"current_steps": 560, "total_steps": 1250, "loss": 0.5834, "lr": 6.7559403494019e-07, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "1:21:43", "remaining_time": "1:40:42"}
+{"current_steps": 570, "total_steps": 1250, "loss": 0.6153, "lr": 6.624539893402382e-07, "epoch": 0.456, "percentage": 45.6, "elapsed_time": "1:23:16", "remaining_time": "1:39:20"}
+{"current_steps": 580, "total_steps": 1250, "loss": 0.6112, "lr": 6.491872670061301e-07, "epoch": 0.464, "percentage": 46.4, "elapsed_time": "1:24:28", "remaining_time": "1:37:35"}
+{"current_steps": 590, "total_steps": 1250, "loss": 0.6148, "lr": 6.358042129288693e-07, "epoch": 0.472, "percentage": 47.2, "elapsed_time": "1:25:45", "remaining_time": "1:35:55"}
+{"current_steps": 600, "total_steps": 1250, "loss": 0.6125, "lr": 6.223152628114536e-07, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "1:27:19", "remaining_time": "1:34:36"}
+{"current_steps": 610, "total_steps": 1250, "loss": 0.5715, "lr": 6.087309349314274e-07, "epoch": 0.488, "percentage": 48.8, "elapsed_time": "1:28:44", "remaining_time": "1:33:06"}
+{"current_steps": 620, "total_steps": 1250, "loss": 0.5864, "lr": 5.950618219390451e-07, "epoch": 0.496, "percentage": 49.6, "elapsed_time": "1:30:16", "remaining_time": "1:31:44"}
+{"current_steps": 630, "total_steps": 1250, "loss": 0.5635, "lr": 5.813185825974418e-07, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "1:31:36", "remaining_time": "1:30:08"}
+{"current_steps": 640, "total_steps": 1250, "loss": 0.6266, "lr": 5.675119334712496e-07, "epoch": 0.512, "percentage": 51.2, "elapsed_time": "1:32:45", "remaining_time": "1:28:24"}
+{"current_steps": 650, "total_steps": 1250, "loss": 0.5606, "lr": 5.536526405701433e-07, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "1:34:11", "remaining_time": "1:26:56"}
+{"current_steps": 660, "total_steps": 1250, "loss": 0.597, "lr": 5.397515109538299e-07, "epoch": 0.528, "percentage": 52.8, "elapsed_time": "1:35:46", "remaining_time": "1:25:36"}
+{"current_steps": 670, "total_steps": 1250, "loss": 0.6027, "lr": 5.258193843050282e-07, "epoch": 0.536, "percentage": 53.6, "elapsed_time": "1:37:17", "remaining_time": "1:24:13"}
+{"current_steps": 680, "total_steps": 1250, "loss": 0.539, "lr": 5.118671244770109e-07, "epoch": 0.544, "percentage": 54.4, "elapsed_time": "1:38:57", "remaining_time": "1:22:56"}
+{"current_steps": 690, "total_steps": 1250, "loss": 0.6108, "lr": 4.979056110222981e-07, "epoch": 0.552, "percentage": 55.2, "elapsed_time": "1:40:11", "remaining_time": "1:21:18"}
+{"current_steps": 700, "total_steps": 1250, "loss": 0.5889, "lr": 4.839457307091092e-07, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "1:41:33", "remaining_time": "1:19:47"}
+{"current_steps": 710, "total_steps": 1250, "loss": 0.6249, "lr": 4.6999836903218975e-07, "epoch": 0.568, "percentage": 56.8, "elapsed_time": "1:43:05", "remaining_time": "1:18:24"}
+{"current_steps": 720, "total_steps": 1250, "loss": 0.5807, "lr": 4.560744017246284e-07, "epoch": 0.576, "percentage": 57.6, "elapsed_time": "1:44:39", "remaining_time": "1:17:02"}
+{"current_steps": 730, "total_steps": 1250, "loss": 0.6027, "lr": 4.4218468627728927e-07, "epoch": 0.584, "percentage": 58.4, "elapsed_time": "1:46:02", "remaining_time": "1:15:32"}
+{"current_steps": 740, "total_steps": 1250, "loss": 0.5744, "lr": 4.2834005347246525e-07, "epoch": 0.592, "percentage": 59.2, "elapsed_time": "1:47:39", "remaining_time": "1:14:11"}
+{"current_steps": 750, "total_steps": 1250, "loss": 0.582, "lr": 4.145512989383617e-07, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "1:48:54", "remaining_time": "1:12:36"}
+{"current_steps": 760, "total_steps": 1250, "loss": 0.6209, "lr": 4.008291747309884e-07, "epoch": 0.608, "percentage": 60.8, "elapsed_time": "1:50:07", "remaining_time": "1:11:00"}
+{"current_steps": 770, "total_steps": 1250, "loss": 0.6108, "lr": 3.8718438095003126e-07, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "1:51:29", "remaining_time": "1:09:29"}
+{"current_steps": 780, "total_steps": 1250, "loss": 0.6099, "lr": 3.7362755739523534e-07, "epoch": 0.624, "percentage": 62.4, "elapsed_time": "1:52:51", "remaining_time": "1:08:00"}
+{"current_steps": 790, "total_steps": 1250, "loss": 0.6125, "lr": 3.601692752698101e-07, "epoch": 0.632, "percentage": 63.2, "elapsed_time": "1:54:05", "remaining_time": "1:06:25"}
+{"current_steps": 800, "total_steps": 1250, "loss": 0.6294, "lr": 3.46820028937322e-07, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "1:55:35", "remaining_time": "1:05:01"}
+{"current_steps": 810, "total_steps": 1250, "loss": 0.5598, "lr": 3.335902277385067e-07, "epoch": 0.648, "percentage": 64.8, "elapsed_time": "1:57:01", "remaining_time": "1:03:34"}
+{"current_steps": 820, "total_steps": 1250, "loss": 0.647, "lr": 3.204901878743769e-07, "epoch": 0.656, "percentage": 65.6, "elapsed_time": "1:58:28", "remaining_time": "1:02:07"}
+{"current_steps": 830, "total_steps": 1250, "loss": 0.67, "lr": 3.075301243619603e-07, "epoch": 0.664, "percentage": 66.4, "elapsed_time": "1:59:54", "remaining_time": "1:00:40"}
+{"current_steps": 840, "total_steps": 1250, "loss": 0.6254, "lr": 2.94720143068936e-07, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "2:01:18", "remaining_time": "0:59:12"}
+{"current_steps": 850, "total_steps": 1250, "loss": 0.5444, "lr": 2.82070232833383e-07, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "2:02:50", "remaining_time": "0:57:48"}
+{"current_steps": 860, "total_steps": 1250, "loss": 0.602, "lr": 2.695902576747846e-07, "epoch": 0.688, "percentage": 68.8, "elapsed_time": "2:04:26", "remaining_time": "0:56:26"}
+{"current_steps": 870, "total_steps": 1250, "loss": 0.5784, "lr": 2.57289949102363e-07, "epoch": 0.696, "percentage": 69.6, "elapsed_time": "2:05:54", "remaining_time": "0:54:59"}
+{"current_steps": 880, "total_steps": 1250, "loss": 0.5973, "lr": 2.451788985267411e-07, "epoch": 0.704, "percentage": 70.4, "elapsed_time": "2:07:07", "remaining_time": "0:53:27"}
+{"current_steps": 890, "total_steps": 1250, "loss": 0.501, "lr": 2.332665497808487e-07, "epoch": 0.712, "percentage": 71.2, "elapsed_time": "2:08:39", "remaining_time": "0:52:02"}
+{"current_steps": 900, "total_steps": 1250, "loss": 0.5251, "lr": 2.215621917559062e-07, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "2:10:06", "remaining_time": "0:50:35"}
+{"current_steps": 910, "total_steps": 1250, "loss": 0.5794, "lr": 2.1007495115822537e-07, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "2:11:41", "remaining_time": "0:49:12"}
+{"current_steps": 920, "total_steps": 1250, "loss": 0.5609, "lr": 1.9881378539248077e-07, "epoch": 0.736, "percentage": 73.6, "elapsed_time": "2:13:18", "remaining_time": "0:47:48"}
+{"current_steps": 930, "total_steps": 1250, "loss": 0.5381, "lr": 1.8778747557699221e-07, "epoch": 0.744, "percentage": 74.4, "elapsed_time": "2:14:49", "remaining_time": "0:46:23"}
+{"current_steps": 940, "total_steps": 1250, "loss": 0.5848, "lr": 1.7700461969647468e-07, "epoch": 0.752, "percentage": 75.2, "elapsed_time": "2:16:21", "remaining_time": "0:44:58"}
+{"current_steps": 950, "total_steps": 1250, "loss": 0.5656, "lr": 1.6647362589758785e-07, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "2:17:46", "remaining_time": "0:43:30"}
+{"current_steps": 960, "total_steps": 1250, "loss": 0.5997, "lr": 1.5620270593251633e-07, "epoch": 0.768, "percentage": 76.8, "elapsed_time": "2:19:05", "remaining_time": "0:42:01"}
+{"current_steps": 970, "total_steps": 1250, "loss": 0.6232, "lr": 1.4619986875569246e-07, "epoch": 0.776, "percentage": 77.6, "elapsed_time": "2:20:16", "remaining_time": "0:40:29"}
+{"current_steps": 980, "total_steps": 1250, "loss": 0.591, "lr": 1.3647291427865416e-07, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "2:21:37", "remaining_time": "0:39:01"}
+{"current_steps": 990, "total_steps": 1250, "loss": 0.6193, "lr": 1.2702942728790894e-07, "epoch": 0.792, "percentage": 79.2, "elapsed_time": "2:23:12", "remaining_time": "0:37:36"}
+{"current_steps": 1000, "total_steps": 1250, "loss": 0.5831, "lr": 1.1787677153054549e-07, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "2:24:45", "remaining_time": "0:36:11"}
+{"current_steps": 1010, "total_steps": 1250, "loss": 0.5912, "lr": 1.0902208397220497e-07, "epoch": 0.808, "percentage": 80.8, "elapsed_time": "2:27:28", "remaining_time": "0:35:02"}
+{"current_steps": 1020, "total_steps": 1250, "loss": 0.5565, "lr": 1.0047226923189022e-07, "epoch": 0.816, "percentage": 81.6, "elapsed_time": "2:29:00", "remaining_time": "0:33:35"}
+{"current_steps": 1030, "total_steps": 1250, "loss": 0.6402, "lr": 9.223399419795092e-08, "epoch": 0.824, "percentage": 82.4, "elapsed_time": "2:30:14", "remaining_time": "0:32:05"}
+{"current_steps": 1040, "total_steps": 1250, "loss": 0.5588, "lr": 8.431368282944584e-08, "epoch": 0.832, "percentage": 83.2, "elapsed_time": "2:31:35", "remaining_time": "0:30:36"}
+{"current_steps": 1050, "total_steps": 1250, "loss": 0.5421, "lr": 7.671751114693103e-08, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "2:33:05", "remaining_time": "0:29:09"}
+{"current_steps": 1060, "total_steps": 1250, "loss": 0.5676, "lr": 6.945140241658686e-08, "epoch": 0.848, "percentage": 84.8, "elapsed_time": "2:34:04", "remaining_time": "0:27:37"}
+{"current_steps": 1070, "total_steps": 1250, "loss": 0.6404, "lr": 6.25210225314312e-08, "epoch": 0.856, "percentage": 85.6, "elapsed_time": "2:35:38", "remaining_time": "0:26:11"}
+{"current_steps": 1080, "total_steps": 1250, "loss": 0.5725, "lr": 5.593177559322776e-08, "epoch": 0.864, "percentage": 86.4, "elapsed_time": "2:37:15", "remaining_time": "0:24:45"}
+{"current_steps": 1090, "total_steps": 1250, "loss": 0.5725, "lr": 4.968879969852985e-08, "epoch": 0.872, "percentage": 87.2, "elapsed_time": "2:38:47", "remaining_time": "0:23:18"}
+{"current_steps": 1100, "total_steps": 1250, "loss": 0.6098, "lr": 4.3796962932146966e-08, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "2:40:04", "remaining_time": "0:21:49"}
+{"current_steps": 1110, "total_steps": 1250, "loss": 0.6195, "lr": 3.8260859571158875e-08, "epoch": 0.888, "percentage": 88.8, "elapsed_time": "2:41:47", "remaining_time": "0:20:24"}
+{"current_steps": 1120, "total_steps": 1250, "loss": 0.5907, "lr": 3.308480650243661e-08, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "2:43:14", "remaining_time": "0:18:56"}
+{"current_steps": 1130, "total_steps": 1250, "loss": 0.5695, "lr": 2.8272839856463782e-08, "epoch": 0.904, "percentage": 90.4, "elapsed_time": "2:44:38", "remaining_time": "0:17:28"}
+{"current_steps": 1140, "total_steps": 1250, "loss": 0.6108, "lr": 2.3828711860083672e-08, "epoch": 0.912, "percentage": 91.2, "elapsed_time": "2:46:02", "remaining_time": "0:16:01"}
+{"current_steps": 1150, "total_steps": 1250, "loss": 0.6049, "lr": 1.9755887910625103e-08, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "2:47:21", "remaining_time": "0:14:33"}
+{"current_steps": 1160, "total_steps": 1250, "loss": 0.6072, "lr": 1.6057543873690683e-08, "epoch": 0.928, "percentage": 92.8, "elapsed_time": "2:48:56", "remaining_time": "0:13:06"}
+{"current_steps": 1170, "total_steps": 1250, "loss": 0.4745, "lr": 1.2736563606711381e-08, "epoch": 0.936, "percentage": 93.6, "elapsed_time": "2:50:34", "remaining_time": "0:11:39"}
+{"current_steps": 1180, "total_steps": 1250, "loss": 0.5551, "lr": 9.795536710202168e-09, "epoch": 0.944, "percentage": 94.4, "elapsed_time": "2:52:01", "remaining_time": "0:10:12"}
+{"current_steps": 1190, "total_steps": 1250, "loss": 0.5737, "lr": 7.236756508468611e-09, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "2:53:35", "remaining_time": "0:08:45"}
+{"current_steps": 1200, "total_steps": 1250, "loss": 0.5902, "lr": 5.062218261342121e-09, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "2:55:08", "remaining_time": "0:07:17"}
+{"current_steps": 1210, "total_steps": 1250, "loss": 0.561, "lr": 3.273617608336221e-09, "epoch": 0.968, "percentage": 96.8, "elapsed_time": "2:56:45", "remaining_time": "0:05:50"}
+{"current_steps": 1220, "total_steps": 1250, "loss": 0.577, "lr": 1.872349246437699e-09, "epoch": 0.976, "percentage": 97.6, "elapsed_time": "2:58:12", "remaining_time": "0:04:22"}
+{"current_steps": 1230, "total_steps": 1250, "loss": 0.5546, "lr": 8.595058425640011e-10, "epoch": 0.984, "percentage": 98.4, "elapsed_time": "2:59:18", "remaining_time": "0:02:54"}
+{"current_steps": 1240, "total_steps": 1250, "loss": 0.551, "lr": 2.3587718153444957e-10, "epoch": 0.992, "percentage": 99.2, "elapsed_time": "3:00:51", "remaining_time": "0:01:27"}
+{"current_steps": 1250, "total_steps": 1250, "loss": 0.5674, "lr": 1.9495502197042213e-12, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:02:05", "remaining_time": "0:00:00"}
+{"current_steps": 1250, "total_steps": 1250, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:03:21", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..73448b1
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,918 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 111.16453552246094,
+      "learning_rate": 7.2e-08,
+      "loss": 1.163,
+      "step": 10
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 124.54598236083984,
+      "learning_rate": 1.5199999999999998e-07,
+      "loss": 1.1726,
+      "step": 20
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 100.91595458984375,
+      "learning_rate": 2.32e-07,
+      "loss": 1.1791,
+      "step": 30
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 80.15464782714844,
+      "learning_rate": 3.12e-07,
+      "loss": 0.966,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 252.4119873046875,
+      "learning_rate": 3.92e-07,
+      "loss": 0.8166,
+      "step": 50
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 678.993896484375,
+      "learning_rate": 4.7199999999999994e-07,
+      "loss": 0.785,
+      "step": 60
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 206.46011352539062,
+      "learning_rate": 5.520000000000001e-07,
+      "loss": 0.732,
+      "step": 70
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 31.90829086303711,
+      "learning_rate": 6.319999999999999e-07,
+      "loss": 0.7326,
+      "step": 80
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 174.7485809326172,
+      "learning_rate": 7.119999999999999e-07,
+      "loss": 0.7385,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 334.99591064453125,
+      "learning_rate": 7.92e-07,
+      "loss": 0.7489,
+      "step": 100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 572.4158325195312,
+      "learning_rate": 8.72e-07,
+      "loss": 0.762,
+      "step": 110
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 139.32351684570312,
+      "learning_rate": 9.52e-07,
+      "loss": 0.6751,
+      "step": 120
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 45.24559020996094,
+      "learning_rate": 9.999688075005433e-07,
+      "loss": 0.6507,
+      "step": 130
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2617.891357421875,
+      "learning_rate": 9.996179365760233e-07,
+      "loss": 0.6309,
+      "step": 140
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 107.30264282226562,
+      "learning_rate": 9.988774786134233e-07,
+      "loss": 0.6199,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 125.14055633544922,
+      "learning_rate": 9.977480109995883e-07,
+      "loss": 0.689,
+      "step": 160
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 81.20503234863281,
+      "learning_rate": 9.962304144593893e-07,
+      "loss": 0.7167,
+      "step": 170
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 251.0092315673828,
+      "learning_rate": 9.94325872368957e-07,
+      "loss": 0.613,
+      "step": 180
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 135.18783569335938,
+      "learning_rate": 9.920358698329241e-07,
+      "loss": 0.6538,
+      "step": 190
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 363.9606018066406,
+      "learning_rate": 9.89362192526383e-07,
+      "loss": 0.6899,
+      "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 155.0046844482422,
+      "learning_rate": 9.863069253024717e-07,
+      "loss": 0.6425,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 562.5201416015625,
+      "learning_rate": 9.828724505666663e-07,
+      "loss": 0.6299,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 260.6285095214844,
+      "learning_rate": 9.790614464190547e-07,
+      "loss": 0.6225,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 410.15966796875,
+      "learning_rate": 9.748768845660333e-07,
+      "loss": 0.6294,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 140.08982849121094,
+      "learning_rate": 9.703220280030607e-07,
+      "loss": 0.6153,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 39.630794525146484,
+      "learning_rate": 9.65400428470271e-07,
+      "loss": 0.6105,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 302.4677429199219,
+      "learning_rate": 9.601159236829351e-07,
+      "loss": 0.6335,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 124.71900177001953,
+      "learning_rate": 9.544726343389243e-07,
+      "loss": 0.6097,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 135.7556610107422,
+      "learning_rate": 9.48474960905515e-07,
+      "loss": 0.6641,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 51.582210540771484,
+      "learning_rate": 9.421275801880362e-07,
+      "loss": 0.6193,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 71.27699279785156,
+      "learning_rate": 9.354354416830376e-07,
+      "loss": 0.6532,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 156.27731323242188,
+      "learning_rate": 9.284037637188213e-07,
+      "loss": 0.6649,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 41.20567321777344,
+      "learning_rate": 9.210380293863461e-07,
+      "loss": 0.6488,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 84.96507263183594,
+      "learning_rate": 9.133439822636777e-07,
+      "loss": 0.6406,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 87.3453369140625,
+      "learning_rate": 9.0532762193732e-07,
+      "loss": 0.6061,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 32.09752655029297,
+      "learning_rate": 8.969951993239177e-07,
+      "loss": 0.6225,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 51.215965270996094,
+      "learning_rate": 8.883532117959796e-07,
+      "loss": 0.6385,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 58.20103454589844,
+      "learning_rate": 8.794083981154228e-07,
+      "loss": 0.6633,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 129.3231658935547,
+      "learning_rate": 8.70167733178889e-07,
+      "loss": 0.635,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 192.52386474609375,
+      "learning_rate": 8.606384225789303e-07,
+      "loss": 0.6243,
+      "step": 400
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 240.092041015625,
+      "learning_rate": 8.508278969853037e-07,
+      "loss": 0.6319,
+      "step": 410
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 126.35558319091797,
+      "learning_rate": 8.407438063507599e-07,
+      "loss": 0.535,
+      "step": 420
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 131.25146484375,
+      "learning_rate": 8.303940139458388e-07,
+      "loss": 0.5109,
+      "step": 430
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 110.47335052490234,
+      "learning_rate": 8.19786590227329e-07,
+      "loss": 0.5803,
+      "step": 440
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 170.6112060546875,
+      "learning_rate": 8.089298065451671e-07,
+      "loss": 0.5606,
+      "step": 450
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 117.88746643066406,
+      "learning_rate": 7.97832128692689e-07,
+      "loss": 0.6236,
+      "step": 460
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 76.8252944946289,
+      "learning_rate": 7.865022103052576e-07,
+      "loss": 0.5872,
+      "step": 470
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 80.5151596069336,
+      "learning_rate": 7.7494888611242e-07,
+      "loss": 0.5743,
+      "step": 480
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 50.92620849609375,
+      "learning_rate": 7.631811650488488e-07,
+      "loss": 0.6218,
+      "step": 490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 58.14357376098633,
+      "learning_rate": 7.51208223229449e-07,
+      "loss": 0.5576,
+      "step": 500
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 36.23912811279297,
+      "learning_rate": 7.390393967940962e-07,
+      "loss": 0.6116,
+      "step": 510
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 116.99472045898438,
+      "learning_rate": 7.266841746275976e-07,
+      "loss": 0.5882,
+      "step": 520
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 201.44654846191406,
+      "learning_rate": 7.141521909605451e-07,
+      "loss": 0.6676,
+      "step": 530
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 148.9322967529297,
+      "learning_rate": 7.014532178568313e-07,
+      "loss": 0.5431,
+      "step": 540
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 64.1119613647461,
+      "learning_rate": 6.885971575936883e-07,
+      "loss": 0.615,
+      "step": 550
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 152.45724487304688,
+      "learning_rate": 6.7559403494019e-07,
+      "loss": 0.5834,
+      "step": 560
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 50.15947341918945,
+      "learning_rate": 6.624539893402382e-07,
+      "loss": 0.6153,
+      "step": 570
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 315.6967468261719,
+      "learning_rate": 6.491872670061301e-07,
+      "loss": 0.6112,
+      "step": 580
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 125.82039642333984,
+      "learning_rate": 6.358042129288693e-07,
+      "loss": 0.6148,
+      "step": 590
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 73.30635833740234,
+      "learning_rate": 6.223152628114536e-07,
+      "loss": 0.6125,
+      "step": 600
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 79.42913818359375,
+      "learning_rate": 6.087309349314274e-07,
+      "loss": 0.5715,
+      "step": 610
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 263.9855651855469,
+      "learning_rate": 5.950618219390451e-07,
+      "loss": 0.5864,
+      "step": 620
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 139.86032104492188,
+      "learning_rate": 5.813185825974418e-07,
+      "loss": 0.5635,
+      "step": 630
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 2561.3486328125,
+      "learning_rate": 5.675119334712496e-07,
+      "loss": 0.6266,
+      "step": 640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 143.13426208496094,
+      "learning_rate": 5.536526405701433e-07,
+      "loss": 0.5606,
+      "step": 650
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 53.60542297363281,
+      "learning_rate": 5.397515109538299e-07,
+      "loss": 0.597,
+      "step": 660
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 73.9623031616211,
+      "learning_rate": 5.258193843050282e-07,
+      "loss": 0.6027,
+      "step": 670
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 36.523921966552734,
+      "learning_rate": 5.118671244770109e-07,
+      "loss": 0.539,
+      "step": 680
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 180.92674255371094,
+      "learning_rate": 4.979056110222981e-07,
+      "loss": 0.6108,
+      "step": 690
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 137.9098663330078,
+      "learning_rate": 4.839457307091092e-07,
+      "loss": 0.5889,
+      "step": 700
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 86.04741668701172,
+      "learning_rate": 4.6999836903218975e-07,
+      "loss": 0.6249,
+      "step": 710
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 356.1498718261719,
+      "learning_rate": 4.560744017246284e-07,
+      "loss": 0.5807,
+      "step": 720
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 299.1434326171875,
+      "learning_rate": 4.4218468627728927e-07,
+      "loss": 0.6027,
+      "step": 730
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 258.3714294433594,
+      "learning_rate": 4.2834005347246525e-07,
+      "loss": 0.5744,
+      "step": 740
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 206.87930297851562,
+      "learning_rate": 4.145512989383617e-07,
+      "loss": 0.582,
+      "step": 750
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 184.38796997070312,
+      "learning_rate": 4.008291747309884e-07,
+      "loss": 0.6209,
+      "step": 760
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 55.654571533203125,
+      "learning_rate": 3.8718438095003126e-07,
+      "loss": 0.6108,
+      "step": 770
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 39.461761474609375,
+      "learning_rate": 3.7362755739523534e-07,
+      "loss": 0.6099,
+      "step": 780
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 48.67549133300781,
+      "learning_rate": 3.601692752698101e-07,
+      "loss": 0.6125,
+      "step": 790
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 151.82383728027344,
+      "learning_rate": 3.46820028937322e-07,
+      "loss": 0.6294,
+      "step": 800
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 60.52513885498047,
+      "learning_rate": 3.335902277385067e-07,
+      "loss": 0.5598,
+      "step": 810
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 33.369258880615234,
+      "learning_rate": 3.204901878743769e-07,
+      "loss": 0.647,
+      "step": 820
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 92.85736846923828,
+      "learning_rate": 3.075301243619603e-07,
+      "loss": 0.67,
+      "step": 830
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 151.1267852783203,
+      "learning_rate": 2.94720143068936e-07,
+      "loss": 0.6254,
+      "step": 840
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 36.22425842285156,
+      "learning_rate": 2.82070232833383e-07,
+      "loss": 0.5444,
+      "step": 850
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 38.03788375854492,
+      "learning_rate": 2.695902576747846e-07,
+      "loss": 0.602,
+      "step": 860
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 172.8454132080078,
+      "learning_rate": 2.57289949102363e-07,
+      "loss": 0.5784,
+      "step": 870
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 55.5506477355957,
+      "learning_rate": 2.451788985267411e-07,
+      "loss": 0.5973,
+      "step": 880
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 44.82487487792969,
+      "learning_rate": 2.332665497808487e-07,
+      "loss": 0.501,
+      "step": 890
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 84.14974212646484,
+      "learning_rate": 2.215621917559062e-07,
+      "loss": 0.5251,
+      "step": 900
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 375.7658386230469,
+      "learning_rate": 2.1007495115822537e-07,
+      "loss": 0.5794,
+      "step": 910
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 50.21950912475586,
+      "learning_rate": 1.9881378539248077e-07,
+      "loss": 0.5609,
+      "step": 920
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 111.80802154541016,
+      "learning_rate": 1.8778747557699221e-07,
+      "loss": 0.5381,
+      "step": 930
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 73.63316345214844,
+      "learning_rate": 1.7700461969647468e-07,
+      "loss": 0.5848,
+      "step": 940
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 37.857364654541016,
+      "learning_rate": 1.6647362589758785e-07,
+      "loss": 0.5656,
+      "step": 950
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 48.537506103515625,
+      "learning_rate": 1.5620270593251633e-07,
+      "loss": 0.5997,
+      "step": 960
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 44.8488655090332,
+      "learning_rate": 1.4619986875569246e-07,
+      "loss": 0.6232,
+      "step": 970
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 240.3300323486328,
+      "learning_rate": 1.3647291427865416e-07,
+      "loss": 0.591,
+      "step": 980
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 65.27213287353516,
+      "learning_rate": 1.2702942728790894e-07,
+      "loss": 0.6193,
+      "step": 990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 89.73007202148438,
+      "learning_rate": 1.1787677153054549e-07,
+      "loss": 0.5831,
+      "step": 1000
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 895.947509765625,
+      "learning_rate": 1.0902208397220497e-07,
+      "loss": 0.5912,
+      "step": 1010
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 86.35826110839844,
+      "learning_rate": 1.0047226923189022e-07,
+      "loss": 0.5565,
+      "step": 1020
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 51.44282913208008,
+      "learning_rate": 9.223399419795092e-08,
+      "loss": 0.6402,
+      "step": 1030
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 149.143798828125,
+      "learning_rate": 8.431368282944584e-08,
+      "loss": 0.5588,
+      "step": 1040
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 59.182315826416016,
+      "learning_rate": 7.671751114693103e-08,
+      "loss": 0.5421,
+      "step": 1050
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 45.4121208190918,
+      "learning_rate": 6.945140241658686e-08,
+      "loss": 0.5676,
+      "step": 1060
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 54.07659149169922,
+      "learning_rate": 6.25210225314312e-08,
+      "loss": 0.6404,
+      "step": 1070
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 60.18058776855469,
+      "learning_rate": 5.593177559322776e-08,
+      "loss": 0.5725,
+      "step": 1080
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 204.9486846923828,
+      "learning_rate": 4.968879969852985e-08,
+      "loss": 0.5725,
+      "step": 1090
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 73.43809509277344,
+      "learning_rate": 4.3796962932146966e-08,
+      "loss": 0.6098,
+      "step": 1100
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 96.1000747680664,
+      "learning_rate": 3.8260859571158875e-08,
+      "loss": 0.6195,
+      "step": 1110
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 880.343017578125,
+      "learning_rate": 3.308480650243661e-08,
+      "loss": 0.5907,
+      "step": 1120
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 27.793603897094727,
+      "learning_rate": 2.8272839856463782e-08,
+      "loss": 0.5695,
+      "step": 1130
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 155.69480895996094,
+      "learning_rate": 2.3828711860083672e-08,
+      "loss": 0.6108,
+      "step": 1140
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 50.02077865600586,
+      "learning_rate": 1.9755887910625103e-08,
+      "loss": 0.6049,
+      "step": 1150
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 124.80931854248047,
+      "learning_rate": 1.6057543873690683e-08,
+      "loss": 0.6072,
+      "step": 1160
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 65.33628845214844,
+      "learning_rate": 1.2736563606711381e-08,
+      "loss": 0.4745,
+      "step": 1170
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 73.99946594238281,
+      "learning_rate": 9.795536710202168e-09,
+      "loss": 0.5551,
+      "step": 1180
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 691.7554931640625,
+      "learning_rate": 7.236756508468611e-09,
+      "loss": 0.5737,
+      "step": 1190
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 182.5045623779297,
+      "learning_rate": 5.062218261342121e-09,
+      "loss": 0.5902,
+      "step": 1200
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 49.040260314941406,
+      "learning_rate": 3.273617608336221e-09,
+      "loss": 0.561,
+      "step": 1210
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 79.2325210571289,
+      "learning_rate": 1.872349246437699e-09,
+      "loss": 0.577,
+      "step": 1220
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 584.78759765625,
+      "learning_rate": 8.595058425640011e-10,
+      "loss": 0.5546,
+      "step": 1230
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 117.03710174560547,
+      "learning_rate": 2.3587718153444957e-10,
+      "loss": 0.551,
+      "step": 1240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 157.88687133789062,
+      "learning_rate": 1.9495502197042213e-12,
+      "loss": 0.5674,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0,
+      "step": 1250,
+      "total_flos": 8.611551323462042e+17,
+      "train_loss": 0.6264356197357178,
+      "train_runtime": 11004.0234,
+      "train_samples_per_second": 0.909,
+      "train_steps_per_second": 0.114
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.611551323462042e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..7b270d8
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e080e2f246fe576cabb236e69e1caab9ca159dbf1faeb380f3abea4f0ce00f
+size 7953
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..c112895
Binary files /dev/null and b/training_loss.png differ
diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json
new file mode 100644
index 0000000..b64d80b
--- /dev/null
+++ b/video_preprocessor_config.json
@@ -0,0 +1,86 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..6c49fc6
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833