Upload continuous evaluation checkpoints, batch 21

.gitattributes

@@ -161,3 +161,5 @@ continuous/qwen3/siglip2_b16_224/finetune/tokenizer.json filter=lfs diff=lfs mer
 continuous/qwen3/siglip2_b16_256/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/siglip2_b16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/siglip2_b16_512/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/siglip2_b32_256/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/siglip2_g16_256/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text

continuous/qwen3/siglip2_b32_256/finetune/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37545aa29d660d11b0f6e31a7bb2c1dd73d35d2facb9b107060a1d7d2864349
+size 4275727488

continuous/qwen3/siglip2_b32_256/finetune/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
+  }
+}

continuous/qwen3/siglip2_b32_256/finetune/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/siglip2_b32_256/finetune/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/siglip2_b32_256/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 17.399673461914062,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.2354,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 6.591804027557373,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.8127,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 4.286101341247559,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.4287,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 0.9336678981781006,
+      "learning_rate": 5e-06,
+      "loss": 1.1149,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.7151913642883301,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0194,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.3828166127204895,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.9383,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.3082261383533478,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.8953,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.27994170784950256,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.8928,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.2731216251850128,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.8642,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.2552836239337921,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.8425,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.25362783670425415,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8284,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.2507377564907074,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8375,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.24645845592021942,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8322,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.3063924014568329,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8271,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.3020160496234894,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8128,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.25229260325431824,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8191,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.2253279983997345,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.82,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.2602565586566925,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.847,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.27228793501853943,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8375,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.2722539007663727,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8266,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.2540534734725952,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.823,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.25183430314064026,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8078,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.25876691937446594,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.809,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.2502481937408447,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.8053,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.28648409247398376,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.8212,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.24661049246788025,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8174,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.2507226765155792,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.8051,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.23374055325984955,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.8052,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.24067363142967224,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8223,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.22014552354812622,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.7843,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.23851515352725983,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.7959,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.25283780694007874,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.8012,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.2476215809583664,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.7977,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.24182692170143127,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.8097,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.2637125849723816,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.8113,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.23853637278079987,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.7976,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.2537155747413635,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8246,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.24734370410442352,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.7838,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.2531227767467499,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.7897,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.24763138592243195,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7899,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.25088584423065186,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7807,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.24977953732013702,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.7997,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.24236732721328735,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.7914,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.24034103751182556,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.7858,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.26663368940353394,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7775,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.24048379063606262,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.783,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.24442338943481445,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.788,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.24536138772964478,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7867,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.23274928331375122,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7744,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.23127488791942596,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7812,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.23285885155200958,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7749,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.24818959832191467,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.8047,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.2927766740322113,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7773,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.2529146373271942,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7908,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.22334717214107513,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7951,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.220277339220047,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7944,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.26139405369758606,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.8029,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.2484871745109558,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7852,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.2571246027946472,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.7931,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.22343143820762634,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7855,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.26438459753990173,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.8062,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.2331703156232834,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.7923,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.25048452615737915,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.8069,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.23496891558170319,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.7986,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.22363696992397308,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7555,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.25794801115989685,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7888,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.2612464129924774,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.7958,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.235639750957489,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7641,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.23842231929302216,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7889,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.24016544222831726,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.7951,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.23306572437286377,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7778,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.22067193686962128,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7813,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.2370743602514267,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.785,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.23177359998226166,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7726,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.22503626346588135,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7732,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.23473258316516876,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7651,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.2298913151025772,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7855,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.2337469607591629,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.781,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.24631734192371368,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7654,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.22251255810260773,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7918,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.24737466871738434,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7826,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.2282305508852005,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7767,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.23452317714691162,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7636,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.24238847196102142,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7705,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.2345394343137741,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.783,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.23322804272174835,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7634,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.23534925282001495,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7743,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.22242678701877594,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7695,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.2411479353904724,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7701,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.21286240220069885,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.7733,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.23966029286384583,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7622,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.24952013790607452,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7634,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.24839071929454803,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7496,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.25830206274986267,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7832,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.23659354448318481,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.8002,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.24896244704723358,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7832,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.23089447617530823,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7615,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.23709183931350708,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.77,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.24235139787197113,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7524,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.23997709155082703,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.772,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.23985305428504944,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.7961,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.24867413938045502,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7842,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.23082126677036285,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7824,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.24064454436302185,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7724,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.21552060544490814,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.768,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.22004924714565277,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.7734,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.23214420676231384,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7658,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.21504080295562744,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7916,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.26677122712135315,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7724,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.2535402774810791,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7863,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.24107396602630615,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.7815,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.24459238350391388,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7781,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.24243788421154022,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.756,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.23331725597381592,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7801,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.2225867658853531,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7687,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.2633574604988098,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7924,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.22096796333789825,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.8016,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.2289510816335678,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7777,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.2625699043273926,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7549,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.24434712529182434,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7678,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.24845881760120392,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7723,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.23834969103336334,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7887,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.2456655204296112,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7903,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.22627101838588715,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7614,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.2232583612203598,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7587,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.24342626333236694,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7669,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.26268237829208374,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.751,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.24920368194580078,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7595,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.2400815784931183,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7703,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.2194257527589798,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7709,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.23020091652870178,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7866,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.24179543554782867,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7525,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.2524612545967102,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7628,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.23600129783153534,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7714,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.22734969854354858,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7644,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.2601025104522705,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7804,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.2423330843448639,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.7796,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.22228918969631195,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7863,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.24944756925106049,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7653,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.2322501242160797,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7649,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.24355918169021606,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7787,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.25162234902381897,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.763,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.2590771019458771,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.7781,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.25337323546409607,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7831,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.25051048398017883,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7668,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.2380058616399765,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7704,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.22948655486106873,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7663,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.2408885657787323,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7626,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.23318137228488922,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7684,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.23481528460979462,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.778,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.239055335521698,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7708,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.2351677566766739,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.777,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.23971226811408997,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7798,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.2263016700744629,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7836,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.23395346105098724,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7715,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.2268238365650177,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7877,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.2485288679599762,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.7813,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.24543245136737823,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7741,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.21275216341018677,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.7746,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.22995324432849884,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7637,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.21815559267997742,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7451,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.2391642928123474,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7466,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.22657158970832825,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7755,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.2139272689819336,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7647,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.24125619232654572,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7743,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.23155874013900757,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7547,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.24198976159095764,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7789,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.24235251545906067,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7727,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.2453235387802124,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7631,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.2163388431072235,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7608,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.24408413469791412,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7771,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.24100986123085022,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7658,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.23548093438148499,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.77,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.2307794839143753,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7699,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.24314947426319122,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7664,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.2246536761522293,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7534,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.2495093196630478,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.7966,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.23497729003429413,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7842,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.23533274233341217,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7935,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.23095090687274933,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7569,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.24031032621860504,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7478,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.22550693154335022,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.7739,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.22942475974559784,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7629,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.25339892506599426,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7673,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.24319203197956085,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7807,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.2351994514465332,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7709,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.23981444537639618,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7684,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.22511078417301178,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7761,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.2527197599411011,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7602,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.23869724571704865,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7657,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.2273840606212616,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7655,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.23502278327941895,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.759,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.2509417235851288,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7754,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.23595649003982544,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7857,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.2405194342136383,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7738,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.2555826008319855,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7893,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.2360113561153412,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7787,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.253983736038208,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7776,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.25266537070274353,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7724,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.23060013353824615,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7636,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.22952835261821747,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7716,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.225642591714859,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7572,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.22994686663150787,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7452,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.2358560413122177,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7607,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.22654050588607788,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.765,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.21720260381698608,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7506,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.24841250479221344,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7723,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.22628287971019745,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7515,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.23611700534820557,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7762,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.22883404791355133,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7618,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.2296970933675766,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7738,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.23220308125019073,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7763,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.24289755523204803,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7637,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.2296438366174698,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7655,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.23566603660583496,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7584,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.2291286289691925,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7769,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.22509491443634033,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7755,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.2284921556711197,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7673,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.22407086193561554,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.7728,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.2546941936016083,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7678,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.2301274687051773,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7404,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.21973896026611328,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7733,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.23894405364990234,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7666,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.22854135930538177,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.7789,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.23299013078212738,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7632,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.23715561628341675,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7511,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.22843122482299805,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7617,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.2291041612625122,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7729,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.2273050993680954,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.7757,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.21896745264530182,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7528,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.21967807412147522,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7654,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.2276875227689743,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7706,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.23036779463291168,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7766,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.2351595014333725,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7703,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.22424428164958954,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7512,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.22707751393318176,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7639,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.26067599654197693,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7549,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.23136737942695618,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7641,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.2342597246170044,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7767,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.2491629272699356,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7773,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.2260773777961731,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7597,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.22122891247272491,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7816,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.23265348374843597,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.779,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.24228999018669128,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7654,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.2471848726272583,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7626,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.23711708188056946,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7856,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.2494245171546936,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7793,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.2378743439912796,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7611,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.28325748443603516,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7652,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.22608216106891632,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7608,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.22855421900749207,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7538,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.24217742681503296,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7774,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.22862949967384338,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7605,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.22079889476299286,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7668,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.21934540569782257,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7737,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.2372514009475708,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.7648,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.23096345365047455,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7544,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.21233251690864563,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.747,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.23853935301303864,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7789,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 3.794160072259535e+18,
+      "train_loss": 0.793988571930813,
+      "train_runtime": 9546.4625,
+      "train_samples_per_second": 69.649,
+      "train_steps_per_second": 0.272
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.794160072259535e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/siglip2_b32_256/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685c74e058c3c2446a54406f7db78a7635b094270e58b561656f4b34a74697d3
+size 6136

continuous/qwen3/siglip2_b32_256/pretrain/config.json

@@ -0,0 +1,60 @@
+{
+  "_attn_implementation_autoset": true,
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 768,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-B-32-SigLIP2-256",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_b32_256.npz",
+  "vocab_size": 151936
+}

continuous/qwen3/siglip2_b32_256/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e8fdc72ccae35673a26182997520a165bea64d76b7594439ef7bcf9a5e38c7
+size 23087160

continuous/qwen3/siglip2_b32_256/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 11.553814888000488,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 8.809,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.778229296207428,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 5.0932,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.36950281262397766,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 4.688,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.4482980966567993,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 4.5681,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.23389378190040588,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.4812,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.21635329723358154,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.3973,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.16594457626342773,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.3182,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.24311694502830505,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.271,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.24172727763652802,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.2226,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.21324187517166138,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.1978,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.26748010516166687,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.1683,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.24543431401252747,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.1493,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.22930380702018738,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.1071,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.25810977816581726,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.0714,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.24746555089950562,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.0566,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.20915043354034424,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.0366,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.1935897022485733,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.0192,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.25095897912979126,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.014,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.21385681629180908,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.19638928771018982,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 3.9864,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.18699896335601807,
+      "learning_rate": 0.00072685988254984,
+      "loss": 3.9754,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.1926472783088684,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 3.9902,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.18664662539958954,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 3.9824,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.199570432305336,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 3.972,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.1901761293411255,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 3.959,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.19408263266086578,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 3.9668,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.1944284290075302,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 3.9529,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.19082660973072052,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 3.9488,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.20726558566093445,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 3.9421,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.20237471163272858,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 3.9414,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.18084080517292023,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 3.9521,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.18834659457206726,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 3.9425,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.19897101819515228,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 3.9294,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.18635424971580505,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 3.9276,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.18816138803958893,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 3.931,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.19665978848934174,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 3.9376,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.18084004521369934,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 3.9264,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.1921074092388153,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 3.9341,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.19048257172107697,
+      "learning_rate": 0.000208323983828828,
+      "loss": 3.9176,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.17172680795192719,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 3.9187,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.17804954946041107,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 3.9255,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.17462874948978424,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 3.9171,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.1638706922531128,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 3.919,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.17891941964626312,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 3.9229,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.16560037434101105,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 3.9183,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.17382565140724182,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 3.9087,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.15809394419193268,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 3.8987,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.1641259789466858,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 3.9057,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.16079506278038025,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 3.9109,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.16936840116977692,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 3.9189,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.15905730426311493,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 3.9105,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.1630670726299286,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 3.9031,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.16333240270614624,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 3.9064,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.1651180535554886,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 3.9086,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 3.11510467111551e+17,
+      "train_loss": 4.134718515238631,
+      "train_runtime": 5626.1192,
+      "train_samples_per_second": 99.203,
+      "train_steps_per_second": 0.097
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.11510467111551e+17,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/siglip2_g16_256/finetune/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

continuous/qwen3/siglip2_g16_256/finetune/config.json

@@ -0,0 +1,59 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1536,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-256",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_256.npz",
+  "vocab_size": 151936
+}

continuous/qwen3/siglip2_g16_256/finetune/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

continuous/qwen3/siglip2_g16_256/finetune/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef0a22464875cc0e80a0948dedb4bc9e7a84244a0d70f0abf675d4ba6c5f514
+size 4993181032

continuous/qwen3/siglip2_g16_256/finetune/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f93134164b4137b036b4698b369830e4ed801ad4ed217303c1fe5c9a74f678
+size 1426115616

continuous/qwen3/siglip2_g16_256/finetune/model.safetensors.index.json

@@ -0,0 +1,820 @@
+{
+  "metadata": {
+    "total_size": 6419192832
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.kv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.kv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.latent": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.q.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.attn_pool.q.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.28.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.29.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.30.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.31.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.32.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.33.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.34.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.35.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.36.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.37.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.38.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.39.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.trunk.pos_embed": "model-00001-of-00002.safetensors"
+  }
+}

continuous/qwen3/siglip2_g16_256/finetune/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
+  }
+}

continuous/qwen3/siglip2_g16_256/finetune/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/siglip2_g16_256/finetune/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/siglip2_g16_256/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 17.001901626586914,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.3493,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 6.229721546173096,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.8167,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 4.144705295562744,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.435,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 0.8807482719421387,
+      "learning_rate": 5e-06,
+      "loss": 1.1309,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.799134373664856,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0352,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.38394564390182495,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.9535,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.3446131944656372,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9085,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.2996153235435486,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.904,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.29100438952445984,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.8741,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.26356300711631775,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.8523,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.2703222930431366,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8346,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.26017993688583374,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8419,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.26330888271331787,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8363,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.2776448130607605,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8303,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.31004276871681213,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8124,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.2719884514808655,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8168,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.23566848039627075,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.2728114128112793,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8384,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.26539143919944763,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8281,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.28642627596855164,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8139,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.2630111277103424,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8123,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.26716381311416626,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.7919,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.2509663701057434,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.7927,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.2625228464603424,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.7872,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.28808584809303284,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.8045,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.2488638311624527,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.7959,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.2685545086860657,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.7846,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.24230284988880157,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.783,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.2452620565891266,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8001,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.23475830256938934,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.7639,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.23735973238945007,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.7724,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.24468407034873962,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.7775,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.2622361481189728,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.7752,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.26173385977745056,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.7851,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.2681578993797302,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.7872,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.2455439418554306,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.7728,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.23979845643043518,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8014,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.25024375319480896,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.7603,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.2444925606250763,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.7625,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.24074195325374603,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7621,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.255297988653183,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7514,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.24500124156475067,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.7741,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.25259312987327576,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.7654,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.24066470563411713,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.7574,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.2433016300201416,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7488,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.23660610616207123,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.7559,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.239033043384552,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.7595,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.2516966462135315,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7562,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.23025453090667725,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7465,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.22530943155288696,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7566,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.2350301295518875,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7453,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.24454602599143982,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.7762,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.25719428062438965,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7497,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.251338928937912,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7611,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.23038256168365479,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7687,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.22519467771053314,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7677,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.274303674697876,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.77,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.24075013399124146,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7558,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.24795418977737427,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.7617,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.23341839015483856,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7547,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.2543427646160126,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.7737,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.24077439308166504,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.7602,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.23847205936908722,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.7756,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.23045678436756134,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.7716,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.22845575213432312,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.726,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.25592362880706787,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7551,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.2521989643573761,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.7669,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.22016696631908417,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7318,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.2366998791694641,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7561,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.2434193193912506,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.7634,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.24080383777618408,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7466,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.22342535853385925,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7526,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.23930536210536957,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.7522,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.2358589917421341,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7403,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.2233259081840515,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7433,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.24245792627334595,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7327,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.23390763998031616,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.753,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.23205864429473877,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.7496,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.24009808897972107,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7318,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.2217990756034851,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7573,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.23997965455055237,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7481,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.22609564661979675,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7425,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.23400382697582245,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7297,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.23760783672332764,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.7353,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.22984182834625244,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7508,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.23052488267421722,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7296,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.2334418147802353,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7409,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.22397293150424957,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7334,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.23403488099575043,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7389,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.21578341722488403,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.7366,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.2411818653345108,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7273,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.2683514356613159,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7296,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.2511104643344879,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7157,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.2635204792022705,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.75,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.2312111109495163,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.7682,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.24828431010246277,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7497,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.2422676384449005,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7254,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.23881083726882935,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.738,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.230425164103508,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7141,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.2359900176525116,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.7383,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.23533719778060913,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.7626,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.24762554466724396,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7474,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.23720742762088776,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7472,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.2358945906162262,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.735,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.21536287665367126,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.7325,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.2226155698299408,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.7366,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.2438584715127945,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7285,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.22369422018527985,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7561,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.2628036439418793,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7352,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.24942883849143982,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7492,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.23051981627941132,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.744,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.24378223717212677,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7403,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.23827357590198517,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7193,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.23982089757919312,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7441,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.2225942760705948,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.728,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.2648972272872925,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.756,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.24106530845165253,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.7645,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.2271379828453064,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7413,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.24168920516967773,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7164,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.2479087859392166,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7324,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.24210581183433533,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7363,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.23122821748256683,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7513,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.23960818350315094,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7541,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.23006169497966766,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7247,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.21883662045001984,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7196,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.2495671510696411,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7309,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.2659909725189209,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7133,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.24770602583885193,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7228,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.24408607184886932,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7323,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.2252800315618515,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7323,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.22551053762435913,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7526,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.23827384412288666,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7139,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.25604939460754395,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7225,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.23150549829006195,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7339,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.2305677831172943,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7299,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.25864893198013306,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7413,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.23968178033828735,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.7369,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.23062781989574432,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7473,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.24722972512245178,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7258,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.2278379201889038,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7273,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.24267904460430145,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7427,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.25002920627593994,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7231,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.26561474800109863,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.74,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.25508132576942444,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7465,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.253028929233551,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7284,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.24765168130397797,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7317,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.23390109837055206,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7248,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.23121578991413116,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.726,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.23322390019893646,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7287,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.2293824553489685,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.7423,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.23473228514194489,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7339,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.23674845695495605,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.7404,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.2276161164045334,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.741,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.23243913054466248,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.7491,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.22110994160175323,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7323,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.22203461825847626,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7446,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.2367440015077591,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.7447,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.24316050112247467,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7336,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.21711480617523193,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.7364,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.22637951374053955,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7266,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.21716508269309998,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7072,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.24472598731517792,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7067,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.22630982100963593,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7373,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.2169499546289444,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7244,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.23345161974430084,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7363,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.22827032208442688,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7178,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.2373630851507187,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7421,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.2473866045475006,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7318,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.24320538341999054,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7233,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.2140652984380722,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7197,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.24802044034004211,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7386,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.24069352447986603,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7285,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.23430080711841583,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.727,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.22492371499538422,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7291,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.23735490441322327,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7289,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.22577188909053802,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7115,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.24922025203704834,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.7587,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.23234711587429047,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7439,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.22324715554714203,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.7542,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.23861061036586761,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7191,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.23271702229976654,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.708,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.22485175728797913,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.7326,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.2284117043018341,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7222,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.2401348501443863,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.727,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.24746112525463104,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7416,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.2300429493188858,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7332,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.24605917930603027,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7304,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.22721430659294128,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.738,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.23618122935295105,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7204,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.24128296971321106,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7279,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.223703071475029,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7255,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.23935826122760773,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.72,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.24560494720935822,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7329,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.23439110815525055,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.748,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.24893862009048462,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7359,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.250186026096344,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7504,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.23569217324256897,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7403,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.2459494024515152,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7367,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.24924947321414948,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7341,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.2330208420753479,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7246,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.22592443227767944,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7343,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.22527796030044556,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7173,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.22940486669540405,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7034,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.22995170950889587,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7205,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.22645732760429382,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.726,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.21724657714366913,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7079,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.24151508510112762,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7294,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.227914959192276,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7118,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.22566641867160797,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7361,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.22741428017616272,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7227,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.23530197143554688,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7361,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.23227599263191223,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.739,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.2425776720046997,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7239,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.2367342710494995,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7263,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.24439552426338196,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7189,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.22101765871047974,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7363,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.22736753523349762,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7337,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.23716013133525848,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7287,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.23001007735729218,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.731,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.2497047334909439,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7297,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.23403166234493256,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7009,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.22131632268428802,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7334,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.2327759563922882,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7281,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.224646657705307,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.7423,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.22365643084049225,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.721,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.23415498435497284,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7115,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.23012809455394745,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7181,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.22955836355686188,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7372,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.22866865992546082,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.7322,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.21626031398773193,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.712,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.22158823907375336,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7236,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.223424032330513,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7276,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.23071041703224182,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7358,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.2371523231267929,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7279,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.23269866406917572,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7123,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.22988665103912354,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7228,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.2557651698589325,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7137,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.22682537138462067,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7255,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.22415465116500854,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7394,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.24386507272720337,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7387,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.22977995872497559,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7201,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.22498345375061035,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7392,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.23391138017177582,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.7401,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.2422756552696228,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7251,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.2521568834781647,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.721,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.23510518670082092,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7444,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.2455679178237915,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7395,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.24016296863555908,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7216,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.27958935499191284,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7252,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.22360941767692566,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7221,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.2370338886976242,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.717,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.23741945624351501,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.741,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.22775302827358246,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7194,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.22790370881557465,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7268,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.22112274169921875,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7317,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.23539648950099945,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.723,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.23230291903018951,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7138,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.20932652056217194,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7046,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.23958426713943481,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7413,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 6.483685924281516e+18,
+      "train_loss": 0.7619180380035742,
+      "train_runtime": 10999.1185,
+      "train_samples_per_second": 60.451,
+      "train_steps_per_second": 0.236
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.483685924281516e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/siglip2_g16_256/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad555491d15692794587eda98250fdf2718127e20a91378b8ef14c7faf0a4ce6
+size 6136

continuous/qwen3/siglip2_g16_256/pretrain/config.json

@@ -0,0 +1,60 @@
+{
+  "_attn_implementation_autoset": true,
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1536,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-256",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_256.npz",
+  "vocab_size": 151936
+}

continuous/qwen3/siglip2_g16_256/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06e2df1524efe08116c337e0bab52978aa9b4a3f8cda8324c07cf8b6b13caf1
+size 29378616

continuous/qwen3/siglip2_g16_256/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 1.2958297729492188,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 8.303,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.39561355113983154,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 5.6128,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.07792200893163681,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 4.8896,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.06107151508331299,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 4.746,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.040635768324136734,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.6865,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.05009353160858154,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.6559,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.07224445790052414,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.6225,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.038170699030160904,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.6063,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.10109762102365494,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.5797,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.12039484083652496,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.5678,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.09555362164974213,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.542,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.1112549751996994,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.5243,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.16773277521133423,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.503,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.09333983063697815,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.4758,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.08428622037172318,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.4551,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.14544250071048737,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.4296,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.05115625262260437,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.4032,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.06884494423866272,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.3758,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07790065556764603,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.354,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.14693310856819153,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 4.3177,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.11695116013288498,
+      "learning_rate": 0.00072685988254984,
+      "loss": 4.2945,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.0838383361697197,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 4.2919,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.07042070478200912,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 4.2738,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.0831403061747551,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 4.247,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.13451963663101196,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 4.2177,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.12985263764858246,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 4.2234,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.09226924180984497,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 4.1904,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.10685190558433533,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 4.177,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.11171908676624298,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 4.1511,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.09870519489049911,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 4.1391,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.09060350805521011,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 4.1459,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.10865882784128189,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 4.1327,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.08293815702199936,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 4.1027,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.0752464011311531,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 4.097,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.09780288487672806,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 4.0933,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.09050949662923813,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 4.0979,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.08397818356752396,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 4.0727,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.08161485940217972,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 4.0806,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.08063549548387527,
+      "learning_rate": 0.000208323983828828,
+      "loss": 4.0579,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.0913953110575676,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 4.0552,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.07131054252386093,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 4.0491,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.08087854087352753,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 4.0383,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.07450354844331741,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 4.0391,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08614518493413925,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 4.0424,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.08040382713079453,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 4.0277,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.07280175387859344,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 4.0173,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.07893404364585876,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 4.0037,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.07581944018602371,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 4.011,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.07082457840442657,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 4.0102,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.07377403229475021,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 4.0219,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.07345166057348251,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 4.0128,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.06671890616416931,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 4.0012,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.06810891628265381,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 4.0045,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.07468347251415253,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 4.0089,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 4.93743650732245e+17,
+      "train_loss": 4.350407224182689,
+      "train_runtime": 5643.4515,
+      "train_samples_per_second": 98.898,
+      "train_steps_per_second": 0.097
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.93743650732245e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/siglip2_g16_384/finetune/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

continuous/qwen3/siglip2_g16_384/finetune/config.json

@@ -0,0 +1,59 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1536,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-384",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_384.npz",
+  "vocab_size": 151936
+}

continuous/qwen3/siglip2_g16_384/finetune/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

continuous/qwen3/siglip2_g16_384/finetune/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d30766b37b7b5e0185652ddb1754f6e20181d1955e6df07fe90ddc0e2e5274
+size 4994164072