Add files using upload-large-folder tool

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.55.0"
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1903904128,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/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
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-1309/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-374/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-374/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-374/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1903904128,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-374/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
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-374/trainer_state.json

@@ -0,0 +1,2652 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 374,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0053475935828877,
+      "grad_norm": 7.882880210876465,
+      "learning_rate": 5e-06,
+      "loss": 1.0432,
+      "step": 1
+    },
+    {
+      "epoch": 0.0106951871657754,
+      "grad_norm": 85.96701049804688,
+      "learning_rate": 4.99999647201733e-06,
+      "loss": 2.7549,
+      "step": 2
+    },
+    {
+      "epoch": 0.016042780748663103,
+      "grad_norm": 10.169342041015625,
+      "learning_rate": 4.999985888079276e-06,
+      "loss": 0.9714,
+      "step": 3
+    },
+    {
+      "epoch": 0.0213903743315508,
+      "grad_norm": 22.814661026000977,
+      "learning_rate": 4.999968248215712e-06,
+      "loss": 2.4815,
+      "step": 4
+    },
+    {
+      "epoch": 0.026737967914438502,
+      "grad_norm": 12.63342571258545,
+      "learning_rate": 4.999943552476422e-06,
+      "loss": 2.2202,
+      "step": 5
+    },
+    {
+      "epoch": 0.03208556149732621,
+      "grad_norm": 20.007993698120117,
+      "learning_rate": 4.999911800931108e-06,
+      "loss": 1.6794,
+      "step": 6
+    },
+    {
+      "epoch": 0.0374331550802139,
+      "grad_norm": 4.85478401184082,
+      "learning_rate": 4.999872993669387e-06,
+      "loss": 0.8276,
+      "step": 7
+    },
+    {
+      "epoch": 0.0427807486631016,
+      "grad_norm": 14.239628791809082,
+      "learning_rate": 4.999827130800785e-06,
+      "loss": 1.7329,
+      "step": 8
+    },
+    {
+      "epoch": 0.0481283422459893,
+      "grad_norm": 58.86729431152344,
+      "learning_rate": 4.999774212454746e-06,
+      "loss": 2.2497,
+      "step": 9
+    },
+    {
+      "epoch": 0.053475935828877004,
+      "grad_norm": 10.084229469299316,
+      "learning_rate": 4.999714238780626e-06,
+      "loss": 1.7491,
+      "step": 10
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 19.655241012573242,
+      "learning_rate": 4.999647209947694e-06,
+      "loss": 1.6772,
+      "step": 11
+    },
+    {
+      "epoch": 0.06417112299465241,
+      "grad_norm": 11.366874694824219,
+      "learning_rate": 4.999573126145132e-06,
+      "loss": 1.6385,
+      "step": 12
+    },
+    {
+      "epoch": 0.06951871657754011,
+      "grad_norm": 13.70612621307373,
+      "learning_rate": 4.999491987582032e-06,
+      "loss": 1.2249,
+      "step": 13
+    },
+    {
+      "epoch": 0.0748663101604278,
+      "grad_norm": 10.751424789428711,
+      "learning_rate": 4.999403794487399e-06,
+      "loss": 1.9696,
+      "step": 14
+    },
+    {
+      "epoch": 0.08021390374331551,
+      "grad_norm": 8.416720390319824,
+      "learning_rate": 4.999308547110147e-06,
+      "loss": 1.1547,
+      "step": 15
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": 7.383161544799805,
+      "learning_rate": 4.9992062457191005e-06,
+      "loss": 1.2688,
+      "step": 16
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 12.522323608398438,
+      "learning_rate": 4.999096890602996e-06,
+      "loss": 1.2582,
+      "step": 17
+    },
+    {
+      "epoch": 0.0962566844919786,
+      "grad_norm": 8.477874755859375,
+      "learning_rate": 4.998980482070473e-06,
+      "loss": 1.3691,
+      "step": 18
+    },
+    {
+      "epoch": 0.10160427807486631,
+      "grad_norm": 7.812965393066406,
+      "learning_rate": 4.998857020450084e-06,
+      "loss": 1.8373,
+      "step": 19
+    },
+    {
+      "epoch": 0.10695187165775401,
+      "grad_norm": 11.452326774597168,
+      "learning_rate": 4.998726506090283e-06,
+      "loss": 1.0001,
+      "step": 20
+    },
+    {
+      "epoch": 0.11229946524064172,
+      "grad_norm": 29.964250564575195,
+      "learning_rate": 4.998588939359435e-06,
+      "loss": 0.8301,
+      "step": 21
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 9.666940689086914,
+      "learning_rate": 4.998444320645803e-06,
+      "loss": 1.5351,
+      "step": 22
+    },
+    {
+      "epoch": 0.12299465240641712,
+      "grad_norm": 17.385601043701172,
+      "learning_rate": 4.998292650357558e-06,
+      "loss": 1.236,
+      "step": 23
+    },
+    {
+      "epoch": 0.12834224598930483,
+      "grad_norm": 22.89784049987793,
+      "learning_rate": 4.998133928922773e-06,
+      "loss": 1.9185,
+      "step": 24
+    },
+    {
+      "epoch": 0.13368983957219252,
+      "grad_norm": 14.70427417755127,
+      "learning_rate": 4.99796815678942e-06,
+      "loss": 1.026,
+      "step": 25
+    },
+    {
+      "epoch": 0.13903743315508021,
+      "grad_norm": 12.778743743896484,
+      "learning_rate": 4.997795334425372e-06,
+      "loss": 1.565,
+      "step": 26
+    },
+    {
+      "epoch": 0.1443850267379679,
+      "grad_norm": 12.15316390991211,
+      "learning_rate": 4.997615462318403e-06,
+      "loss": 1.6375,
+      "step": 27
+    },
+    {
+      "epoch": 0.1497326203208556,
+      "grad_norm": 17.102373123168945,
+      "learning_rate": 4.997428540976177e-06,
+      "loss": 1.3189,
+      "step": 28
+    },
+    {
+      "epoch": 0.15508021390374332,
+      "grad_norm": 16.350406646728516,
+      "learning_rate": 4.997234570926263e-06,
+      "loss": 0.9817,
+      "step": 29
+    },
+    {
+      "epoch": 0.16042780748663102,
+      "grad_norm": 3.93855357170105,
+      "learning_rate": 4.997033552716116e-06,
+      "loss": 0.8303,
+      "step": 30
+    },
+    {
+      "epoch": 0.1657754010695187,
+      "grad_norm": 8.227142333984375,
+      "learning_rate": 4.9968254869130885e-06,
+      "loss": 0.8079,
+      "step": 31
+    },
+    {
+      "epoch": 0.1711229946524064,
+      "grad_norm": 2.515702962875366,
+      "learning_rate": 4.996610374104422e-06,
+      "loss": 0.6338,
+      "step": 32
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 2.707545757293701,
+      "learning_rate": 4.9963882148972475e-06,
+      "loss": 1.1573,
+      "step": 33
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.4493415355682373,
+      "learning_rate": 4.996159009918586e-06,
+      "loss": 0.9202,
+      "step": 34
+    },
+    {
+      "epoch": 0.18716577540106952,
+      "grad_norm": 5.61538553237915,
+      "learning_rate": 4.9959227598153395e-06,
+      "loss": 1.1953,
+      "step": 35
+    },
+    {
+      "epoch": 0.1925133689839572,
+      "grad_norm": 5.1660919189453125,
+      "learning_rate": 4.9956794652542994e-06,
+      "loss": 1.4263,
+      "step": 36
+    },
+    {
+      "epoch": 0.19786096256684493,
+      "grad_norm": 8.260229110717773,
+      "learning_rate": 4.9954291269221364e-06,
+      "loss": 0.8832,
+      "step": 37
+    },
+    {
+      "epoch": 0.20320855614973263,
+      "grad_norm": 7.102392673492432,
+      "learning_rate": 4.995171745525401e-06,
+      "loss": 1.4082,
+      "step": 38
+    },
+    {
+      "epoch": 0.20855614973262032,
+      "grad_norm": 6.636760234832764,
+      "learning_rate": 4.994907321790524e-06,
+      "loss": 1.2018,
+      "step": 39
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": 3.7511961460113525,
+      "learning_rate": 4.994635856463811e-06,
+      "loss": 0.8592,
+      "step": 40
+    },
+    {
+      "epoch": 0.2192513368983957,
+      "grad_norm": 6.456974029541016,
+      "learning_rate": 4.994357350311441e-06,
+      "loss": 1.4007,
+      "step": 41
+    },
+    {
+      "epoch": 0.22459893048128343,
+      "grad_norm": 8.8861083984375,
+      "learning_rate": 4.994071804119467e-06,
+      "loss": 1.0535,
+      "step": 42
+    },
+    {
+      "epoch": 0.22994652406417113,
+      "grad_norm": 5.479948043823242,
+      "learning_rate": 4.993779218693811e-06,
+      "loss": 1.5014,
+      "step": 43
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 4.117030620574951,
+      "learning_rate": 4.99347959486026e-06,
+      "loss": 0.8533,
+      "step": 44
+    },
+    {
+      "epoch": 0.24064171122994651,
+      "grad_norm": 5.722311973571777,
+      "learning_rate": 4.99317293346447e-06,
+      "loss": 0.746,
+      "step": 45
+    },
+    {
+      "epoch": 0.24598930481283424,
+      "grad_norm": 5.541464805603027,
+      "learning_rate": 4.992859235371958e-06,
+      "loss": 0.6629,
+      "step": 46
+    },
+    {
+      "epoch": 0.25133689839572193,
+      "grad_norm": 5.9008941650390625,
+      "learning_rate": 4.992538501468101e-06,
+      "loss": 0.7509,
+      "step": 47
+    },
+    {
+      "epoch": 0.25668449197860965,
+      "grad_norm": 7.691971302032471,
+      "learning_rate": 4.992210732658132e-06,
+      "loss": 1.1433,
+      "step": 48
+    },
+    {
+      "epoch": 0.2620320855614973,
+      "grad_norm": 5.942367076873779,
+      "learning_rate": 4.991875929867143e-06,
+      "loss": 1.2333,
+      "step": 49
+    },
+    {
+      "epoch": 0.26737967914438504,
+      "grad_norm": 5.679361820220947,
+      "learning_rate": 4.991534094040077e-06,
+      "loss": 0.7365,
+      "step": 50
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 2.5231547355651855,
+      "learning_rate": 4.991185226141726e-06,
+      "loss": 0.7526,
+      "step": 51
+    },
+    {
+      "epoch": 0.27807486631016043,
+      "grad_norm": 5.636293888092041,
+      "learning_rate": 4.990829327156729e-06,
+      "loss": 0.9582,
+      "step": 52
+    },
+    {
+      "epoch": 0.28342245989304815,
+      "grad_norm": 1.912962555885315,
+      "learning_rate": 4.990466398089571e-06,
+      "loss": 0.7778,
+      "step": 53
+    },
+    {
+      "epoch": 0.2887700534759358,
+      "grad_norm": 3.1763367652893066,
+      "learning_rate": 4.99009643996458e-06,
+      "loss": 0.5196,
+      "step": 54
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 3.7918894290924072,
+      "learning_rate": 4.989719453825918e-06,
+      "loss": 0.6574,
+      "step": 55
+    },
+    {
+      "epoch": 0.2994652406417112,
+      "grad_norm": 2.7639365196228027,
+      "learning_rate": 4.989335440737587e-06,
+      "loss": 0.6746,
+      "step": 56
+    },
+    {
+      "epoch": 0.3048128342245989,
+      "grad_norm": 2.7929069995880127,
+      "learning_rate": 4.9889444017834185e-06,
+      "loss": 0.7843,
+      "step": 57
+    },
+    {
+      "epoch": 0.31016042780748665,
+      "grad_norm": 2.1778111457824707,
+      "learning_rate": 4.988546338067078e-06,
+      "loss": 0.8516,
+      "step": 58
+    },
+    {
+      "epoch": 0.3155080213903743,
+      "grad_norm": 3.2910144329071045,
+      "learning_rate": 4.988141250712053e-06,
+      "loss": 0.9807,
+      "step": 59
+    },
+    {
+      "epoch": 0.32085561497326204,
+      "grad_norm": 2.2481296062469482,
+      "learning_rate": 4.987729140861657e-06,
+      "loss": 0.8325,
+      "step": 60
+    },
+    {
+      "epoch": 0.32620320855614976,
+      "grad_norm": 2.7023563385009766,
+      "learning_rate": 4.987310009679023e-06,
+      "loss": 0.849,
+      "step": 61
+    },
+    {
+      "epoch": 0.3315508021390374,
+      "grad_norm": 4.397724151611328,
+      "learning_rate": 4.986883858347101e-06,
+      "loss": 0.7713,
+      "step": 62
+    },
+    {
+      "epoch": 0.33689839572192515,
+      "grad_norm": 5.798337459564209,
+      "learning_rate": 4.986450688068655e-06,
+      "loss": 0.5797,
+      "step": 63
+    },
+    {
+      "epoch": 0.3422459893048128,
+      "grad_norm": 2.813290596008301,
+      "learning_rate": 4.986010500066258e-06,
+      "loss": 0.7509,
+      "step": 64
+    },
+    {
+      "epoch": 0.34759358288770054,
+      "grad_norm": 2.072097063064575,
+      "learning_rate": 4.985563295582292e-06,
+      "loss": 0.6999,
+      "step": 65
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 2.612741708755493,
+      "learning_rate": 4.98510907587894e-06,
+      "loss": 0.8122,
+      "step": 66
+    },
+    {
+      "epoch": 0.3582887700534759,
+      "grad_norm": 3.386460304260254,
+      "learning_rate": 4.984647842238185e-06,
+      "loss": 1.0947,
+      "step": 67
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.876708745956421,
+      "learning_rate": 4.984179595961806e-06,
+      "loss": 0.5697,
+      "step": 68
+    },
+    {
+      "epoch": 0.3689839572192513,
+      "grad_norm": 2.664186716079712,
+      "learning_rate": 4.983704338371375e-06,
+      "loss": 0.6758,
+      "step": 69
+    },
+    {
+      "epoch": 0.37433155080213903,
+      "grad_norm": 2.482248544692993,
+      "learning_rate": 4.983222070808255e-06,
+      "loss": 0.5781,
+      "step": 70
+    },
+    {
+      "epoch": 0.37967914438502676,
+      "grad_norm": 3.0911777019500732,
+      "learning_rate": 4.982732794633588e-06,
+      "loss": 0.9204,
+      "step": 71
+    },
+    {
+      "epoch": 0.3850267379679144,
+      "grad_norm": 1.8997831344604492,
+      "learning_rate": 4.982236511228301e-06,
+      "loss": 0.7021,
+      "step": 72
+    },
+    {
+      "epoch": 0.39037433155080214,
+      "grad_norm": 3.3967373371124268,
+      "learning_rate": 4.981733221993099e-06,
+      "loss": 1.1137,
+      "step": 73
+    },
+    {
+      "epoch": 0.39572192513368987,
+      "grad_norm": 3.588660717010498,
+      "learning_rate": 4.981222928348456e-06,
+      "loss": 0.9182,
+      "step": 74
+    },
+    {
+      "epoch": 0.40106951871657753,
+      "grad_norm": 2.569033145904541,
+      "learning_rate": 4.98070563173462e-06,
+      "loss": 0.8233,
+      "step": 75
+    },
+    {
+      "epoch": 0.40641711229946526,
+      "grad_norm": 2.371328592300415,
+      "learning_rate": 4.980181333611601e-06,
+      "loss": 0.6619,
+      "step": 76
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 2.558084487915039,
+      "learning_rate": 4.979650035459171e-06,
+      "loss": 0.6363,
+      "step": 77
+    },
+    {
+      "epoch": 0.41711229946524064,
+      "grad_norm": 2.783773183822632,
+      "learning_rate": 4.9791117387768575e-06,
+      "loss": 0.9989,
+      "step": 78
+    },
+    {
+      "epoch": 0.42245989304812837,
+      "grad_norm": 1.7847092151641846,
+      "learning_rate": 4.978566445083942e-06,
+      "loss": 0.5506,
+      "step": 79
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 1.6320348978042603,
+      "learning_rate": 4.978014155919455e-06,
+      "loss": 0.6413,
+      "step": 80
+    },
+    {
+      "epoch": 0.43315508021390375,
+      "grad_norm": 2.219749927520752,
+      "learning_rate": 4.977454872842169e-06,
+      "loss": 0.6972,
+      "step": 81
+    },
+    {
+      "epoch": 0.4385026737967914,
+      "grad_norm": 2.1894898414611816,
+      "learning_rate": 4.976888597430597e-06,
+      "loss": 0.8983,
+      "step": 82
+    },
+    {
+      "epoch": 0.44385026737967914,
+      "grad_norm": 3.926828384399414,
+      "learning_rate": 4.976315331282985e-06,
+      "loss": 0.8303,
+      "step": 83
+    },
+    {
+      "epoch": 0.44919786096256686,
+      "grad_norm": 2.039591073989868,
+      "learning_rate": 4.9757350760173144e-06,
+      "loss": 0.6847,
+      "step": 84
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 2.611128091812134,
+      "learning_rate": 4.975147833271288e-06,
+      "loss": 0.8938,
+      "step": 85
+    },
+    {
+      "epoch": 0.45989304812834225,
+      "grad_norm": 3.209350347518921,
+      "learning_rate": 4.974553604702332e-06,
+      "loss": 0.6694,
+      "step": 86
+    },
+    {
+      "epoch": 0.46524064171123,
+      "grad_norm": 1.7005733251571655,
+      "learning_rate": 4.973952391987589e-06,
+      "loss": 0.7588,
+      "step": 87
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 2.1625118255615234,
+      "learning_rate": 4.9733441968239125e-06,
+      "loss": 0.9778,
+      "step": 88
+    },
+    {
+      "epoch": 0.47593582887700536,
+      "grad_norm": 2.2802696228027344,
+      "learning_rate": 4.972729020927866e-06,
+      "loss": 0.587,
+      "step": 89
+    },
+    {
+      "epoch": 0.48128342245989303,
+      "grad_norm": 1.9127228260040283,
+      "learning_rate": 4.97210686603571e-06,
+      "loss": 0.7531,
+      "step": 90
+    },
+    {
+      "epoch": 0.48663101604278075,
+      "grad_norm": 2.179333209991455,
+      "learning_rate": 4.97147773390341e-06,
+      "loss": 0.6735,
+      "step": 91
+    },
+    {
+      "epoch": 0.4919786096256685,
+      "grad_norm": 3.6383707523345947,
+      "learning_rate": 4.970841626306617e-06,
+      "loss": 0.7944,
+      "step": 92
+    },
+    {
+      "epoch": 0.49732620320855614,
+      "grad_norm": 3.261329412460327,
+      "learning_rate": 4.970198545040673e-06,
+      "loss": 0.9247,
+      "step": 93
+    },
+    {
+      "epoch": 0.5026737967914439,
+      "grad_norm": 2.4254188537597656,
+      "learning_rate": 4.969548491920603e-06,
+      "loss": 0.8103,
+      "step": 94
+    },
+    {
+      "epoch": 0.5080213903743316,
+      "grad_norm": 2.3364553451538086,
+      "learning_rate": 4.968891468781105e-06,
+      "loss": 0.8665,
+      "step": 95
+    },
+    {
+      "epoch": 0.5133689839572193,
+      "grad_norm": 1.924232006072998,
+      "learning_rate": 4.968227477476554e-06,
+      "loss": 0.7296,
+      "step": 96
+    },
+    {
+      "epoch": 0.5187165775401069,
+      "grad_norm": 3.2073605060577393,
+      "learning_rate": 4.9675565198809905e-06,
+      "loss": 0.9934,
+      "step": 97
+    },
+    {
+      "epoch": 0.5240641711229946,
+      "grad_norm": 3.708503484725952,
+      "learning_rate": 4.966878597888114e-06,
+      "loss": 0.8737,
+      "step": 98
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 2.033870220184326,
+      "learning_rate": 4.966193713411284e-06,
+      "loss": 0.6058,
+      "step": 99
+    },
+    {
+      "epoch": 0.5347593582887701,
+      "grad_norm": 1.9964888095855713,
+      "learning_rate": 4.965501868383507e-06,
+      "loss": 0.5937,
+      "step": 100
+    },
+    {
+      "epoch": 0.5401069518716578,
+      "grad_norm": 4.396932125091553,
+      "learning_rate": 4.964803064757438e-06,
+      "loss": 0.8674,
+      "step": 101
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.7765685319900513,
+      "learning_rate": 4.964097304505371e-06,
+      "loss": 0.6939,
+      "step": 102
+    },
+    {
+      "epoch": 0.5508021390374331,
+      "grad_norm": 1.561779499053955,
+      "learning_rate": 4.963384589619233e-06,
+      "loss": 0.5736,
+      "step": 103
+    },
+    {
+      "epoch": 0.5561497326203209,
+      "grad_norm": 1.7359256744384766,
+      "learning_rate": 4.962664922110581e-06,
+      "loss": 0.7812,
+      "step": 104
+    },
+    {
+      "epoch": 0.5614973262032086,
+      "grad_norm": 1.6068986654281616,
+      "learning_rate": 4.9619383040105954e-06,
+      "loss": 0.8682,
+      "step": 105
+    },
+    {
+      "epoch": 0.5668449197860963,
+      "grad_norm": 3.2965404987335205,
+      "learning_rate": 4.961204737370071e-06,
+      "loss": 0.8061,
+      "step": 106
+    },
+    {
+      "epoch": 0.5721925133689839,
+      "grad_norm": 2.4301652908325195,
+      "learning_rate": 4.960464224259418e-06,
+      "loss": 1.0406,
+      "step": 107
+    },
+    {
+      "epoch": 0.5775401069518716,
+      "grad_norm": 1.5491291284561157,
+      "learning_rate": 4.95971676676865e-06,
+      "loss": 0.4941,
+      "step": 108
+    },
+    {
+      "epoch": 0.5828877005347594,
+      "grad_norm": 1.4951472282409668,
+      "learning_rate": 4.958962367007381e-06,
+      "loss": 0.7875,
+      "step": 109
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.8285131454467773,
+      "learning_rate": 4.958201027104818e-06,
+      "loss": 0.6404,
+      "step": 110
+    },
+    {
+      "epoch": 0.5935828877005348,
+      "grad_norm": 4.358597278594971,
+      "learning_rate": 4.957432749209755e-06,
+      "loss": 0.6184,
+      "step": 111
+    },
+    {
+      "epoch": 0.5989304812834224,
+      "grad_norm": 2.530116081237793,
+      "learning_rate": 4.95665753549057e-06,
+      "loss": 0.7618,
+      "step": 112
+    },
+    {
+      "epoch": 0.6042780748663101,
+      "grad_norm": 1.753998041152954,
+      "learning_rate": 4.9558753881352165e-06,
+      "loss": 1.1332,
+      "step": 113
+    },
+    {
+      "epoch": 0.6096256684491979,
+      "grad_norm": 1.646666407585144,
+      "learning_rate": 4.955086309351213e-06,
+      "loss": 0.9139,
+      "step": 114
+    },
+    {
+      "epoch": 0.6149732620320856,
+      "grad_norm": 1.3483537435531616,
+      "learning_rate": 4.9542903013656485e-06,
+      "loss": 0.5049,
+      "step": 115
+    },
+    {
+      "epoch": 0.6203208556149733,
+      "grad_norm": 2.0325682163238525,
+      "learning_rate": 4.953487366425163e-06,
+      "loss": 0.6356,
+      "step": 116
+    },
+    {
+      "epoch": 0.6256684491978609,
+      "grad_norm": 1.3857232332229614,
+      "learning_rate": 4.952677506795949e-06,
+      "loss": 0.5253,
+      "step": 117
+    },
+    {
+      "epoch": 0.6310160427807486,
+      "grad_norm": 2.02527117729187,
+      "learning_rate": 4.951860724763743e-06,
+      "loss": 0.675,
+      "step": 118
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.785488247871399,
+      "learning_rate": 4.95103702263382e-06,
+      "loss": 0.6542,
+      "step": 119
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 1.613588809967041,
+      "learning_rate": 4.950206402730984e-06,
+      "loss": 0.6771,
+      "step": 120
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 1.6810681819915771,
+      "learning_rate": 4.949368867399567e-06,
+      "loss": 0.4783,
+      "step": 121
+    },
+    {
+      "epoch": 0.6524064171122995,
+      "grad_norm": 1.7504608631134033,
+      "learning_rate": 4.948524419003415e-06,
+      "loss": 1.0496,
+      "step": 122
+    },
+    {
+      "epoch": 0.6577540106951871,
+      "grad_norm": 2.051908254623413,
+      "learning_rate": 4.947673059925889e-06,
+      "loss": 0.749,
+      "step": 123
+    },
+    {
+      "epoch": 0.6631016042780749,
+      "grad_norm": 1.903017520904541,
+      "learning_rate": 4.9468147925698525e-06,
+      "loss": 0.7986,
+      "step": 124
+    },
+    {
+      "epoch": 0.6684491978609626,
+      "grad_norm": 1.893696904182434,
+      "learning_rate": 4.945949619357668e-06,
+      "loss": 0.5936,
+      "step": 125
+    },
+    {
+      "epoch": 0.6737967914438503,
+      "grad_norm": 1.7495923042297363,
+      "learning_rate": 4.945077542731188e-06,
+      "loss": 0.4725,
+      "step": 126
+    },
+    {
+      "epoch": 0.679144385026738,
+      "grad_norm": 1.5601329803466797,
+      "learning_rate": 4.94419856515175e-06,
+      "loss": 0.7723,
+      "step": 127
+    },
+    {
+      "epoch": 0.6844919786096256,
+      "grad_norm": 1.3742767572402954,
+      "learning_rate": 4.943312689100166e-06,
+      "loss": 0.7655,
+      "step": 128
+    },
+    {
+      "epoch": 0.6898395721925134,
+      "grad_norm": 2.281935214996338,
+      "learning_rate": 4.942419917076723e-06,
+      "loss": 0.568,
+      "step": 129
+    },
+    {
+      "epoch": 0.6951871657754011,
+      "grad_norm": 1.5451651811599731,
+      "learning_rate": 4.941520251601167e-06,
+      "loss": 0.6721,
+      "step": 130
+    },
+    {
+      "epoch": 0.7005347593582888,
+      "grad_norm": 1.0952168703079224,
+      "learning_rate": 4.940613695212702e-06,
+      "loss": 0.4304,
+      "step": 131
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 2.339934825897217,
+      "learning_rate": 4.939700250469979e-06,
+      "loss": 0.9099,
+      "step": 132
+    },
+    {
+      "epoch": 0.7112299465240641,
+      "grad_norm": 1.9422153234481812,
+      "learning_rate": 4.938779919951092e-06,
+      "loss": 0.7644,
+      "step": 133
+    },
+    {
+      "epoch": 0.7165775401069518,
+      "grad_norm": 1.9965571165084839,
+      "learning_rate": 4.93785270625357e-06,
+      "loss": 0.4816,
+      "step": 134
+    },
+    {
+      "epoch": 0.7219251336898396,
+      "grad_norm": 2.0928704738616943,
+      "learning_rate": 4.936918611994368e-06,
+      "loss": 0.6259,
+      "step": 135
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.843796968460083,
+      "learning_rate": 4.935977639809861e-06,
+      "loss": 0.7413,
+      "step": 136
+    },
+    {
+      "epoch": 0.732620320855615,
+      "grad_norm": 1.280937910079956,
+      "learning_rate": 4.935029792355834e-06,
+      "loss": 0.5484,
+      "step": 137
+    },
+    {
+      "epoch": 0.7379679144385026,
+      "grad_norm": 1.5927443504333496,
+      "learning_rate": 4.934075072307481e-06,
+      "loss": 0.8891,
+      "step": 138
+    },
+    {
+      "epoch": 0.7433155080213903,
+      "grad_norm": 1.5817301273345947,
+      "learning_rate": 4.933113482359388e-06,
+      "loss": 0.4734,
+      "step": 139
+    },
+    {
+      "epoch": 0.7486631016042781,
+      "grad_norm": 1.6494516134262085,
+      "learning_rate": 4.932145025225535e-06,
+      "loss": 0.6241,
+      "step": 140
+    },
+    {
+      "epoch": 0.7540106951871658,
+      "grad_norm": 2.0221598148345947,
+      "learning_rate": 4.931169703639282e-06,
+      "loss": 0.7615,
+      "step": 141
+    },
+    {
+      "epoch": 0.7593582887700535,
+      "grad_norm": 2.3522613048553467,
+      "learning_rate": 4.930187520353363e-06,
+      "loss": 0.6726,
+      "step": 142
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 1.4179843664169312,
+      "learning_rate": 4.929198478139877e-06,
+      "loss": 0.569,
+      "step": 143
+    },
+    {
+      "epoch": 0.7700534759358288,
+      "grad_norm": 1.4593474864959717,
+      "learning_rate": 4.928202579790285e-06,
+      "loss": 0.5177,
+      "step": 144
+    },
+    {
+      "epoch": 0.7754010695187166,
+      "grad_norm": 1.4810280799865723,
+      "learning_rate": 4.927199828115395e-06,
+      "loss": 0.6381,
+      "step": 145
+    },
+    {
+      "epoch": 0.7807486631016043,
+      "grad_norm": 1.6429814100265503,
+      "learning_rate": 4.9261902259453616e-06,
+      "loss": 0.7551,
+      "step": 146
+    },
+    {
+      "epoch": 0.786096256684492,
+      "grad_norm": 1.8405572175979614,
+      "learning_rate": 4.925173776129669e-06,
+      "loss": 0.9238,
+      "step": 147
+    },
+    {
+      "epoch": 0.7914438502673797,
+      "grad_norm": 1.1145843267440796,
+      "learning_rate": 4.9241504815371346e-06,
+      "loss": 0.4301,
+      "step": 148
+    },
+    {
+      "epoch": 0.7967914438502673,
+      "grad_norm": 1.8401663303375244,
+      "learning_rate": 4.923120345055887e-06,
+      "loss": 0.658,
+      "step": 149
+    },
+    {
+      "epoch": 0.8021390374331551,
+      "grad_norm": 1.4048869609832764,
+      "learning_rate": 4.922083369593372e-06,
+      "loss": 0.5583,
+      "step": 150
+    },
+    {
+      "epoch": 0.8074866310160428,
+      "grad_norm": 1.8184750080108643,
+      "learning_rate": 4.921039558076335e-06,
+      "loss": 0.8338,
+      "step": 151
+    },
+    {
+      "epoch": 0.8128342245989305,
+      "grad_norm": 1.7716563940048218,
+      "learning_rate": 4.919988913450812e-06,
+      "loss": 0.3922,
+      "step": 152
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 2.0364320278167725,
+      "learning_rate": 4.918931438682132e-06,
+      "loss": 0.7769,
+      "step": 153
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 1.6823168992996216,
+      "learning_rate": 4.917867136754894e-06,
+      "loss": 0.7906,
+      "step": 154
+    },
+    {
+      "epoch": 0.8288770053475936,
+      "grad_norm": 1.4398829936981201,
+      "learning_rate": 4.916796010672969e-06,
+      "loss": 0.6593,
+      "step": 155
+    },
+    {
+      "epoch": 0.8342245989304813,
+      "grad_norm": 1.2640691995620728,
+      "learning_rate": 4.91571806345949e-06,
+      "loss": 0.6742,
+      "step": 156
+    },
+    {
+      "epoch": 0.839572192513369,
+      "grad_norm": 1.4318958520889282,
+      "learning_rate": 4.91463329815684e-06,
+      "loss": 0.7198,
+      "step": 157
+    },
+    {
+      "epoch": 0.8449197860962567,
+      "grad_norm": 1.5374701023101807,
+      "learning_rate": 4.913541717826645e-06,
+      "loss": 0.5204,
+      "step": 158
+    },
+    {
+      "epoch": 0.8502673796791443,
+      "grad_norm": 1.208862543106079,
+      "learning_rate": 4.912443325549767e-06,
+      "loss": 0.4366,
+      "step": 159
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 1.7627031803131104,
+      "learning_rate": 4.911338124426291e-06,
+      "loss": 0.6549,
+      "step": 160
+    },
+    {
+      "epoch": 0.8609625668449198,
+      "grad_norm": 1.8459937572479248,
+      "learning_rate": 4.910226117575525e-06,
+      "loss": 0.7216,
+      "step": 161
+    },
+    {
+      "epoch": 0.8663101604278075,
+      "grad_norm": 1.7513830661773682,
+      "learning_rate": 4.909107308135978e-06,
+      "loss": 0.459,
+      "step": 162
+    },
+    {
+      "epoch": 0.8716577540106952,
+      "grad_norm": 1.3642503023147583,
+      "learning_rate": 4.907981699265364e-06,
+      "loss": 0.5261,
+      "step": 163
+    },
+    {
+      "epoch": 0.8770053475935828,
+      "grad_norm": 4.495706081390381,
+      "learning_rate": 4.906849294140587e-06,
+      "loss": 0.7482,
+      "step": 164
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 1.7943322658538818,
+      "learning_rate": 4.9057100959577285e-06,
+      "loss": 0.5995,
+      "step": 165
+    },
+    {
+      "epoch": 0.8877005347593583,
+      "grad_norm": 1.5851768255233765,
+      "learning_rate": 4.904564107932048e-06,
+      "loss": 0.8498,
+      "step": 166
+    },
+    {
+      "epoch": 0.893048128342246,
+      "grad_norm": 1.555903434753418,
+      "learning_rate": 4.903411333297966e-06,
+      "loss": 0.7843,
+      "step": 167
+    },
+    {
+      "epoch": 0.8983957219251337,
+      "grad_norm": 1.8726716041564941,
+      "learning_rate": 4.902251775309057e-06,
+      "loss": 0.6857,
+      "step": 168
+    },
+    {
+      "epoch": 0.9037433155080213,
+      "grad_norm": 1.9718592166900635,
+      "learning_rate": 4.901085437238041e-06,
+      "loss": 0.4818,
+      "step": 169
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.3602139949798584,
+      "learning_rate": 4.899912322376776e-06,
+      "loss": 0.846,
+      "step": 170
+    },
+    {
+      "epoch": 0.9144385026737968,
+      "grad_norm": 2.0077531337738037,
+      "learning_rate": 4.8987324340362445e-06,
+      "loss": 0.7561,
+      "step": 171
+    },
+    {
+      "epoch": 0.9197860962566845,
+      "grad_norm": 3.3830618858337402,
+      "learning_rate": 4.897545775546545e-06,
+      "loss": 0.6971,
+      "step": 172
+    },
+    {
+      "epoch": 0.9251336898395722,
+      "grad_norm": 1.8507704734802246,
+      "learning_rate": 4.8963523502568886e-06,
+      "loss": 0.922,
+      "step": 173
+    },
+    {
+      "epoch": 0.93048128342246,
+      "grad_norm": 1.7138328552246094,
+      "learning_rate": 4.895152161535582e-06,
+      "loss": 0.6531,
+      "step": 174
+    },
+    {
+      "epoch": 0.9358288770053476,
+      "grad_norm": 1.738075613975525,
+      "learning_rate": 4.893945212770019e-06,
+      "loss": 0.6223,
+      "step": 175
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 1.9560719728469849,
+      "learning_rate": 4.892731507366678e-06,
+      "loss": 0.7126,
+      "step": 176
+    },
+    {
+      "epoch": 0.946524064171123,
+      "grad_norm": 1.6179195642471313,
+      "learning_rate": 4.891511048751102e-06,
+      "loss": 0.6367,
+      "step": 177
+    },
+    {
+      "epoch": 0.9518716577540107,
+      "grad_norm": 1.37952721118927,
+      "learning_rate": 4.890283840367898e-06,
+      "loss": 1.0321,
+      "step": 178
+    },
+    {
+      "epoch": 0.9572192513368984,
+      "grad_norm": 1.692561149597168,
+      "learning_rate": 4.889049885680721e-06,
+      "loss": 0.6592,
+      "step": 179
+    },
+    {
+      "epoch": 0.9625668449197861,
+      "grad_norm": 1.6270350217819214,
+      "learning_rate": 4.887809188172268e-06,
+      "loss": 0.6125,
+      "step": 180
+    },
+    {
+      "epoch": 0.9679144385026738,
+      "grad_norm": 1.5192607641220093,
+      "learning_rate": 4.886561751344266e-06,
+      "loss": 0.6991,
+      "step": 181
+    },
+    {
+      "epoch": 0.9732620320855615,
+      "grad_norm": 1.4138613939285278,
+      "learning_rate": 4.885307578717464e-06,
+      "loss": 0.693,
+      "step": 182
+    },
+    {
+      "epoch": 0.9786096256684492,
+      "grad_norm": 1.7233471870422363,
+      "learning_rate": 4.8840466738316216e-06,
+      "loss": 0.7376,
+      "step": 183
+    },
+    {
+      "epoch": 0.983957219251337,
+      "grad_norm": 1.4464185237884521,
+      "learning_rate": 4.882779040245499e-06,
+      "loss": 0.6605,
+      "step": 184
+    },
+    {
+      "epoch": 0.9893048128342246,
+      "grad_norm": 2.1437132358551025,
+      "learning_rate": 4.881504681536847e-06,
+      "loss": 0.5219,
+      "step": 185
+    },
+    {
+      "epoch": 0.9946524064171123,
+      "grad_norm": 1.3524681329727173,
+      "learning_rate": 4.880223601302398e-06,
+      "loss": 0.5204,
+      "step": 186
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5214648246765137,
+      "learning_rate": 4.878935803157856e-06,
+      "loss": 0.5093,
+      "step": 187
+    },
+    {
+      "epoch": 1.0053475935828877,
+      "grad_norm": 1.7434720993041992,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.6176,
+      "step": 188
+    },
+    {
+      "epoch": 1.0106951871657754,
+      "grad_norm": 1.6024550199508667,
+      "learning_rate": 4.876340067696097e-06,
+      "loss": 0.5942,
+      "step": 189
+    },
+    {
+      "epoch": 1.0160427807486632,
+      "grad_norm": 1.549131989479065,
+      "learning_rate": 4.875032137705047e-06,
+      "loss": 0.6042,
+      "step": 190
+    },
+    {
+      "epoch": 1.0213903743315509,
+      "grad_norm": 2.7187979221343994,
+      "learning_rate": 4.873717504456219e-06,
+      "loss": 0.7115,
+      "step": 191
+    },
+    {
+      "epoch": 1.0267379679144386,
+      "grad_norm": 1.2187429666519165,
+      "learning_rate": 4.872396171660014e-06,
+      "loss": 0.4006,
+      "step": 192
+    },
+    {
+      "epoch": 1.032085561497326,
+      "grad_norm": 1.6391255855560303,
+      "learning_rate": 4.8710681430457466e-06,
+      "loss": 0.5641,
+      "step": 193
+    },
+    {
+      "epoch": 1.0374331550802138,
+      "grad_norm": 3.5284950733184814,
+      "learning_rate": 4.8697334223616226e-06,
+      "loss": 0.8563,
+      "step": 194
+    },
+    {
+      "epoch": 1.0427807486631016,
+      "grad_norm": 1.3998245000839233,
+      "learning_rate": 4.8683920133747405e-06,
+      "loss": 0.5421,
+      "step": 195
+    },
+    {
+      "epoch": 1.0481283422459893,
+      "grad_norm": 1.9181461334228516,
+      "learning_rate": 4.867043919871076e-06,
+      "loss": 0.4988,
+      "step": 196
+    },
+    {
+      "epoch": 1.053475935828877,
+      "grad_norm": 1.4075592756271362,
+      "learning_rate": 4.865689145655467e-06,
+      "loss": 0.5719,
+      "step": 197
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 1.3631396293640137,
+      "learning_rate": 4.864327694551612e-06,
+      "loss": 0.559,
+      "step": 198
+    },
+    {
+      "epoch": 1.0641711229946524,
+      "grad_norm": 1.9037824869155884,
+      "learning_rate": 4.86295957040205e-06,
+      "loss": 0.9052,
+      "step": 199
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "grad_norm": 1.7171858549118042,
+      "learning_rate": 4.861584777068154e-06,
+      "loss": 0.6885,
+      "step": 200
+    },
+    {
+      "epoch": 1.0748663101604279,
+      "grad_norm": 1.0221351385116577,
+      "learning_rate": 4.860203318430126e-06,
+      "loss": 0.3132,
+      "step": 201
+    },
+    {
+      "epoch": 1.0802139037433156,
+      "grad_norm": 1.6972734928131104,
+      "learning_rate": 4.858815198386973e-06,
+      "loss": 0.6087,
+      "step": 202
+    },
+    {
+      "epoch": 1.085561497326203,
+      "grad_norm": 1.4142796993255615,
+      "learning_rate": 4.8574204208565056e-06,
+      "loss": 0.5655,
+      "step": 203
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 1.1811615228652954,
+      "learning_rate": 4.856018989775326e-06,
+      "loss": 0.546,
+      "step": 204
+    },
+    {
+      "epoch": 1.0962566844919786,
+      "grad_norm": 1.669250726699829,
+      "learning_rate": 4.854610909098813e-06,
+      "loss": 0.6367,
+      "step": 205
+    },
+    {
+      "epoch": 1.1016042780748663,
+      "grad_norm": 1.6402302980422974,
+      "learning_rate": 4.853196182801112e-06,
+      "loss": 0.9829,
+      "step": 206
+    },
+    {
+      "epoch": 1.106951871657754,
+      "grad_norm": 1.7030971050262451,
+      "learning_rate": 4.851774814875131e-06,
+      "loss": 0.6479,
+      "step": 207
+    },
+    {
+      "epoch": 1.1122994652406417,
+      "grad_norm": 1.2214148044586182,
+      "learning_rate": 4.850346809332515e-06,
+      "loss": 0.6702,
+      "step": 208
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 1.502031922340393,
+      "learning_rate": 4.8489121702036515e-06,
+      "loss": 0.7065,
+      "step": 209
+    },
+    {
+      "epoch": 1.1229946524064172,
+      "grad_norm": 1.7563908100128174,
+      "learning_rate": 4.847470901537642e-06,
+      "loss": 0.6531,
+      "step": 210
+    },
+    {
+      "epoch": 1.1283422459893049,
+      "grad_norm": 1.194395661354065,
+      "learning_rate": 4.846023007402305e-06,
+      "loss": 0.475,
+      "step": 211
+    },
+    {
+      "epoch": 1.1336898395721926,
+      "grad_norm": 1.268503189086914,
+      "learning_rate": 4.844568491884156e-06,
+      "loss": 0.3603,
+      "step": 212
+    },
+    {
+      "epoch": 1.1390374331550803,
+      "grad_norm": 1.4655746221542358,
+      "learning_rate": 4.843107359088402e-06,
+      "loss": 0.5436,
+      "step": 213
+    },
+    {
+      "epoch": 1.1443850267379678,
+      "grad_norm": 2.1540749073028564,
+      "learning_rate": 4.84163961313892e-06,
+      "loss": 0.5905,
+      "step": 214
+    },
+    {
+      "epoch": 1.1497326203208555,
+      "grad_norm": 1.3801507949829102,
+      "learning_rate": 4.840165258178259e-06,
+      "loss": 0.5773,
+      "step": 215
+    },
+    {
+      "epoch": 1.1550802139037433,
+      "grad_norm": 1.3531941175460815,
+      "learning_rate": 4.838684298367616e-06,
+      "loss": 0.7402,
+      "step": 216
+    },
+    {
+      "epoch": 1.160427807486631,
+      "grad_norm": 1.5139514207839966,
+      "learning_rate": 4.837196737886834e-06,
+      "loss": 0.7483,
+      "step": 217
+    },
+    {
+      "epoch": 1.1657754010695187,
+      "grad_norm": 1.6450551748275757,
+      "learning_rate": 4.83570258093438e-06,
+      "loss": 0.7784,
+      "step": 218
+    },
+    {
+      "epoch": 1.1711229946524064,
+      "grad_norm": 1.5549203157424927,
+      "learning_rate": 4.834201831727343e-06,
+      "loss": 0.4954,
+      "step": 219
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 1.275998592376709,
+      "learning_rate": 4.832694494501417e-06,
+      "loss": 0.5775,
+      "step": 220
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 1.2826159000396729,
+      "learning_rate": 4.83118057351089e-06,
+      "loss": 0.3923,
+      "step": 221
+    },
+    {
+      "epoch": 1.1871657754010696,
+      "grad_norm": 1.286811351776123,
+      "learning_rate": 4.829660073028631e-06,
+      "loss": 0.5178,
+      "step": 222
+    },
+    {
+      "epoch": 1.192513368983957,
+      "grad_norm": 1.6808027029037476,
+      "learning_rate": 4.82813299734608e-06,
+      "loss": 0.5097,
+      "step": 223
+    },
+    {
+      "epoch": 1.1978609625668448,
+      "grad_norm": 1.3839917182922363,
+      "learning_rate": 4.826599350773234e-06,
+      "loss": 0.4322,
+      "step": 224
+    },
+    {
+      "epoch": 1.2032085561497325,
+      "grad_norm": 1.7111115455627441,
+      "learning_rate": 4.825059137638636e-06,
+      "loss": 0.7774,
+      "step": 225
+    },
+    {
+      "epoch": 1.2085561497326203,
+      "grad_norm": 4.316058158874512,
+      "learning_rate": 4.823512362289362e-06,
+      "loss": 0.5888,
+      "step": 226
+    },
+    {
+      "epoch": 1.213903743315508,
+      "grad_norm": 1.0499860048294067,
+      "learning_rate": 4.821959029091009e-06,
+      "loss": 0.5654,
+      "step": 227
+    },
+    {
+      "epoch": 1.2192513368983957,
+      "grad_norm": 1.3451086282730103,
+      "learning_rate": 4.820399142427684e-06,
+      "loss": 0.5458,
+      "step": 228
+    },
+    {
+      "epoch": 1.2245989304812834,
+      "grad_norm": 1.2978215217590332,
+      "learning_rate": 4.818832706701989e-06,
+      "loss": 0.4517,
+      "step": 229
+    },
+    {
+      "epoch": 1.2299465240641712,
+      "grad_norm": 1.4518600702285767,
+      "learning_rate": 4.817259726335009e-06,
+      "loss": 0.812,
+      "step": 230
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 1.6614092588424683,
+      "learning_rate": 4.815680205766304e-06,
+      "loss": 0.7466,
+      "step": 231
+    },
+    {
+      "epoch": 1.2406417112299466,
+      "grad_norm": 1.0057603120803833,
+      "learning_rate": 4.814094149453891e-06,
+      "loss": 0.3875,
+      "step": 232
+    },
+    {
+      "epoch": 1.2459893048128343,
+      "grad_norm": 1.4217561483383179,
+      "learning_rate": 4.812501561874232e-06,
+      "loss": 0.6488,
+      "step": 233
+    },
+    {
+      "epoch": 1.251336898395722,
+      "grad_norm": 1.5921685695648193,
+      "learning_rate": 4.8109024475222255e-06,
+      "loss": 0.6634,
+      "step": 234
+    },
+    {
+      "epoch": 1.2566844919786098,
+      "grad_norm": 1.297590732574463,
+      "learning_rate": 4.809296810911188e-06,
+      "loss": 0.8039,
+      "step": 235
+    },
+    {
+      "epoch": 1.2620320855614973,
+      "grad_norm": 1.5579601526260376,
+      "learning_rate": 4.8076846565728475e-06,
+      "loss": 0.8313,
+      "step": 236
+    },
+    {
+      "epoch": 1.267379679144385,
+      "grad_norm": 1.285669207572937,
+      "learning_rate": 4.806065989057326e-06,
+      "loss": 0.6066,
+      "step": 237
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 1.2519177198410034,
+      "learning_rate": 4.8044408129331266e-06,
+      "loss": 0.4313,
+      "step": 238
+    },
+    {
+      "epoch": 1.2780748663101604,
+      "grad_norm": 1.2070441246032715,
+      "learning_rate": 4.802809132787125e-06,
+      "loss": 0.5928,
+      "step": 239
+    },
+    {
+      "epoch": 1.2834224598930482,
+      "grad_norm": 1.2995857000350952,
+      "learning_rate": 4.801170953224554e-06,
+      "loss": 0.7107,
+      "step": 240
+    },
+    {
+      "epoch": 1.2887700534759359,
+      "grad_norm": 1.0017821788787842,
+      "learning_rate": 4.7995262788689865e-06,
+      "loss": 0.4193,
+      "step": 241
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 1.4988553524017334,
+      "learning_rate": 4.797875114362331e-06,
+      "loss": 0.5377,
+      "step": 242
+    },
+    {
+      "epoch": 1.299465240641711,
+      "grad_norm": 1.468322515487671,
+      "learning_rate": 4.796217464364808e-06,
+      "loss": 0.6555,
+      "step": 243
+    },
+    {
+      "epoch": 1.3048128342245988,
+      "grad_norm": 1.2765485048294067,
+      "learning_rate": 4.794553333554949e-06,
+      "loss": 0.6666,
+      "step": 244
+    },
+    {
+      "epoch": 1.3101604278074865,
+      "grad_norm": 1.2116676568984985,
+      "learning_rate": 4.792882726629572e-06,
+      "loss": 0.5579,
+      "step": 245
+    },
+    {
+      "epoch": 1.3155080213903743,
+      "grad_norm": 1.4981611967086792,
+      "learning_rate": 4.791205648303775e-06,
+      "loss": 0.7938,
+      "step": 246
+    },
+    {
+      "epoch": 1.320855614973262,
+      "grad_norm": 1.5231660604476929,
+      "learning_rate": 4.789522103310922e-06,
+      "loss": 0.5846,
+      "step": 247
+    },
+    {
+      "epoch": 1.3262032085561497,
+      "grad_norm": 1.488196611404419,
+      "learning_rate": 4.787832096402626e-06,
+      "loss": 0.6159,
+      "step": 248
+    },
+    {
+      "epoch": 1.3315508021390374,
+      "grad_norm": 1.6516927480697632,
+      "learning_rate": 4.786135632348738e-06,
+      "loss": 0.63,
+      "step": 249
+    },
+    {
+      "epoch": 1.3368983957219251,
+      "grad_norm": 1.4712694883346558,
+      "learning_rate": 4.7844327159373365e-06,
+      "loss": 0.7973,
+      "step": 250
+    },
+    {
+      "epoch": 1.3422459893048129,
+      "grad_norm": 1.0578755140304565,
+      "learning_rate": 4.782723351974708e-06,
+      "loss": 0.5215,
+      "step": 251
+    },
+    {
+      "epoch": 1.3475935828877006,
+      "grad_norm": 1.295639157295227,
+      "learning_rate": 4.7810075452853385e-06,
+      "loss": 0.6462,
+      "step": 252
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 1.51445734500885,
+      "learning_rate": 4.779285300711897e-06,
+      "loss": 0.6209,
+      "step": 253
+    },
+    {
+      "epoch": 1.358288770053476,
+      "grad_norm": 1.044088363647461,
+      "learning_rate": 4.7775566231152216e-06,
+      "loss": 0.3432,
+      "step": 254
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 1.2576799392700195,
+      "learning_rate": 4.775821517374308e-06,
+      "loss": 0.8383,
+      "step": 255
+    },
+    {
+      "epoch": 1.3689839572192513,
+      "grad_norm": 1.2666455507278442,
+      "learning_rate": 4.7740799883862966e-06,
+      "loss": 0.4709,
+      "step": 256
+    },
+    {
+      "epoch": 1.374331550802139,
+      "grad_norm": 1.103685975074768,
+      "learning_rate": 4.772332041066452e-06,
+      "loss": 0.4297,
+      "step": 257
+    },
+    {
+      "epoch": 1.3796791443850267,
+      "grad_norm": 1.6457346677780151,
+      "learning_rate": 4.770577680348159e-06,
+      "loss": 0.8415,
+      "step": 258
+    },
+    {
+      "epoch": 1.3850267379679144,
+      "grad_norm": 1.3685829639434814,
+      "learning_rate": 4.768816911182899e-06,
+      "loss": 0.4262,
+      "step": 259
+    },
+    {
+      "epoch": 1.3903743315508021,
+      "grad_norm": 1.352225661277771,
+      "learning_rate": 4.767049738540244e-06,
+      "loss": 0.5196,
+      "step": 260
+    },
+    {
+      "epoch": 1.3957219251336899,
+      "grad_norm": 1.3067526817321777,
+      "learning_rate": 4.765276167407836e-06,
+      "loss": 0.3993,
+      "step": 261
+    },
+    {
+      "epoch": 1.4010695187165776,
+      "grad_norm": 2.2841289043426514,
+      "learning_rate": 4.7634962027913784e-06,
+      "loss": 0.7369,
+      "step": 262
+    },
+    {
+      "epoch": 1.4064171122994653,
+      "grad_norm": 1.2478086948394775,
+      "learning_rate": 4.761709849714619e-06,
+      "loss": 0.5529,
+      "step": 263
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 1.3700896501541138,
+      "learning_rate": 4.7599171132193355e-06,
+      "loss": 0.6576,
+      "step": 264
+    },
+    {
+      "epoch": 1.4171122994652405,
+      "grad_norm": 1.3073475360870361,
+      "learning_rate": 4.7581179983653224e-06,
+      "loss": 0.5824,
+      "step": 265
+    },
+    {
+      "epoch": 1.4224598930481283,
+      "grad_norm": 1.0777263641357422,
+      "learning_rate": 4.756312510230377e-06,
+      "loss": 0.3627,
+      "step": 266
+    },
+    {
+      "epoch": 1.427807486631016,
+      "grad_norm": 1.5585756301879883,
+      "learning_rate": 4.754500653910284e-06,
+      "loss": 0.5558,
+      "step": 267
+    },
+    {
+      "epoch": 1.4331550802139037,
+      "grad_norm": 1.1606045961380005,
+      "learning_rate": 4.752682434518801e-06,
+      "loss": 0.5699,
+      "step": 268
+    },
+    {
+      "epoch": 1.4385026737967914,
+      "grad_norm": 1.424801230430603,
+      "learning_rate": 4.750857857187645e-06,
+      "loss": 0.4391,
+      "step": 269
+    },
+    {
+      "epoch": 1.4438502673796791,
+      "grad_norm": 2.311251163482666,
+      "learning_rate": 4.749026927066479e-06,
+      "loss": 0.739,
+      "step": 270
+    },
+    {
+      "epoch": 1.4491978609625669,
+      "grad_norm": 0.8563798069953918,
+      "learning_rate": 4.747189649322894e-06,
+      "loss": 0.5015,
+      "step": 271
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.4205528497695923,
+      "learning_rate": 4.745346029142397e-06,
+      "loss": 0.6266,
+      "step": 272
+    },
+    {
+      "epoch": 1.4598930481283423,
+      "grad_norm": 1.0935620069503784,
+      "learning_rate": 4.743496071728396e-06,
+      "loss": 0.6173,
+      "step": 273
+    },
+    {
+      "epoch": 1.46524064171123,
+      "grad_norm": 1.2095967531204224,
+      "learning_rate": 4.741639782302187e-06,
+      "loss": 0.4226,
+      "step": 274
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 1.1226903200149536,
+      "learning_rate": 4.739777166102933e-06,
+      "loss": 0.4797,
+      "step": 275
+    },
+    {
+      "epoch": 1.4759358288770055,
+      "grad_norm": 1.1917341947555542,
+      "learning_rate": 4.737908228387656e-06,
+      "loss": 0.5437,
+      "step": 276
+    },
+    {
+      "epoch": 1.481283422459893,
+      "grad_norm": 1.0938372611999512,
+      "learning_rate": 4.736032974431222e-06,
+      "loss": 0.4817,
+      "step": 277
+    },
+    {
+      "epoch": 1.4866310160427807,
+      "grad_norm": 1.0449817180633545,
+      "learning_rate": 4.7341514095263214e-06,
+      "loss": 0.4552,
+      "step": 278
+    },
+    {
+      "epoch": 1.4919786096256684,
+      "grad_norm": 1.297238826751709,
+      "learning_rate": 4.732263538983456e-06,
+      "loss": 0.584,
+      "step": 279
+    },
+    {
+      "epoch": 1.4973262032085561,
+      "grad_norm": 1.5626052618026733,
+      "learning_rate": 4.730369368130925e-06,
+      "loss": 0.6484,
+      "step": 280
+    },
+    {
+      "epoch": 1.5026737967914439,
+      "grad_norm": 1.8843748569488525,
+      "learning_rate": 4.728468902314811e-06,
+      "loss": 1.215,
+      "step": 281
+    },
+    {
+      "epoch": 1.5080213903743316,
+      "grad_norm": 1.134339451789856,
+      "learning_rate": 4.726562146898963e-06,
+      "loss": 0.643,
+      "step": 282
+    },
+    {
+      "epoch": 1.5133689839572193,
+      "grad_norm": 1.7309473752975464,
+      "learning_rate": 4.72464910726498e-06,
+      "loss": 0.4788,
+      "step": 283
+    },
+    {
+      "epoch": 1.5187165775401068,
+      "grad_norm": 1.4553159475326538,
+      "learning_rate": 4.7227297888121985e-06,
+      "loss": 0.7248,
+      "step": 284
+    },
+    {
+      "epoch": 1.5240641711229945,
+      "grad_norm": 1.1522701978683472,
+      "learning_rate": 4.720804196957676e-06,
+      "loss": 0.58,
+      "step": 285
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 1.2750757932662964,
+      "learning_rate": 4.718872337136176e-06,
+      "loss": 0.7695,
+      "step": 286
+    },
+    {
+      "epoch": 1.53475935828877,
+      "grad_norm": 1.4252182245254517,
+      "learning_rate": 4.716934214800155e-06,
+      "loss": 0.9835,
+      "step": 287
+    },
+    {
+      "epoch": 1.5401069518716577,
+      "grad_norm": 1.3734545707702637,
+      "learning_rate": 4.714989835419741e-06,
+      "loss": 0.5944,
+      "step": 288
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 1.4612936973571777,
+      "learning_rate": 4.713039204482723e-06,
+      "loss": 0.48,
+      "step": 289
+    },
+    {
+      "epoch": 1.5508021390374331,
+      "grad_norm": 1.1801178455352783,
+      "learning_rate": 4.711082327494536e-06,
+      "loss": 0.7062,
+      "step": 290
+    },
+    {
+      "epoch": 1.5561497326203209,
+      "grad_norm": 1.5561658143997192,
+      "learning_rate": 4.709119209978242e-06,
+      "loss": 0.4857,
+      "step": 291
+    },
+    {
+      "epoch": 1.5614973262032086,
+      "grad_norm": 1.1322139501571655,
+      "learning_rate": 4.707149857474516e-06,
+      "loss": 0.3912,
+      "step": 292
+    },
+    {
+      "epoch": 1.5668449197860963,
+      "grad_norm": 1.125351071357727,
+      "learning_rate": 4.705174275541632e-06,
+      "loss": 0.523,
+      "step": 293
+    },
+    {
+      "epoch": 1.572192513368984,
+      "grad_norm": 1.1379163265228271,
+      "learning_rate": 4.703192469755444e-06,
+      "loss": 0.6023,
+      "step": 294
+    },
+    {
+      "epoch": 1.5775401069518717,
+      "grad_norm": 1.850498914718628,
+      "learning_rate": 4.701204445709375e-06,
+      "loss": 0.6206,
+      "step": 295
+    },
+    {
+      "epoch": 1.5828877005347595,
+      "grad_norm": 1.1480787992477417,
+      "learning_rate": 4.699210209014394e-06,
+      "loss": 0.6406,
+      "step": 296
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 1.3049321174621582,
+      "learning_rate": 4.69720976529901e-06,
+      "loss": 0.4942,
+      "step": 297
+    },
+    {
+      "epoch": 1.593582887700535,
+      "grad_norm": 1.1686694622039795,
+      "learning_rate": 4.695203120209245e-06,
+      "loss": 0.453,
+      "step": 298
+    },
+    {
+      "epoch": 1.5989304812834224,
+      "grad_norm": 1.4365569353103638,
+      "learning_rate": 4.693190279408628e-06,
+      "loss": 0.4446,
+      "step": 299
+    },
+    {
+      "epoch": 1.6042780748663101,
+      "grad_norm": 1.2973593473434448,
+      "learning_rate": 4.691171248578172e-06,
+      "loss": 0.4765,
+      "step": 300
+    },
+    {
+      "epoch": 1.6096256684491979,
+      "grad_norm": 1.0093376636505127,
+      "learning_rate": 4.689146033416362e-06,
+      "loss": 0.6681,
+      "step": 301
+    },
+    {
+      "epoch": 1.6149732620320856,
+      "grad_norm": 1.7874302864074707,
+      "learning_rate": 4.687114639639136e-06,
+      "loss": 0.4031,
+      "step": 302
+    },
+    {
+      "epoch": 1.6203208556149733,
+      "grad_norm": 1.2745457887649536,
+      "learning_rate": 4.685077072979874e-06,
+      "loss": 0.4327,
+      "step": 303
+    },
+    {
+      "epoch": 1.6256684491978608,
+      "grad_norm": 1.2880927324295044,
+      "learning_rate": 4.683033339189375e-06,
+      "loss": 0.4426,
+      "step": 304
+    },
+    {
+      "epoch": 1.6310160427807485,
+      "grad_norm": 1.4269540309906006,
+      "learning_rate": 4.680983444035843e-06,
+      "loss": 0.6982,
+      "step": 305
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 1.1514452695846558,
+      "learning_rate": 4.678927393304877e-06,
+      "loss": 0.3421,
+      "step": 306
+    },
+    {
+      "epoch": 1.641711229946524,
+      "grad_norm": 1.1018633842468262,
+      "learning_rate": 4.676865192799443e-06,
+      "loss": 0.461,
+      "step": 307
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 1.1519875526428223,
+      "learning_rate": 4.6747968483398695e-06,
+      "loss": 0.7697,
+      "step": 308
+    },
+    {
+      "epoch": 1.6524064171122994,
+      "grad_norm": 0.9200301766395569,
+      "learning_rate": 4.672722365763821e-06,
+      "loss": 0.3437,
+      "step": 309
+    },
+    {
+      "epoch": 1.6577540106951871,
+      "grad_norm": 1.2333654165267944,
+      "learning_rate": 4.6706417509262905e-06,
+      "loss": 0.5374,
+      "step": 310
+    },
+    {
+      "epoch": 1.6631016042780749,
+      "grad_norm": 1.1560025215148926,
+      "learning_rate": 4.668555009699575e-06,
+      "loss": 0.4684,
+      "step": 311
+    },
+    {
+      "epoch": 1.6684491978609626,
+      "grad_norm": 1.18622887134552,
+      "learning_rate": 4.666462147973264e-06,
+      "loss": 0.5904,
+      "step": 312
+    },
+    {
+      "epoch": 1.6737967914438503,
+      "grad_norm": 1.8510594367980957,
+      "learning_rate": 4.664363171654223e-06,
+      "loss": 0.6529,
+      "step": 313
+    },
+    {
+      "epoch": 1.679144385026738,
+      "grad_norm": 1.9835350513458252,
+      "learning_rate": 4.662258086666571e-06,
+      "loss": 0.8396,
+      "step": 314
+    },
+    {
+      "epoch": 1.6844919786096257,
+      "grad_norm": 1.4230506420135498,
+      "learning_rate": 4.660146898951674e-06,
+      "loss": 0.7583,
+      "step": 315
+    },
+    {
+      "epoch": 1.6898395721925135,
+      "grad_norm": 1.553373098373413,
+      "learning_rate": 4.6580296144681155e-06,
+      "loss": 0.6657,
+      "step": 316
+    },
+    {
+      "epoch": 1.6951871657754012,
+      "grad_norm": 1.335451602935791,
+      "learning_rate": 4.655906239191693e-06,
+      "loss": 0.737,
+      "step": 317
+    },
+    {
+      "epoch": 1.700534759358289,
+      "grad_norm": 1.1293808221817017,
+      "learning_rate": 4.653776779115389e-06,
+      "loss": 0.64,
+      "step": 318
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 1.83036470413208,
+      "learning_rate": 4.651641240249364e-06,
+      "loss": 0.4238,
+      "step": 319
+    },
+    {
+      "epoch": 1.7112299465240641,
+      "grad_norm": 1.1998335123062134,
+      "learning_rate": 4.649499628620931e-06,
+      "loss": 0.3807,
+      "step": 320
+    },
+    {
+      "epoch": 1.7165775401069518,
+      "grad_norm": 1.1866393089294434,
+      "learning_rate": 4.647351950274548e-06,
+      "loss": 0.6002,
+      "step": 321
+    },
+    {
+      "epoch": 1.7219251336898396,
+      "grad_norm": 1.1516408920288086,
+      "learning_rate": 4.6451982112717896e-06,
+      "loss": 0.644,
+      "step": 322
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 1.1254485845565796,
+      "learning_rate": 4.643038417691341e-06,
+      "loss": 0.4767,
+      "step": 323
+    },
+    {
+      "epoch": 1.732620320855615,
+      "grad_norm": 1.024702787399292,
+      "learning_rate": 4.640872575628973e-06,
+      "loss": 0.4226,
+      "step": 324
+    },
+    {
+      "epoch": 1.7379679144385025,
+      "grad_norm": 1.1981152296066284,
+      "learning_rate": 4.6387006911975275e-06,
+      "loss": 0.6884,
+      "step": 325
+    },
+    {
+      "epoch": 1.7433155080213902,
+      "grad_norm": 1.215268850326538,
+      "learning_rate": 4.6365227705269026e-06,
+      "loss": 0.6557,
+      "step": 326
+    },
+    {
+      "epoch": 1.748663101604278,
+      "grad_norm": 3.9249322414398193,
+      "learning_rate": 4.634338819764029e-06,
+      "loss": 0.5379,
+      "step": 327
+    },
+    {
+      "epoch": 1.7540106951871657,
+      "grad_norm": 1.243040919303894,
+      "learning_rate": 4.632148845072861e-06,
+      "loss": 0.4667,
+      "step": 328
+    },
+    {
+      "epoch": 1.7593582887700534,
+      "grad_norm": 1.2313203811645508,
+      "learning_rate": 4.6299528526343525e-06,
+      "loss": 0.5398,
+      "step": 329
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 2.7076449394226074,
+      "learning_rate": 4.627750848646443e-06,
+      "loss": 0.8683,
+      "step": 330
+    },
+    {
+      "epoch": 1.7700534759358288,
+      "grad_norm": 1.2153202295303345,
+      "learning_rate": 4.625542839324036e-06,
+      "loss": 0.5502,
+      "step": 331
+    },
+    {
+      "epoch": 1.7754010695187166,
+      "grad_norm": 1.07277512550354,
+      "learning_rate": 4.6233288308989874e-06,
+      "loss": 0.3664,
+      "step": 332
+    },
+    {
+      "epoch": 1.7807486631016043,
+      "grad_norm": 1.111885905265808,
+      "learning_rate": 4.6211088296200834e-06,
+      "loss": 0.4065,
+      "step": 333
+    },
+    {
+      "epoch": 1.786096256684492,
+      "grad_norm": 1.2741719484329224,
+      "learning_rate": 4.618882841753026e-06,
+      "loss": 0.6007,
+      "step": 334
+    },
+    {
+      "epoch": 1.7914438502673797,
+      "grad_norm": 1.1446245908737183,
+      "learning_rate": 4.616650873580411e-06,
+      "loss": 0.5967,
+      "step": 335
+    },
+    {
+      "epoch": 1.7967914438502675,
+      "grad_norm": 1.1254442930221558,
+      "learning_rate": 4.614412931401715e-06,
+      "loss": 0.5137,
+      "step": 336
+    },
+    {
+      "epoch": 1.8021390374331552,
+      "grad_norm": 1.2005317211151123,
+      "learning_rate": 4.612169021533276e-06,
+      "loss": 0.4683,
+      "step": 337
+    },
+    {
+      "epoch": 1.807486631016043,
+      "grad_norm": 1.4505470991134644,
+      "learning_rate": 4.609919150308273e-06,
+      "loss": 0.5668,
+      "step": 338
+    },
+    {
+      "epoch": 1.8128342245989306,
+      "grad_norm": 1.1275708675384521,
+      "learning_rate": 4.607663324076711e-06,
+      "loss": 0.4926,
+      "step": 339
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.28780198097229,
+      "learning_rate": 4.605401549205404e-06,
+      "loss": 0.6597,
+      "step": 340
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 2.3382999897003174,
+      "learning_rate": 4.603133832077953e-06,
+      "loss": 0.5681,
+      "step": 341
+    },
+    {
+      "epoch": 1.8288770053475936,
+      "grad_norm": 1.4183709621429443,
+      "learning_rate": 4.600860179094732e-06,
+      "loss": 0.6266,
+      "step": 342
+    },
+    {
+      "epoch": 1.8342245989304813,
+      "grad_norm": 1.3375359773635864,
+      "learning_rate": 4.5985805966728675e-06,
+      "loss": 0.6057,
+      "step": 343
+    },
+    {
+      "epoch": 1.839572192513369,
+      "grad_norm": 2.183406352996826,
+      "learning_rate": 4.596295091246221e-06,
+      "loss": 0.4818,
+      "step": 344
+    },
+    {
+      "epoch": 1.8449197860962567,
+      "grad_norm": 1.3354779481887817,
+      "learning_rate": 4.594003669265371e-06,
+      "loss": 0.565,
+      "step": 345
+    },
+    {
+      "epoch": 1.8502673796791442,
+      "grad_norm": 1.575484275817871,
+      "learning_rate": 4.591706337197597e-06,
+      "loss": 0.6056,
+      "step": 346
+    },
+    {
+      "epoch": 1.855614973262032,
+      "grad_norm": 1.880417823791504,
+      "learning_rate": 4.589403101526854e-06,
+      "loss": 0.4297,
+      "step": 347
+    },
+    {
+      "epoch": 1.8609625668449197,
+      "grad_norm": 1.17208993434906,
+      "learning_rate": 4.587093968753765e-06,
+      "loss": 0.6161,
+      "step": 348
+    },
+    {
+      "epoch": 1.8663101604278074,
+      "grad_norm": 1.0894412994384766,
+      "learning_rate": 4.584778945395594e-06,
+      "loss": 0.4187,
+      "step": 349
+    },
+    {
+      "epoch": 1.8716577540106951,
+      "grad_norm": 1.5079829692840576,
+      "learning_rate": 4.582458037986231e-06,
+      "loss": 0.6172,
+      "step": 350
+    },
+    {
+      "epoch": 1.8770053475935828,
+      "grad_norm": 1.7538971900939941,
+      "learning_rate": 4.580131253076171e-06,
+      "loss": 0.8843,
+      "step": 351
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 1.668242335319519,
+      "learning_rate": 4.5777985972325016e-06,
+      "loss": 0.5589,
+      "step": 352
+    },
+    {
+      "epoch": 1.8877005347593583,
+      "grad_norm": 1.3463695049285889,
+      "learning_rate": 4.575460077038877e-06,
+      "loss": 0.3643,
+      "step": 353
+    },
+    {
+      "epoch": 1.893048128342246,
+      "grad_norm": 2.2697858810424805,
+      "learning_rate": 4.573115699095505e-06,
+      "loss": 0.8601,
+      "step": 354
+    },
+    {
+      "epoch": 1.8983957219251337,
+      "grad_norm": 1.3223217725753784,
+      "learning_rate": 4.570765470019125e-06,
+      "loss": 0.4313,
+      "step": 355
+    },
+    {
+      "epoch": 1.9037433155080214,
+      "grad_norm": 1.628551721572876,
+      "learning_rate": 4.5684093964429906e-06,
+      "loss": 0.6051,
+      "step": 356
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 1.149308681488037,
+      "learning_rate": 4.566047485016853e-06,
+      "loss": 0.4402,
+      "step": 357
+    },
+    {
+      "epoch": 1.914438502673797,
+      "grad_norm": 1.798424243927002,
+      "learning_rate": 4.563679742406935e-06,
+      "loss": 0.6086,
+      "step": 358
+    },
+    {
+      "epoch": 1.9197860962566846,
+      "grad_norm": 1.4567193984985352,
+      "learning_rate": 4.5613061752959236e-06,
+      "loss": 1.0573,
+      "step": 359
+    },
+    {
+      "epoch": 1.9251336898395723,
+      "grad_norm": 1.4123218059539795,
+      "learning_rate": 4.558926790382941e-06,
+      "loss": 0.8455,
+      "step": 360
+    },
+    {
+      "epoch": 1.93048128342246,
+      "grad_norm": 1.6043243408203125,
+      "learning_rate": 4.556541594383528e-06,
+      "loss": 0.5767,
+      "step": 361
+    },
+    {
+      "epoch": 1.9358288770053476,
+      "grad_norm": 1.0144673585891724,
+      "learning_rate": 4.554150594029631e-06,
+      "loss": 0.2808,
+      "step": 362
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 1.1464323997497559,
+      "learning_rate": 4.551753796069577e-06,
+      "loss": 0.5614,
+      "step": 363
+    },
+    {
+      "epoch": 1.946524064171123,
+      "grad_norm": 1.111174464225769,
+      "learning_rate": 4.5493512072680535e-06,
+      "loss": 0.5738,
+      "step": 364
+    },
+    {
+      "epoch": 1.9518716577540107,
+      "grad_norm": 1.324460744857788,
+      "learning_rate": 4.546942834406094e-06,
+      "loss": 0.7303,
+      "step": 365
+    },
+    {
+      "epoch": 1.9572192513368984,
+      "grad_norm": 1.229299545288086,
+      "learning_rate": 4.544528684281056e-06,
+      "loss": 0.426,
+      "step": 366
+    },
+    {
+      "epoch": 1.962566844919786,
+      "grad_norm": 1.1022107601165771,
+      "learning_rate": 4.5421087637066065e-06,
+      "loss": 0.4434,
+      "step": 367
+    },
+    {
+      "epoch": 1.9679144385026737,
+      "grad_norm": 1.2204968929290771,
+      "learning_rate": 4.539683079512692e-06,
+      "loss": 0.6719,
+      "step": 368
+    },
+    {
+      "epoch": 1.9732620320855614,
+      "grad_norm": 1.4362984895706177,
+      "learning_rate": 4.537251638545532e-06,
+      "loss": 0.5375,
+      "step": 369
+    },
+    {
+      "epoch": 1.9786096256684491,
+      "grad_norm": 1.1409226655960083,
+      "learning_rate": 4.534814447667591e-06,
+      "loss": 0.2699,
+      "step": 370
+    },
+    {
+      "epoch": 1.9839572192513368,
+      "grad_norm": 1.1425247192382812,
+      "learning_rate": 4.532371513757564e-06,
+      "loss": 0.4671,
+      "step": 371
+    },
+    {
+      "epoch": 1.9893048128342246,
+      "grad_norm": 1.3072478771209717,
+      "learning_rate": 4.529922843710354e-06,
+      "loss": 0.5961,
+      "step": 372
+    },
+    {
+      "epoch": 1.9946524064171123,
+      "grad_norm": 2.0365114212036133,
+      "learning_rate": 4.52746844443705e-06,
+      "loss": 0.6017,
+      "step": 373
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1788240671157837,
+      "learning_rate": 4.525008322864917e-06,
+      "loss": 0.62,
+      "step": 374
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.023726260846592e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.55.0"
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1903904128,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/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
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-748/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.55.0"
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1903904128,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/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
+  }
+}

qwen2_5_math_7b/limo_filtered_combined/checkpoint-935/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2_5_math_7b/limo_filtered_combined/trainer_log.jsonl

@@ -0,0 +1,187 @@
+{"current_steps": 1, "total_steps": 1870, "loss": 1.0432, "lr": 5e-06, "epoch": 0.0053475935828877, "percentage": 0.05, "elapsed_time": "0:00:02", "remaining_time": "1:23:55"}
+{"current_steps": 2, "total_steps": 1870, "loss": 2.755, "lr": 4.99999647201733e-06, "epoch": 0.0106951871657754, "percentage": 0.11, "elapsed_time": "0:00:05", "remaining_time": "1:29:58"}
+{"current_steps": 3, "total_steps": 1870, "loss": 0.9712, "lr": 4.999985888079276e-06, "epoch": 0.016042780748663103, "percentage": 0.16, "elapsed_time": "0:00:07", "remaining_time": "1:17:15"}
+{"current_steps": 4, "total_steps": 1870, "loss": 2.4821, "lr": 4.999968248215712e-06, "epoch": 0.0213903743315508, "percentage": 0.21, "elapsed_time": "0:00:12", "remaining_time": "1:38:15"}
+{"current_steps": 5, "total_steps": 1870, "loss": 2.2207, "lr": 4.999943552476422e-06, "epoch": 0.026737967914438502, "percentage": 0.27, "elapsed_time": "0:00:16", "remaining_time": "1:44:57"}
+{"current_steps": 6, "total_steps": 1870, "loss": 1.6801, "lr": 4.999911800931108e-06, "epoch": 0.03208556149732621, "percentage": 0.32, "elapsed_time": "0:00:20", "remaining_time": "1:46:26"}
+{"current_steps": 7, "total_steps": 1870, "loss": 0.8298, "lr": 4.999872993669387e-06, "epoch": 0.0374331550802139, "percentage": 0.37, "elapsed_time": "0:00:21", "remaining_time": "1:36:54"}
+{"current_steps": 8, "total_steps": 1870, "loss": 1.749, "lr": 4.999827130800785e-06, "epoch": 0.0427807486631016, "percentage": 0.43, "elapsed_time": "0:00:24", "remaining_time": "1:33:10"}
+{"current_steps": 9, "total_steps": 1870, "loss": 2.2523, "lr": 4.999774212454746e-06, "epoch": 0.0481283422459893, "percentage": 0.48, "elapsed_time": "0:00:27", "remaining_time": "1:33:37"}
+{"current_steps": 10, "total_steps": 1870, "loss": 1.753, "lr": 4.999714238780626e-06, "epoch": 0.053475935828877004, "percentage": 0.53, "elapsed_time": "0:00:30", "remaining_time": "1:33:14"}
+{"current_steps": 11, "total_steps": 1870, "loss": 1.6893, "lr": 4.999647209947694e-06, "epoch": 0.058823529411764705, "percentage": 0.59, "elapsed_time": "0:00:33", "remaining_time": "1:34:15"}
+{"current_steps": 12, "total_steps": 1870, "loss": 1.645, "lr": 4.999573126145132e-06, "epoch": 0.06417112299465241, "percentage": 0.64, "elapsed_time": "0:00:36", "remaining_time": "1:34:07"}
+{"current_steps": 13, "total_steps": 1870, "loss": 1.2288, "lr": 4.999491987582032e-06, "epoch": 0.06951871657754011, "percentage": 0.7, "elapsed_time": "0:00:40", "remaining_time": "1:35:23"}
+{"current_steps": 14, "total_steps": 1870, "loss": 1.9827, "lr": 4.999403794487399e-06, "epoch": 0.0748663101604278, "percentage": 0.75, "elapsed_time": "0:00:45", "remaining_time": "1:40:25"}
+{"current_steps": 15, "total_steps": 1870, "loss": 1.172, "lr": 4.999308547110147e-06, "epoch": 0.08021390374331551, "percentage": 0.8, "elapsed_time": "0:00:47", "remaining_time": "1:38:05"}
+{"current_steps": 16, "total_steps": 1870, "loss": 1.2894, "lr": 4.9992062457191005e-06, "epoch": 0.0855614973262032, "percentage": 0.86, "elapsed_time": "0:00:49", "remaining_time": "1:35:01"}
+{"current_steps": 17, "total_steps": 1870, "loss": 1.2801, "lr": 4.999096890602996e-06, "epoch": 0.09090909090909091, "percentage": 0.91, "elapsed_time": "0:00:53", "remaining_time": "1:36:35"}
+{"current_steps": 18, "total_steps": 1870, "loss": 1.3917, "lr": 4.998980482070473e-06, "epoch": 0.0962566844919786, "percentage": 0.96, "elapsed_time": "0:00:57", "remaining_time": "1:37:48"}
+{"current_steps": 19, "total_steps": 1870, "loss": 1.8526, "lr": 4.998857020450084e-06, "epoch": 0.10160427807486631, "percentage": 1.02, "elapsed_time": "0:01:02", "remaining_time": "1:41:25"}
+{"current_steps": 20, "total_steps": 1870, "loss": 1.0143, "lr": 4.998726506090283e-06, "epoch": 0.10695187165775401, "percentage": 1.07, "elapsed_time": "0:01:04", "remaining_time": "1:39:28"}
+{"current_steps": 21, "total_steps": 1870, "loss": 0.8347, "lr": 4.998588939359435e-06, "epoch": 0.11229946524064172, "percentage": 1.12, "elapsed_time": "0:01:06", "remaining_time": "1:36:53"}
+{"current_steps": 22, "total_steps": 1870, "loss": 1.5395, "lr": 4.998444320645803e-06, "epoch": 0.11764705882352941, "percentage": 1.18, "elapsed_time": "0:01:11", "remaining_time": "1:40:26"}
+{"current_steps": 23, "total_steps": 1870, "loss": 1.2366, "lr": 4.998292650357558e-06, "epoch": 0.12299465240641712, "percentage": 1.23, "elapsed_time": "0:01:15", "remaining_time": "1:40:48"}
+{"current_steps": 24, "total_steps": 1870, "loss": 1.9291, "lr": 4.998133928922773e-06, "epoch": 0.12834224598930483, "percentage": 1.28, "elapsed_time": "0:01:21", "remaining_time": "1:43:59"}
+{"current_steps": 25, "total_steps": 1870, "loss": 1.0207, "lr": 4.99796815678942e-06, "epoch": 0.13368983957219252, "percentage": 1.34, "elapsed_time": "0:01:24", "remaining_time": "1:43:35"}
+{"current_steps": 26, "total_steps": 1870, "loss": 1.5651, "lr": 4.997795334425372e-06, "epoch": 0.13903743315508021, "percentage": 1.39, "elapsed_time": "0:01:29", "remaining_time": "1:46:06"}
+{"current_steps": 27, "total_steps": 1870, "loss": 1.6426, "lr": 4.997615462318403e-06, "epoch": 0.1443850267379679, "percentage": 1.44, "elapsed_time": "0:01:34", "remaining_time": "1:47:18"}
+{"current_steps": 28, "total_steps": 1870, "loss": 1.3191, "lr": 4.997428540976177e-06, "epoch": 0.1497326203208556, "percentage": 1.5, "elapsed_time": "0:01:39", "remaining_time": "1:48:52"}
+{"current_steps": 29, "total_steps": 1870, "loss": 0.9809, "lr": 4.997234570926263e-06, "epoch": 0.15508021390374332, "percentage": 1.55, "elapsed_time": "0:01:42", "remaining_time": "1:48:28"}
+{"current_steps": 30, "total_steps": 1870, "loss": 0.8292, "lr": 4.997033552716116e-06, "epoch": 0.16042780748663102, "percentage": 1.6, "elapsed_time": "0:01:44", "remaining_time": "1:46:30"}
+{"current_steps": 31, "total_steps": 1870, "loss": 0.8013, "lr": 4.9968254869130885e-06, "epoch": 0.1657754010695187, "percentage": 1.66, "elapsed_time": "0:01:46", "remaining_time": "1:44:52"}
+{"current_steps": 32, "total_steps": 1870, "loss": 0.6308, "lr": 4.996610374104422e-06, "epoch": 0.1711229946524064, "percentage": 1.71, "elapsed_time": "0:01:46", "remaining_time": "1:42:14"}
+{"current_steps": 33, "total_steps": 1870, "loss": 1.155, "lr": 4.9963882148972475e-06, "epoch": 0.17647058823529413, "percentage": 1.76, "elapsed_time": "0:01:48", "remaining_time": "1:40:16"}
+{"current_steps": 34, "total_steps": 1870, "loss": 0.9171, "lr": 4.996159009918586e-06, "epoch": 0.18181818181818182, "percentage": 1.82, "elapsed_time": "0:01:49", "remaining_time": "1:38:21"}
+{"current_steps": 35, "total_steps": 1870, "loss": 1.1837, "lr": 4.9959227598153395e-06, "epoch": 0.18716577540106952, "percentage": 1.87, "elapsed_time": "0:01:52", "remaining_time": "1:38:43"}
+{"current_steps": 36, "total_steps": 1870, "loss": 1.4155, "lr": 4.9956794652542994e-06, "epoch": 0.1925133689839572, "percentage": 1.93, "elapsed_time": "0:01:55", "remaining_time": "1:38:22"}
+{"current_steps": 37, "total_steps": 1870, "loss": 0.8738, "lr": 4.9954291269221364e-06, "epoch": 0.19786096256684493, "percentage": 1.98, "elapsed_time": "0:01:58", "remaining_time": "1:37:53"}
+{"current_steps": 38, "total_steps": 1870, "loss": 1.4079, "lr": 4.995171745525401e-06, "epoch": 0.20320855614973263, "percentage": 2.03, "elapsed_time": "0:02:03", "remaining_time": "1:39:01"}
+{"current_steps": 39, "total_steps": 1870, "loss": 1.1997, "lr": 4.994907321790524e-06, "epoch": 0.20855614973262032, "percentage": 2.09, "elapsed_time": "0:02:06", "remaining_time": "1:38:48"}
+{"current_steps": 40, "total_steps": 1870, "loss": 0.8544, "lr": 4.994635856463811e-06, "epoch": 0.21390374331550802, "percentage": 2.14, "elapsed_time": "0:02:09", "remaining_time": "1:38:48"}
+{"current_steps": 41, "total_steps": 1870, "loss": 1.3907, "lr": 4.994357350311441e-06, "epoch": 0.2192513368983957, "percentage": 2.19, "elapsed_time": "0:02:15", "remaining_time": "1:40:36"}
+{"current_steps": 42, "total_steps": 1870, "loss": 1.0473, "lr": 4.994071804119467e-06, "epoch": 0.22459893048128343, "percentage": 2.25, "elapsed_time": "0:02:17", "remaining_time": "1:40:05"}
+{"current_steps": 43, "total_steps": 1870, "loss": 1.5007, "lr": 4.993779218693811e-06, "epoch": 0.22994652406417113, "percentage": 2.3, "elapsed_time": "0:02:20", "remaining_time": "1:39:46"}
+{"current_steps": 44, "total_steps": 1870, "loss": 0.8521, "lr": 4.99347959486026e-06, "epoch": 0.23529411764705882, "percentage": 2.35, "elapsed_time": "0:02:24", "remaining_time": "1:39:52"}
+{"current_steps": 45, "total_steps": 1870, "loss": 0.742, "lr": 4.99317293346447e-06, "epoch": 0.24064171122994651, "percentage": 2.41, "elapsed_time": "0:02:26", "remaining_time": "1:39:21"}
+{"current_steps": 46, "total_steps": 1870, "loss": 0.6611, "lr": 4.992859235371958e-06, "epoch": 0.24598930481283424, "percentage": 2.46, "elapsed_time": "0:02:28", "remaining_time": "1:37:57"}
+{"current_steps": 47, "total_steps": 1870, "loss": 0.7421, "lr": 4.992538501468101e-06, "epoch": 0.25133689839572193, "percentage": 2.51, "elapsed_time": "0:02:31", "remaining_time": "1:37:58"}
+{"current_steps": 48, "total_steps": 1870, "loss": 1.1311, "lr": 4.992210732658132e-06, "epoch": 0.25668449197860965, "percentage": 2.57, "elapsed_time": "0:02:34", "remaining_time": "1:37:47"}
+{"current_steps": 49, "total_steps": 1870, "loss": 1.2115, "lr": 4.991875929867143e-06, "epoch": 0.2620320855614973, "percentage": 2.62, "elapsed_time": "0:02:37", "remaining_time": "1:37:31"}
+{"current_steps": 50, "total_steps": 1870, "loss": 0.7334, "lr": 4.991534094040077e-06, "epoch": 0.26737967914438504, "percentage": 2.67, "elapsed_time": "0:02:41", "remaining_time": "1:37:46"}
+{"current_steps": 51, "total_steps": 1870, "loss": 0.7493, "lr": 4.991185226141726e-06, "epoch": 0.2727272727272727, "percentage": 2.73, "elapsed_time": "0:02:42", "remaining_time": "1:36:28"}
+{"current_steps": 52, "total_steps": 1870, "loss": 0.9573, "lr": 4.990829327156729e-06, "epoch": 0.27807486631016043, "percentage": 2.78, "elapsed_time": "0:02:44", "remaining_time": "1:36:01"}
+{"current_steps": 53, "total_steps": 1870, "loss": 0.7737, "lr": 4.990466398089571e-06, "epoch": 0.28342245989304815, "percentage": 2.83, "elapsed_time": "0:02:46", "remaining_time": "1:34:51"}
+{"current_steps": 54, "total_steps": 1870, "loss": 0.516, "lr": 4.99009643996458e-06, "epoch": 0.2887700534759358, "percentage": 2.89, "elapsed_time": "0:02:48", "remaining_time": "1:34:17"}
+{"current_steps": 55, "total_steps": 1870, "loss": 0.659, "lr": 4.989719453825918e-06, "epoch": 0.29411764705882354, "percentage": 2.94, "elapsed_time": "0:02:50", "remaining_time": "1:33:35"}
+{"current_steps": 56, "total_steps": 1870, "loss": 0.6734, "lr": 4.989335440737587e-06, "epoch": 0.2994652406417112, "percentage": 2.99, "elapsed_time": "0:02:52", "remaining_time": "1:33:14"}
+{"current_steps": 57, "total_steps": 1870, "loss": 0.7813, "lr": 4.9889444017834185e-06, "epoch": 0.3048128342245989, "percentage": 3.05, "elapsed_time": "0:02:54", "remaining_time": "1:32:16"}
+{"current_steps": 58, "total_steps": 1870, "loss": 0.8475, "lr": 4.988546338067078e-06, "epoch": 0.31016042780748665, "percentage": 3.1, "elapsed_time": "0:02:56", "remaining_time": "1:31:58"}
+{"current_steps": 59, "total_steps": 1870, "loss": 0.9743, "lr": 4.988141250712053e-06, "epoch": 0.3155080213903743, "percentage": 3.16, "elapsed_time": "0:03:01", "remaining_time": "1:32:48"}
+{"current_steps": 60, "total_steps": 1870, "loss": 0.8313, "lr": 4.987729140861657e-06, "epoch": 0.32085561497326204, "percentage": 3.21, "elapsed_time": "0:03:02", "remaining_time": "1:31:52"}
+{"current_steps": 61, "total_steps": 1870, "loss": 0.8487, "lr": 4.987310009679023e-06, "epoch": 0.32620320855614976, "percentage": 3.26, "elapsed_time": "0:03:04", "remaining_time": "1:31:16"}
+{"current_steps": 62, "total_steps": 1870, "loss": 0.7708, "lr": 4.986883858347101e-06, "epoch": 0.3315508021390374, "percentage": 3.32, "elapsed_time": "0:03:06", "remaining_time": "1:30:34"}
+{"current_steps": 63, "total_steps": 1870, "loss": 0.5743, "lr": 4.986450688068655e-06, "epoch": 0.33689839572192515, "percentage": 3.37, "elapsed_time": "0:03:08", "remaining_time": "1:30:12"}
+{"current_steps": 64, "total_steps": 1870, "loss": 0.7455, "lr": 4.986010500066258e-06, "epoch": 0.3422459893048128, "percentage": 3.42, "elapsed_time": "0:03:12", "remaining_time": "1:30:18"}
+{"current_steps": 65, "total_steps": 1870, "loss": 0.6992, "lr": 4.985563295582292e-06, "epoch": 0.34759358288770054, "percentage": 3.48, "elapsed_time": "0:03:13", "remaining_time": "1:29:36"}
+{"current_steps": 66, "total_steps": 1870, "loss": 0.8094, "lr": 4.98510907587894e-06, "epoch": 0.35294117647058826, "percentage": 3.53, "elapsed_time": "0:03:17", "remaining_time": "1:29:46"}
+{"current_steps": 67, "total_steps": 1870, "loss": 1.0877, "lr": 4.984647842238185e-06, "epoch": 0.3582887700534759, "percentage": 3.58, "elapsed_time": "0:03:22", "remaining_time": "1:30:53"}
+{"current_steps": 68, "total_steps": 1870, "loss": 0.5666, "lr": 4.984179595961806e-06, "epoch": 0.36363636363636365, "percentage": 3.64, "elapsed_time": "0:03:25", "remaining_time": "1:30:46"}
+{"current_steps": 69, "total_steps": 1870, "loss": 0.6734, "lr": 4.983704338371375e-06, "epoch": 0.3689839572192513, "percentage": 3.69, "elapsed_time": "0:03:27", "remaining_time": "1:30:06"}
+{"current_steps": 70, "total_steps": 1870, "loss": 0.5773, "lr": 4.983222070808255e-06, "epoch": 0.37433155080213903, "percentage": 3.74, "elapsed_time": "0:03:29", "remaining_time": "1:29:45"}
+{"current_steps": 71, "total_steps": 1870, "loss": 0.9197, "lr": 4.982732794633588e-06, "epoch": 0.37967914438502676, "percentage": 3.8, "elapsed_time": "0:03:31", "remaining_time": "1:29:18"}
+{"current_steps": 72, "total_steps": 1870, "loss": 0.7004, "lr": 4.982236511228301e-06, "epoch": 0.3850267379679144, "percentage": 3.85, "elapsed_time": "0:03:32", "remaining_time": "1:28:23"}
+{"current_steps": 73, "total_steps": 1870, "loss": 1.1037, "lr": 4.981733221993099e-06, "epoch": 0.39037433155080214, "percentage": 3.9, "elapsed_time": "0:03:35", "remaining_time": "1:28:29"}
+{"current_steps": 74, "total_steps": 1870, "loss": 0.917, "lr": 4.981222928348456e-06, "epoch": 0.39572192513368987, "percentage": 3.96, "elapsed_time": "0:03:38", "remaining_time": "1:28:25"}
+{"current_steps": 75, "total_steps": 1870, "loss": 0.8169, "lr": 4.98070563173462e-06, "epoch": 0.40106951871657753, "percentage": 4.01, "elapsed_time": "0:03:40", "remaining_time": "1:28:07"}
+{"current_steps": 76, "total_steps": 1870, "loss": 0.6608, "lr": 4.980181333611601e-06, "epoch": 0.40641711229946526, "percentage": 4.06, "elapsed_time": "0:03:44", "remaining_time": "1:28:28"}
+{"current_steps": 77, "total_steps": 1870, "loss": 0.6377, "lr": 4.979650035459171e-06, "epoch": 0.4117647058823529, "percentage": 4.12, "elapsed_time": "0:03:46", "remaining_time": "1:27:51"}
+{"current_steps": 78, "total_steps": 1870, "loss": 0.9951, "lr": 4.9791117387768575e-06, "epoch": 0.41711229946524064, "percentage": 4.17, "elapsed_time": "0:03:48", "remaining_time": "1:27:23"}
+{"current_steps": 79, "total_steps": 1870, "loss": 0.5495, "lr": 4.978566445083942e-06, "epoch": 0.42245989304812837, "percentage": 4.22, "elapsed_time": "0:03:50", "remaining_time": "1:27:02"}
+{"current_steps": 80, "total_steps": 1870, "loss": 0.6404, "lr": 4.978014155919455e-06, "epoch": 0.42780748663101603, "percentage": 4.28, "elapsed_time": "0:03:51", "remaining_time": "1:26:17"}
+{"current_steps": 81, "total_steps": 1870, "loss": 0.6956, "lr": 4.977454872842169e-06, "epoch": 0.43315508021390375, "percentage": 4.33, "elapsed_time": "0:03:53", "remaining_time": "1:26:04"}
+{"current_steps": 82, "total_steps": 1870, "loss": 0.9001, "lr": 4.976888597430597e-06, "epoch": 0.4385026737967914, "percentage": 4.39, "elapsed_time": "0:03:57", "remaining_time": "1:26:18"}
+{"current_steps": 83, "total_steps": 1870, "loss": 0.8242, "lr": 4.976315331282985e-06, "epoch": 0.44385026737967914, "percentage": 4.44, "elapsed_time": "0:04:01", "remaining_time": "1:26:34"}
+{"current_steps": 84, "total_steps": 1870, "loss": 0.6821, "lr": 4.9757350760173144e-06, "epoch": 0.44919786096256686, "percentage": 4.49, "elapsed_time": "0:04:04", "remaining_time": "1:26:30"}
+{"current_steps": 85, "total_steps": 1870, "loss": 0.8884, "lr": 4.975147833271288e-06, "epoch": 0.45454545454545453, "percentage": 4.55, "elapsed_time": "0:04:07", "remaining_time": "1:26:37"}
+{"current_steps": 86, "total_steps": 1870, "loss": 0.6627, "lr": 4.974553604702332e-06, "epoch": 0.45989304812834225, "percentage": 4.6, "elapsed_time": "0:04:11", "remaining_time": "1:26:57"}
+{"current_steps": 87, "total_steps": 1870, "loss": 0.7558, "lr": 4.973952391987589e-06, "epoch": 0.46524064171123, "percentage": 4.65, "elapsed_time": "0:04:12", "remaining_time": "1:26:19"}
+{"current_steps": 88, "total_steps": 1870, "loss": 0.9766, "lr": 4.9733441968239125e-06, "epoch": 0.47058823529411764, "percentage": 4.71, "elapsed_time": "0:04:14", "remaining_time": "1:25:56"}
+{"current_steps": 89, "total_steps": 1870, "loss": 0.5867, "lr": 4.972729020927866e-06, "epoch": 0.47593582887700536, "percentage": 4.76, "elapsed_time": "0:04:16", "remaining_time": "1:25:42"}
+{"current_steps": 90, "total_steps": 1870, "loss": 0.7517, "lr": 4.97210686603571e-06, "epoch": 0.48128342245989303, "percentage": 4.81, "elapsed_time": "0:04:18", "remaining_time": "1:25:16"}
+{"current_steps": 91, "total_steps": 1870, "loss": 0.6692, "lr": 4.97147773390341e-06, "epoch": 0.48663101604278075, "percentage": 4.87, "elapsed_time": "0:04:22", "remaining_time": "1:25:25"}
+{"current_steps": 92, "total_steps": 1870, "loss": 0.7875, "lr": 4.970841626306617e-06, "epoch": 0.4919786096256685, "percentage": 4.92, "elapsed_time": "0:04:24", "remaining_time": "1:25:15"}
+{"current_steps": 93, "total_steps": 1870, "loss": 0.9176, "lr": 4.970198545040673e-06, "epoch": 0.49732620320855614, "percentage": 4.97, "elapsed_time": "0:04:30", "remaining_time": "1:26:11"}
+{"current_steps": 94, "total_steps": 1870, "loss": 0.8047, "lr": 4.969548491920603e-06, "epoch": 0.5026737967914439, "percentage": 5.03, "elapsed_time": "0:04:34", "remaining_time": "1:26:24"}
+{"current_steps": 95, "total_steps": 1870, "loss": 0.8636, "lr": 4.968891468781105e-06, "epoch": 0.5080213903743316, "percentage": 5.08, "elapsed_time": "0:04:37", "remaining_time": "1:26:21"}
+{"current_steps": 96, "total_steps": 1870, "loss": 0.7283, "lr": 4.968227477476554e-06, "epoch": 0.5133689839572193, "percentage": 5.13, "elapsed_time": "0:04:38", "remaining_time": "1:25:46"}
+{"current_steps": 97, "total_steps": 1870, "loss": 0.9871, "lr": 4.9675565198809905e-06, "epoch": 0.5187165775401069, "percentage": 5.19, "elapsed_time": "0:04:43", "remaining_time": "1:26:13"}
+{"current_steps": 98, "total_steps": 1870, "loss": 0.8698, "lr": 4.966878597888114e-06, "epoch": 0.5240641711229946, "percentage": 5.24, "elapsed_time": "0:04:45", "remaining_time": "1:26:09"}
+{"current_steps": 99, "total_steps": 1870, "loss": 0.6065, "lr": 4.966193713411284e-06, "epoch": 0.5294117647058824, "percentage": 5.29, "elapsed_time": "0:04:47", "remaining_time": "1:25:50"}
+{"current_steps": 100, "total_steps": 1870, "loss": 0.5926, "lr": 4.965501868383507e-06, "epoch": 0.5347593582887701, "percentage": 5.35, "elapsed_time": "0:04:52", "remaining_time": "1:26:15"}
+{"current_steps": 101, "total_steps": 1870, "loss": 0.8591, "lr": 4.964803064757438e-06, "epoch": 0.5401069518716578, "percentage": 5.4, "elapsed_time": "0:04:55", "remaining_time": "1:26:10"}
+{"current_steps": 102, "total_steps": 1870, "loss": 0.6921, "lr": 4.964097304505371e-06, "epoch": 0.5454545454545454, "percentage": 5.45, "elapsed_time": "0:04:58", "remaining_time": "1:26:09"}
+{"current_steps": 103, "total_steps": 1870, "loss": 0.5718, "lr": 4.963384589619233e-06, "epoch": 0.5508021390374331, "percentage": 5.51, "elapsed_time": "0:05:00", "remaining_time": "1:25:52"}
+{"current_steps": 104, "total_steps": 1870, "loss": 0.7824, "lr": 4.962664922110581e-06, "epoch": 0.5561497326203209, "percentage": 5.56, "elapsed_time": "0:05:01", "remaining_time": "1:25:20"}
+{"current_steps": 105, "total_steps": 1870, "loss": 0.8677, "lr": 4.9619383040105954e-06, "epoch": 0.5614973262032086, "percentage": 5.61, "elapsed_time": "0:05:03", "remaining_time": "1:24:53"}
+{"current_steps": 106, "total_steps": 1870, "loss": 0.804, "lr": 4.961204737370071e-06, "epoch": 0.5668449197860963, "percentage": 5.67, "elapsed_time": "0:05:06", "remaining_time": "1:25:03"}
+{"current_steps": 107, "total_steps": 1870, "loss": 1.0349, "lr": 4.960464224259418e-06, "epoch": 0.5721925133689839, "percentage": 5.72, "elapsed_time": "0:05:12", "remaining_time": "1:25:46"}
+{"current_steps": 108, "total_steps": 1870, "loss": 0.4946, "lr": 4.95971676676865e-06, "epoch": 0.5775401069518716, "percentage": 5.78, "elapsed_time": "0:05:14", "remaining_time": "1:25:37"}
+{"current_steps": 109, "total_steps": 1870, "loss": 0.7878, "lr": 4.958962367007381e-06, "epoch": 0.5828877005347594, "percentage": 5.83, "elapsed_time": "0:05:16", "remaining_time": "1:25:14"}
+{"current_steps": 110, "total_steps": 1870, "loss": 0.6389, "lr": 4.958201027104818e-06, "epoch": 0.5882352941176471, "percentage": 5.88, "elapsed_time": "0:05:19", "remaining_time": "1:25:10"}
+{"current_steps": 111, "total_steps": 1870, "loss": 0.6094, "lr": 4.957432749209755e-06, "epoch": 0.5935828877005348, "percentage": 5.94, "elapsed_time": "0:05:22", "remaining_time": "1:25:06"}
+{"current_steps": 112, "total_steps": 1870, "loss": 0.7564, "lr": 4.95665753549057e-06, "epoch": 0.5989304812834224, "percentage": 5.99, "elapsed_time": "0:05:26", "remaining_time": "1:25:30"}
+{"current_steps": 113, "total_steps": 1870, "loss": 1.1311, "lr": 4.9558753881352165e-06, "epoch": 0.6042780748663101, "percentage": 6.04, "elapsed_time": "0:05:29", "remaining_time": "1:25:24"}
+{"current_steps": 114, "total_steps": 1870, "loss": 0.9121, "lr": 4.955086309351213e-06, "epoch": 0.6096256684491979, "percentage": 6.1, "elapsed_time": "0:05:31", "remaining_time": "1:25:12"}
+{"current_steps": 115, "total_steps": 1870, "loss": 0.5045, "lr": 4.9542903013656485e-06, "epoch": 0.6149732620320856, "percentage": 6.15, "elapsed_time": "0:05:33", "remaining_time": "1:24:44"}
+{"current_steps": 116, "total_steps": 1870, "loss": 0.6346, "lr": 4.953487366425163e-06, "epoch": 0.6203208556149733, "percentage": 6.2, "elapsed_time": "0:05:36", "remaining_time": "1:24:54"}
+{"current_steps": 117, "total_steps": 1870, "loss": 0.5257, "lr": 4.952677506795949e-06, "epoch": 0.6256684491978609, "percentage": 6.26, "elapsed_time": "0:05:38", "remaining_time": "1:24:28"}
+{"current_steps": 118, "total_steps": 1870, "loss": 0.6732, "lr": 4.951860724763743e-06, "epoch": 0.6310160427807486, "percentage": 6.31, "elapsed_time": "0:05:41", "remaining_time": "1:24:23"}
+{"current_steps": 119, "total_steps": 1870, "loss": 0.6556, "lr": 4.95103702263382e-06, "epoch": 0.6363636363636364, "percentage": 6.36, "elapsed_time": "0:05:42", "remaining_time": "1:24:06"}
+{"current_steps": 120, "total_steps": 1870, "loss": 0.6768, "lr": 4.950206402730984e-06, "epoch": 0.6417112299465241, "percentage": 6.42, "elapsed_time": "0:05:46", "remaining_time": "1:24:16"}
+{"current_steps": 121, "total_steps": 1870, "loss": 0.4773, "lr": 4.949368867399567e-06, "epoch": 0.6470588235294118, "percentage": 6.47, "elapsed_time": "0:05:48", "remaining_time": "1:23:54"}
+{"current_steps": 122, "total_steps": 1870, "loss": 1.0473, "lr": 4.948524419003415e-06, "epoch": 0.6524064171122995, "percentage": 6.52, "elapsed_time": "0:05:51", "remaining_time": "1:23:49"}
+{"current_steps": 123, "total_steps": 1870, "loss": 0.7472, "lr": 4.947673059925889e-06, "epoch": 0.6577540106951871, "percentage": 6.58, "elapsed_time": "0:05:55", "remaining_time": "1:24:13"}
+{"current_steps": 124, "total_steps": 1870, "loss": 0.7974, "lr": 4.9468147925698525e-06, "epoch": 0.6631016042780749, "percentage": 6.63, "elapsed_time": "0:05:59", "remaining_time": "1:24:20"}
+{"current_steps": 125, "total_steps": 1870, "loss": 0.5923, "lr": 4.945949619357668e-06, "epoch": 0.6684491978609626, "percentage": 6.68, "elapsed_time": "0:06:01", "remaining_time": "1:24:01"}
+{"current_steps": 126, "total_steps": 1870, "loss": 0.4737, "lr": 4.945077542731188e-06, "epoch": 0.6737967914438503, "percentage": 6.74, "elapsed_time": "0:06:03", "remaining_time": "1:23:46"}
+{"current_steps": 127, "total_steps": 1870, "loss": 0.7695, "lr": 4.94419856515175e-06, "epoch": 0.679144385026738, "percentage": 6.79, "elapsed_time": "0:06:06", "remaining_time": "1:23:44"}
+{"current_steps": 128, "total_steps": 1870, "loss": 0.7668, "lr": 4.943312689100166e-06, "epoch": 0.6844919786096256, "percentage": 6.84, "elapsed_time": "0:06:08", "remaining_time": "1:23:28"}
+{"current_steps": 129, "total_steps": 1870, "loss": 0.5666, "lr": 4.942419917076723e-06, "epoch": 0.6898395721925134, "percentage": 6.9, "elapsed_time": "0:06:11", "remaining_time": "1:23:40"}
+{"current_steps": 130, "total_steps": 1870, "loss": 0.6729, "lr": 4.941520251601167e-06, "epoch": 0.6951871657754011, "percentage": 6.95, "elapsed_time": "0:06:13", "remaining_time": "1:23:25"}
+{"current_steps": 131, "total_steps": 1870, "loss": 0.4296, "lr": 4.940613695212702e-06, "epoch": 0.7005347593582888, "percentage": 7.01, "elapsed_time": "0:06:15", "remaining_time": "1:22:58"}
+{"current_steps": 132, "total_steps": 1870, "loss": 0.9123, "lr": 4.939700250469979e-06, "epoch": 0.7058823529411765, "percentage": 7.06, "elapsed_time": "0:06:18", "remaining_time": "1:23:07"}
+{"current_steps": 133, "total_steps": 1870, "loss": 0.765, "lr": 4.938779919951092e-06, "epoch": 0.7112299465240641, "percentage": 7.11, "elapsed_time": "0:06:21", "remaining_time": "1:22:56"}
+{"current_steps": 134, "total_steps": 1870, "loss": 0.4831, "lr": 4.93785270625357e-06, "epoch": 0.7165775401069518, "percentage": 7.17, "elapsed_time": "0:06:23", "remaining_time": "1:22:52"}
+{"current_steps": 135, "total_steps": 1870, "loss": 0.6263, "lr": 4.936918611994368e-06, "epoch": 0.7219251336898396, "percentage": 7.22, "elapsed_time": "0:06:26", "remaining_time": "1:22:49"}
+{"current_steps": 136, "total_steps": 1870, "loss": 0.7421, "lr": 4.935977639809861e-06, "epoch": 0.7272727272727273, "percentage": 7.27, "elapsed_time": "0:06:30", "remaining_time": "1:22:57"}
+{"current_steps": 137, "total_steps": 1870, "loss": 0.5482, "lr": 4.935029792355834e-06, "epoch": 0.732620320855615, "percentage": 7.33, "elapsed_time": "0:06:34", "remaining_time": "1:23:11"}
+{"current_steps": 138, "total_steps": 1870, "loss": 0.8893, "lr": 4.934075072307481e-06, "epoch": 0.7379679144385026, "percentage": 7.38, "elapsed_time": "0:06:37", "remaining_time": "1:23:04"}
+{"current_steps": 139, "total_steps": 1870, "loss": 0.4719, "lr": 4.933113482359388e-06, "epoch": 0.7433155080213903, "percentage": 7.43, "elapsed_time": "0:06:38", "remaining_time": "1:22:44"}
+{"current_steps": 140, "total_steps": 1870, "loss": 0.6237, "lr": 4.932145025225535e-06, "epoch": 0.7486631016042781, "percentage": 7.49, "elapsed_time": "0:06:40", "remaining_time": "1:22:25"}
+{"current_steps": 141, "total_steps": 1870, "loss": 0.7627, "lr": 4.931169703639282e-06, "epoch": 0.7540106951871658, "percentage": 7.54, "elapsed_time": "0:06:42", "remaining_time": "1:22:12"}
+{"current_steps": 142, "total_steps": 1870, "loss": 0.6748, "lr": 4.930187520353363e-06, "epoch": 0.7593582887700535, "percentage": 7.59, "elapsed_time": "0:06:45", "remaining_time": "1:22:10"}
+{"current_steps": 143, "total_steps": 1870, "loss": 0.5698, "lr": 4.929198478139877e-06, "epoch": 0.7647058823529411, "percentage": 7.65, "elapsed_time": "0:06:47", "remaining_time": "1:22:00"}
+{"current_steps": 144, "total_steps": 1870, "loss": 0.5172, "lr": 4.928202579790285e-06, "epoch": 0.7700534759358288, "percentage": 7.7, "elapsed_time": "0:06:50", "remaining_time": "1:22:00"}
+{"current_steps": 145, "total_steps": 1870, "loss": 0.6379, "lr": 4.927199828115395e-06, "epoch": 0.7754010695187166, "percentage": 7.75, "elapsed_time": "0:06:51", "remaining_time": "1:21:38"}
+{"current_steps": 146, "total_steps": 1870, "loss": 0.7566, "lr": 4.9261902259453616e-06, "epoch": 0.7807486631016043, "percentage": 7.81, "elapsed_time": "0:06:55", "remaining_time": "1:21:44"}
+{"current_steps": 147, "total_steps": 1870, "loss": 0.9248, "lr": 4.925173776129669e-06, "epoch": 0.786096256684492, "percentage": 7.86, "elapsed_time": "0:07:00", "remaining_time": "1:22:11"}
+{"current_steps": 148, "total_steps": 1870, "loss": 0.4283, "lr": 4.9241504815371346e-06, "epoch": 0.7914438502673797, "percentage": 7.91, "elapsed_time": "0:07:02", "remaining_time": "1:21:53"}
+{"current_steps": 149, "total_steps": 1870, "loss": 0.6585, "lr": 4.923120345055887e-06, "epoch": 0.7967914438502673, "percentage": 7.97, "elapsed_time": "0:07:06", "remaining_time": "1:22:01"}
+{"current_steps": 150, "total_steps": 1870, "loss": 0.5589, "lr": 4.922083369593372e-06, "epoch": 0.8021390374331551, "percentage": 8.02, "elapsed_time": "0:07:07", "remaining_time": "1:21:44"}
+{"current_steps": 151, "total_steps": 1870, "loss": 0.8331, "lr": 4.921039558076335e-06, "epoch": 0.8074866310160428, "percentage": 8.07, "elapsed_time": "0:07:12", "remaining_time": "1:22:06"}
+{"current_steps": 152, "total_steps": 1870, "loss": 0.3931, "lr": 4.919988913450812e-06, "epoch": 0.8128342245989305, "percentage": 8.13, "elapsed_time": "0:07:15", "remaining_time": "1:22:03"}
+{"current_steps": 153, "total_steps": 1870, "loss": 0.7812, "lr": 4.918931438682132e-06, "epoch": 0.8181818181818182, "percentage": 8.18, "elapsed_time": "0:07:18", "remaining_time": "1:22:01"}
+{"current_steps": 154, "total_steps": 1870, "loss": 0.7923, "lr": 4.917867136754894e-06, "epoch": 0.8235294117647058, "percentage": 8.24, "elapsed_time": "0:07:20", "remaining_time": "1:21:52"}
+{"current_steps": 155, "total_steps": 1870, "loss": 0.6596, "lr": 4.916796010672969e-06, "epoch": 0.8288770053475936, "percentage": 8.29, "elapsed_time": "0:07:23", "remaining_time": "1:21:51"}
+{"current_steps": 156, "total_steps": 1870, "loss": 0.6742, "lr": 4.91571806345949e-06, "epoch": 0.8342245989304813, "percentage": 8.34, "elapsed_time": "0:07:25", "remaining_time": "1:21:39"}
+{"current_steps": 157, "total_steps": 1870, "loss": 0.7188, "lr": 4.91463329815684e-06, "epoch": 0.839572192513369, "percentage": 8.4, "elapsed_time": "0:07:27", "remaining_time": "1:21:22"}
+{"current_steps": 158, "total_steps": 1870, "loss": 0.52, "lr": 4.913541717826645e-06, "epoch": 0.8449197860962567, "percentage": 8.45, "elapsed_time": "0:07:30", "remaining_time": "1:21:23"}
+{"current_steps": 159, "total_steps": 1870, "loss": 0.4367, "lr": 4.912443325549767e-06, "epoch": 0.8502673796791443, "percentage": 8.5, "elapsed_time": "0:07:34", "remaining_time": "1:21:32"}
+{"current_steps": 160, "total_steps": 1870, "loss": 0.6559, "lr": 4.911338124426291e-06, "epoch": 0.8556149732620321, "percentage": 8.56, "elapsed_time": "0:07:37", "remaining_time": "1:21:29"}
+{"current_steps": 161, "total_steps": 1870, "loss": 0.7222, "lr": 4.910226117575525e-06, "epoch": 0.8609625668449198, "percentage": 8.61, "elapsed_time": "0:07:40", "remaining_time": "1:21:32"}
+{"current_steps": 162, "total_steps": 1870, "loss": 0.458, "lr": 4.909107308135978e-06, "epoch": 0.8663101604278075, "percentage": 8.66, "elapsed_time": "0:07:43", "remaining_time": "1:21:25"}
+{"current_steps": 163, "total_steps": 1870, "loss": 0.526, "lr": 4.907981699265364e-06, "epoch": 0.8716577540106952, "percentage": 8.72, "elapsed_time": "0:07:44", "remaining_time": "1:21:07"}
+{"current_steps": 164, "total_steps": 1870, "loss": 0.749, "lr": 4.906849294140587e-06, "epoch": 0.8770053475935828, "percentage": 8.77, "elapsed_time": "0:07:47", "remaining_time": "1:21:04"}
+{"current_steps": 165, "total_steps": 1870, "loss": 0.5973, "lr": 4.9057100959577285e-06, "epoch": 0.8823529411764706, "percentage": 8.82, "elapsed_time": "0:07:51", "remaining_time": "1:21:12"}
+{"current_steps": 166, "total_steps": 1870, "loss": 0.8493, "lr": 4.904564107932048e-06, "epoch": 0.8877005347593583, "percentage": 8.88, "elapsed_time": "0:07:53", "remaining_time": "1:21:00"}
+{"current_steps": 167, "total_steps": 1870, "loss": 0.7836, "lr": 4.903411333297966e-06, "epoch": 0.893048128342246, "percentage": 8.93, "elapsed_time": "0:07:56", "remaining_time": "1:20:58"}
+{"current_steps": 168, "total_steps": 1870, "loss": 0.6846, "lr": 4.902251775309057e-06, "epoch": 0.8983957219251337, "percentage": 8.98, "elapsed_time": "0:07:59", "remaining_time": "1:20:57"}
+{"current_steps": 169, "total_steps": 1870, "loss": 0.481, "lr": 4.901085437238041e-06, "epoch": 0.9037433155080213, "percentage": 9.04, "elapsed_time": "0:08:02", "remaining_time": "1:20:54"}
+{"current_steps": 170, "total_steps": 1870, "loss": 0.8458, "lr": 4.899912322376776e-06, "epoch": 0.9090909090909091, "percentage": 9.09, "elapsed_time": "0:08:03", "remaining_time": "1:20:38"}
+{"current_steps": 171, "total_steps": 1870, "loss": 0.7558, "lr": 4.8987324340362445e-06, "epoch": 0.9144385026737968, "percentage": 9.14, "elapsed_time": "0:08:08", "remaining_time": "1:20:49"}
+{"current_steps": 172, "total_steps": 1870, "loss": 0.6952, "lr": 4.897545775546545e-06, "epoch": 0.9197860962566845, "percentage": 9.2, "elapsed_time": "0:08:09", "remaining_time": "1:20:28"}
+{"current_steps": 173, "total_steps": 1870, "loss": 0.9228, "lr": 4.8963523502568886e-06, "epoch": 0.9251336898395722, "percentage": 9.25, "elapsed_time": "0:08:12", "remaining_time": "1:20:30"}
+{"current_steps": 174, "total_steps": 1870, "loss": 0.6523, "lr": 4.895152161535582e-06, "epoch": 0.93048128342246, "percentage": 9.3, "elapsed_time": "0:08:14", "remaining_time": "1:20:15"}
+{"current_steps": 175, "total_steps": 1870, "loss": 0.6227, "lr": 4.893945212770019e-06, "epoch": 0.9358288770053476, "percentage": 9.36, "elapsed_time": "0:08:17", "remaining_time": "1:20:16"}
+{"current_steps": 176, "total_steps": 1870, "loss": 0.7118, "lr": 4.892731507366678e-06, "epoch": 0.9411764705882353, "percentage": 9.41, "elapsed_time": "0:08:22", "remaining_time": "1:20:32"}
+{"current_steps": 177, "total_steps": 1870, "loss": 0.6376, "lr": 4.891511048751102e-06, "epoch": 0.946524064171123, "percentage": 9.47, "elapsed_time": "0:08:24", "remaining_time": "1:20:28"}
+{"current_steps": 178, "total_steps": 1870, "loss": 1.0352, "lr": 4.890283840367898e-06, "epoch": 0.9518716577540107, "percentage": 9.52, "elapsed_time": "0:08:29", "remaining_time": "1:20:44"}
+{"current_steps": 179, "total_steps": 1870, "loss": 0.665, "lr": 4.889049885680721e-06, "epoch": 0.9572192513368984, "percentage": 9.57, "elapsed_time": "0:08:32", "remaining_time": "1:20:41"}
+{"current_steps": 180, "total_steps": 1870, "loss": 0.6114, "lr": 4.887809188172268e-06, "epoch": 0.9625668449197861, "percentage": 9.63, "elapsed_time": "0:08:34", "remaining_time": "1:20:26"}
+{"current_steps": 181, "total_steps": 1870, "loss": 0.6999, "lr": 4.886561751344266e-06, "epoch": 0.9679144385026738, "percentage": 9.68, "elapsed_time": "0:08:35", "remaining_time": "1:20:13"}
+{"current_steps": 182, "total_steps": 1870, "loss": 0.695, "lr": 4.885307578717464e-06, "epoch": 0.9732620320855615, "percentage": 9.73, "elapsed_time": "0:08:40", "remaining_time": "1:20:29"}
+{"current_steps": 183, "total_steps": 1870, "loss": 0.7406, "lr": 4.8840466738316216e-06, "epoch": 0.9786096256684492, "percentage": 9.79, "elapsed_time": "0:08:45", "remaining_time": "1:20:47"}
+{"current_steps": 184, "total_steps": 1870, "loss": 0.6611, "lr": 4.882779040245499e-06, "epoch": 0.983957219251337, "percentage": 9.84, "elapsed_time": "0:08:47", "remaining_time": "1:20:33"}
+{"current_steps": 185, "total_steps": 1870, "loss": 0.5232, "lr": 4.881504681536847e-06, "epoch": 0.9893048128342246, "percentage": 9.89, "elapsed_time": "0:08:52", "remaining_time": "1:20:51"}
+{"current_steps": 186, "total_steps": 1870, "loss": 0.5211, "lr": 4.880223601302398e-06, "epoch": 0.9946524064171123, "percentage": 9.95, "elapsed_time": "0:08:56", "remaining_time": "1:20:59"}
+{"current_steps": 187, "total_steps": 1870, "loss": 0.5064, "lr": 4.878935803157856e-06, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:08:58", "remaining_time": "1:20:49"}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.55.0"
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1903904128,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/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
+  }
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-1467/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-163/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_5_math_7b/limo_filtered_correct/checkpoint-163/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}