Add files using upload-large-folder tool

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/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 %}

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "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": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.55.0"
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/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"
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/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
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-1230/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-1435/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/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 %}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "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": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.55.0"
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/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"
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/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
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-205/trainer_state.json

@@ -0,0 +1,1469 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 205,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004878048780487805,
+      "grad_norm": 37.90617752075195,
+      "learning_rate": 5e-06,
+      "loss": 5.3731,
+      "step": 1
+    },
+    {
+      "epoch": 0.00975609756097561,
+      "grad_norm": 32.92101287841797,
+      "learning_rate": 4.999997064365715e-06,
+      "loss": 3.7922,
+      "step": 2
+    },
+    {
+      "epoch": 0.014634146341463415,
+      "grad_norm": 28.488866806030273,
+      "learning_rate": 4.999988257469751e-06,
+      "loss": 3.3238,
+      "step": 3
+    },
+    {
+      "epoch": 0.01951219512195122,
+      "grad_norm": 28.274654388427734,
+      "learning_rate": 4.999973579332793e-06,
+      "loss": 3.5405,
+      "step": 4
+    },
+    {
+      "epoch": 0.024390243902439025,
+      "grad_norm": 18.761985778808594,
+      "learning_rate": 4.999953029989312e-06,
+      "loss": 2.7492,
+      "step": 5
+    },
+    {
+      "epoch": 0.02926829268292683,
+      "grad_norm": 9.646541595458984,
+      "learning_rate": 4.999926609487568e-06,
+      "loss": 1.7146,
+      "step": 6
+    },
+    {
+      "epoch": 0.03414634146341464,
+      "grad_norm": 15.763612747192383,
+      "learning_rate": 4.9998943178896106e-06,
+      "loss": 2.8485,
+      "step": 7
+    },
+    {
+      "epoch": 0.03902439024390244,
+      "grad_norm": 13.853349685668945,
+      "learning_rate": 4.999856155271276e-06,
+      "loss": 3.0975,
+      "step": 8
+    },
+    {
+      "epoch": 0.04390243902439024,
+      "grad_norm": 16.893617630004883,
+      "learning_rate": 4.999812121722191e-06,
+      "loss": 2.8534,
+      "step": 9
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 15.47554874420166,
+      "learning_rate": 4.999762217345766e-06,
+      "loss": 3.4569,
+      "step": 10
+    },
+    {
+      "epoch": 0.05365853658536585,
+      "grad_norm": 6.277958393096924,
+      "learning_rate": 4.999706442259205e-06,
+      "loss": 1.8088,
+      "step": 11
+    },
+    {
+      "epoch": 0.05853658536585366,
+      "grad_norm": 5.451688289642334,
+      "learning_rate": 4.999644796593492e-06,
+      "loss": 1.8104,
+      "step": 12
+    },
+    {
+      "epoch": 0.06341463414634146,
+      "grad_norm": 4.333822727203369,
+      "learning_rate": 4.999577280493407e-06,
+      "loss": 1.7201,
+      "step": 13
+    },
+    {
+      "epoch": 0.06829268292682927,
+      "grad_norm": 4.488610744476318,
+      "learning_rate": 4.99950389411751e-06,
+      "loss": 1.9804,
+      "step": 14
+    },
+    {
+      "epoch": 0.07317073170731707,
+      "grad_norm": 1.8763024806976318,
+      "learning_rate": 4.999424637638148e-06,
+      "loss": 0.9227,
+      "step": 15
+    },
+    {
+      "epoch": 0.07804878048780488,
+      "grad_norm": 2.98995304107666,
+      "learning_rate": 4.999339511241458e-06,
+      "loss": 1.2368,
+      "step": 16
+    },
+    {
+      "epoch": 0.08292682926829269,
+      "grad_norm": 5.778397083282471,
+      "learning_rate": 4.9992485151273584e-06,
+      "loss": 2.5745,
+      "step": 17
+    },
+    {
+      "epoch": 0.08780487804878048,
+      "grad_norm": 5.222808361053467,
+      "learning_rate": 4.999151649509554e-06,
+      "loss": 2.0987,
+      "step": 18
+    },
+    {
+      "epoch": 0.09268292682926829,
+      "grad_norm": 4.075173377990723,
+      "learning_rate": 4.9990489146155356e-06,
+      "loss": 1.7732,
+      "step": 19
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 4.210625171661377,
+      "learning_rate": 4.9989403106865765e-06,
+      "loss": 1.8928,
+      "step": 20
+    },
+    {
+      "epoch": 0.1024390243902439,
+      "grad_norm": 1.7968504428863525,
+      "learning_rate": 4.9988258379777334e-06,
+      "loss": 1.0457,
+      "step": 21
+    },
+    {
+      "epoch": 0.1073170731707317,
+      "grad_norm": 2.494248151779175,
+      "learning_rate": 4.998705496757846e-06,
+      "loss": 1.3236,
+      "step": 22
+    },
+    {
+      "epoch": 0.11219512195121951,
+      "grad_norm": 4.312766075134277,
+      "learning_rate": 4.998579287309538e-06,
+      "loss": 2.4289,
+      "step": 23
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 5.361437797546387,
+      "learning_rate": 4.998447209929211e-06,
+      "loss": 1.7608,
+      "step": 24
+    },
+    {
+      "epoch": 0.12195121951219512,
+      "grad_norm": 1.4642046689987183,
+      "learning_rate": 4.998309264927053e-06,
+      "loss": 0.7571,
+      "step": 25
+    },
+    {
+      "epoch": 0.12682926829268293,
+      "grad_norm": 3.642005205154419,
+      "learning_rate": 4.998165452627025e-06,
+      "loss": 1.0634,
+      "step": 26
+    },
+    {
+      "epoch": 0.13170731707317074,
+      "grad_norm": 3.2727863788604736,
+      "learning_rate": 4.998015773366874e-06,
+      "loss": 1.4016,
+      "step": 27
+    },
+    {
+      "epoch": 0.13658536585365855,
+      "grad_norm": 1.5661338567733765,
+      "learning_rate": 4.997860227498122e-06,
+      "loss": 0.8305,
+      "step": 28
+    },
+    {
+      "epoch": 0.14146341463414633,
+      "grad_norm": 3.3989508152008057,
+      "learning_rate": 4.99769881538607e-06,
+      "loss": 1.8744,
+      "step": 29
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 3.512221574783325,
+      "learning_rate": 4.997531537409794e-06,
+      "loss": 1.7701,
+      "step": 30
+    },
+    {
+      "epoch": 0.15121951219512195,
+      "grad_norm": 2.261887311935425,
+      "learning_rate": 4.99735839396215e-06,
+      "loss": 1.0653,
+      "step": 31
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 2.2495696544647217,
+      "learning_rate": 4.9971793854497655e-06,
+      "loss": 1.1914,
+      "step": 32
+    },
+    {
+      "epoch": 0.16097560975609757,
+      "grad_norm": 4.262424468994141,
+      "learning_rate": 4.996994512293042e-06,
+      "loss": 1.7311,
+      "step": 33
+    },
+    {
+      "epoch": 0.16585365853658537,
+      "grad_norm": 3.361311674118042,
+      "learning_rate": 4.996803774926157e-06,
+      "loss": 1.4482,
+      "step": 34
+    },
+    {
+      "epoch": 0.17073170731707318,
+      "grad_norm": 1.5855786800384521,
+      "learning_rate": 4.996607173797059e-06,
+      "loss": 1.3959,
+      "step": 35
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 2.5001468658447266,
+      "learning_rate": 4.996404709367466e-06,
+      "loss": 1.3452,
+      "step": 36
+    },
+    {
+      "epoch": 0.18048780487804877,
+      "grad_norm": 2.7903096675872803,
+      "learning_rate": 4.996196382112868e-06,
+      "loss": 1.018,
+      "step": 37
+    },
+    {
+      "epoch": 0.18536585365853658,
+      "grad_norm": 2.7586171627044678,
+      "learning_rate": 4.9959821925225235e-06,
+      "loss": 1.291,
+      "step": 38
+    },
+    {
+      "epoch": 0.1902439024390244,
+      "grad_norm": 2.873840808868408,
+      "learning_rate": 4.995762141099456e-06,
+      "loss": 1.1418,
+      "step": 39
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 1.6896076202392578,
+      "learning_rate": 4.995536228360461e-06,
+      "loss": 1.1662,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4597285985946655,
+      "learning_rate": 4.995304454836095e-06,
+      "loss": 1.0373,
+      "step": 41
+    },
+    {
+      "epoch": 0.2048780487804878,
+      "grad_norm": 2.4222421646118164,
+      "learning_rate": 4.9950668210706795e-06,
+      "loss": 1.1895,
+      "step": 42
+    },
+    {
+      "epoch": 0.2097560975609756,
+      "grad_norm": 3.295085906982422,
+      "learning_rate": 4.994823327622299e-06,
+      "loss": 1.4166,
+      "step": 43
+    },
+    {
+      "epoch": 0.2146341463414634,
+      "grad_norm": 1.8216716051101685,
+      "learning_rate": 4.9945739750628e-06,
+      "loss": 1.0009,
+      "step": 44
+    },
+    {
+      "epoch": 0.21951219512195122,
+      "grad_norm": 2.2421364784240723,
+      "learning_rate": 4.994318763977789e-06,
+      "loss": 1.1999,
+      "step": 45
+    },
+    {
+      "epoch": 0.22439024390243903,
+      "grad_norm": 5.6812744140625,
+      "learning_rate": 4.994057694966632e-06,
+      "loss": 1.3831,
+      "step": 46
+    },
+    {
+      "epoch": 0.22926829268292684,
+      "grad_norm": 1.477816104888916,
+      "learning_rate": 4.993790768642449e-06,
+      "loss": 1.1419,
+      "step": 47
+    },
+    {
+      "epoch": 0.23414634146341465,
+      "grad_norm": 4.485177993774414,
+      "learning_rate": 4.99351798563212e-06,
+      "loss": 1.9434,
+      "step": 48
+    },
+    {
+      "epoch": 0.23902439024390243,
+      "grad_norm": 2.770219326019287,
+      "learning_rate": 4.993239346576278e-06,
+      "loss": 1.3214,
+      "step": 49
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 2.721611976623535,
+      "learning_rate": 4.99295485212931e-06,
+      "loss": 1.4329,
+      "step": 50
+    },
+    {
+      "epoch": 0.24878048780487805,
+      "grad_norm": 3.714306592941284,
+      "learning_rate": 4.992664502959351e-06,
+      "loss": 1.372,
+      "step": 51
+    },
+    {
+      "epoch": 0.25365853658536586,
+      "grad_norm": 1.2679803371429443,
+      "learning_rate": 4.99236829974829e-06,
+      "loss": 0.8086,
+      "step": 52
+    },
+    {
+      "epoch": 0.25853658536585367,
+      "grad_norm": 1.6986169815063477,
+      "learning_rate": 4.992066243191762e-06,
+      "loss": 1.2012,
+      "step": 53
+    },
+    {
+      "epoch": 0.2634146341463415,
+      "grad_norm": 1.3443604707717896,
+      "learning_rate": 4.991758333999148e-06,
+      "loss": 0.8986,
+      "step": 54
+    },
+    {
+      "epoch": 0.2682926829268293,
+      "grad_norm": 2.0896975994110107,
+      "learning_rate": 4.991444572893575e-06,
+      "loss": 0.8819,
+      "step": 55
+    },
+    {
+      "epoch": 0.2731707317073171,
+      "grad_norm": 1.255516529083252,
+      "learning_rate": 4.991124960611916e-06,
+      "loss": 0.6255,
+      "step": 56
+    },
+    {
+      "epoch": 0.2780487804878049,
+      "grad_norm": 2.125410318374634,
+      "learning_rate": 4.99079949790478e-06,
+      "loss": 0.9983,
+      "step": 57
+    },
+    {
+      "epoch": 0.28292682926829266,
+      "grad_norm": 2.0312907695770264,
+      "learning_rate": 4.99046818553652e-06,
+      "loss": 1.1137,
+      "step": 58
+    },
+    {
+      "epoch": 0.28780487804878047,
+      "grad_norm": 2.904625177383423,
+      "learning_rate": 4.9901310242852246e-06,
+      "loss": 1.2009,
+      "step": 59
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 2.512932777404785,
+      "learning_rate": 4.9897880149427206e-06,
+      "loss": 1.2234,
+      "step": 60
+    },
+    {
+      "epoch": 0.2975609756097561,
+      "grad_norm": 2.5621752738952637,
+      "learning_rate": 4.989439158314566e-06,
+      "loss": 1.2354,
+      "step": 61
+    },
+    {
+      "epoch": 0.3024390243902439,
+      "grad_norm": 1.0051912069320679,
+      "learning_rate": 4.989084455220056e-06,
+      "loss": 0.614,
+      "step": 62
+    },
+    {
+      "epoch": 0.3073170731707317,
+      "grad_norm": 1.5008565187454224,
+      "learning_rate": 4.988723906492212e-06,
+      "loss": 1.002,
+      "step": 63
+    },
+    {
+      "epoch": 0.3121951219512195,
+      "grad_norm": 1.1436376571655273,
+      "learning_rate": 4.988357512977785e-06,
+      "loss": 0.6483,
+      "step": 64
+    },
+    {
+      "epoch": 0.3170731707317073,
+      "grad_norm": 1.16792893409729,
+      "learning_rate": 4.987985275537252e-06,
+      "loss": 0.638,
+      "step": 65
+    },
+    {
+      "epoch": 0.32195121951219513,
+      "grad_norm": 1.5670536756515503,
+      "learning_rate": 4.9876071950448185e-06,
+      "loss": 1.0274,
+      "step": 66
+    },
+    {
+      "epoch": 0.32682926829268294,
+      "grad_norm": 1.357515811920166,
+      "learning_rate": 4.987223272388407e-06,
+      "loss": 0.7612,
+      "step": 67
+    },
+    {
+      "epoch": 0.33170731707317075,
+      "grad_norm": 1.8383222818374634,
+      "learning_rate": 4.986833508469663e-06,
+      "loss": 1.1496,
+      "step": 68
+    },
+    {
+      "epoch": 0.33658536585365856,
+      "grad_norm": 2.8976657390594482,
+      "learning_rate": 4.98643790420395e-06,
+      "loss": 0.9924,
+      "step": 69
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 1.7679390907287598,
+      "learning_rate": 4.986036460520348e-06,
+      "loss": 0.9408,
+      "step": 70
+    },
+    {
+      "epoch": 0.3463414634146341,
+      "grad_norm": 2.3815059661865234,
+      "learning_rate": 4.98562917836165e-06,
+      "loss": 1.2923,
+      "step": 71
+    },
+    {
+      "epoch": 0.35121951219512193,
+      "grad_norm": 1.679026484489441,
+      "learning_rate": 4.985216058684362e-06,
+      "loss": 0.8476,
+      "step": 72
+    },
+    {
+      "epoch": 0.35609756097560974,
+      "grad_norm": 1.7254586219787598,
+      "learning_rate": 4.984797102458697e-06,
+      "loss": 1.1775,
+      "step": 73
+    },
+    {
+      "epoch": 0.36097560975609755,
+      "grad_norm": 1.195844292640686,
+      "learning_rate": 4.984372310668579e-06,
+      "loss": 0.6664,
+      "step": 74
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 1.754431128501892,
+      "learning_rate": 4.983941684311633e-06,
+      "loss": 1.4361,
+      "step": 75
+    },
+    {
+      "epoch": 0.37073170731707317,
+      "grad_norm": 1.8255788087844849,
+      "learning_rate": 4.983505224399188e-06,
+      "loss": 0.8977,
+      "step": 76
+    },
+    {
+      "epoch": 0.375609756097561,
+      "grad_norm": 1.340451717376709,
+      "learning_rate": 4.983062931956275e-06,
+      "loss": 0.9432,
+      "step": 77
+    },
+    {
+      "epoch": 0.3804878048780488,
+      "grad_norm": 1.7810503244400024,
+      "learning_rate": 4.9826148080216195e-06,
+      "loss": 1.0463,
+      "step": 78
+    },
+    {
+      "epoch": 0.3853658536585366,
+      "grad_norm": 1.729826807975769,
+      "learning_rate": 4.9821608536476445e-06,
+      "loss": 1.4451,
+      "step": 79
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 2.6638681888580322,
+      "learning_rate": 4.981701069900465e-06,
+      "loss": 1.0409,
+      "step": 80
+    },
+    {
+      "epoch": 0.3951219512195122,
+      "grad_norm": 1.467076301574707,
+      "learning_rate": 4.9812354578598876e-06,
+      "loss": 0.8596,
+      "step": 81
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.453657627105713,
+      "learning_rate": 4.980764018619405e-06,
+      "loss": 0.9033,
+      "step": 82
+    },
+    {
+      "epoch": 0.40487804878048783,
+      "grad_norm": 1.9025623798370361,
+      "learning_rate": 4.980286753286196e-06,
+      "loss": 1.0586,
+      "step": 83
+    },
+    {
+      "epoch": 0.4097560975609756,
+      "grad_norm": 1.4698103666305542,
+      "learning_rate": 4.97980366298112e-06,
+      "loss": 0.8611,
+      "step": 84
+    },
+    {
+      "epoch": 0.4146341463414634,
+      "grad_norm": 1.6086381673812866,
+      "learning_rate": 4.97931474883872e-06,
+      "loss": 0.8884,
+      "step": 85
+    },
+    {
+      "epoch": 0.4195121951219512,
+      "grad_norm": 1.6679224967956543,
+      "learning_rate": 4.978820012007213e-06,
+      "loss": 0.969,
+      "step": 86
+    },
+    {
+      "epoch": 0.424390243902439,
+      "grad_norm": 1.5308334827423096,
+      "learning_rate": 4.978319453648495e-06,
+      "loss": 1.0345,
+      "step": 87
+    },
+    {
+      "epoch": 0.4292682926829268,
+      "grad_norm": 1.7788817882537842,
+      "learning_rate": 4.977813074938128e-06,
+      "loss": 0.9649,
+      "step": 88
+    },
+    {
+      "epoch": 0.43414634146341463,
+      "grad_norm": 1.591383934020996,
+      "learning_rate": 4.977300877065347e-06,
+      "loss": 0.9299,
+      "step": 89
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 1.525985836982727,
+      "learning_rate": 4.976782861233053e-06,
+      "loss": 0.7272,
+      "step": 90
+    },
+    {
+      "epoch": 0.44390243902439025,
+      "grad_norm": 2.7333128452301025,
+      "learning_rate": 4.976259028657812e-06,
+      "loss": 0.6694,
+      "step": 91
+    },
+    {
+      "epoch": 0.44878048780487806,
+      "grad_norm": 1.2718108892440796,
+      "learning_rate": 4.975729380569845e-06,
+      "loss": 0.8037,
+      "step": 92
+    },
+    {
+      "epoch": 0.45365853658536587,
+      "grad_norm": 1.157771110534668,
+      "learning_rate": 4.975193918213035e-06,
+      "loss": 0.52,
+      "step": 93
+    },
+    {
+      "epoch": 0.4585365853658537,
+      "grad_norm": 1.0602248907089233,
+      "learning_rate": 4.974652642844921e-06,
+      "loss": 0.7135,
+      "step": 94
+    },
+    {
+      "epoch": 0.4634146341463415,
+      "grad_norm": 2.418555974960327,
+      "learning_rate": 4.974105555736693e-06,
+      "loss": 1.0996,
+      "step": 95
+    },
+    {
+      "epoch": 0.4682926829268293,
+      "grad_norm": 1.1728110313415527,
+      "learning_rate": 4.973552658173186e-06,
+      "loss": 0.7268,
+      "step": 96
+    },
+    {
+      "epoch": 0.47317073170731705,
+      "grad_norm": 1.943113088607788,
+      "learning_rate": 4.972993951452887e-06,
+      "loss": 0.9091,
+      "step": 97
+    },
+    {
+      "epoch": 0.47804878048780486,
+      "grad_norm": 5.063096523284912,
+      "learning_rate": 4.9724294368879214e-06,
+      "loss": 0.8242,
+      "step": 98
+    },
+    {
+      "epoch": 0.48292682926829267,
+      "grad_norm": 1.5232555866241455,
+      "learning_rate": 4.971859115804055e-06,
+      "loss": 1.0543,
+      "step": 99
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 1.1453967094421387,
+      "learning_rate": 4.9712829895406935e-06,
+      "loss": 0.8209,
+      "step": 100
+    },
+    {
+      "epoch": 0.4926829268292683,
+      "grad_norm": 2.12345814704895,
+      "learning_rate": 4.970701059450872e-06,
+      "loss": 0.5849,
+      "step": 101
+    },
+    {
+      "epoch": 0.4975609756097561,
+      "grad_norm": 1.2201842069625854,
+      "learning_rate": 4.970113326901258e-06,
+      "loss": 0.9969,
+      "step": 102
+    },
+    {
+      "epoch": 0.5024390243902439,
+      "grad_norm": 1.3047524690628052,
+      "learning_rate": 4.9695197932721455e-06,
+      "loss": 0.9339,
+      "step": 103
+    },
+    {
+      "epoch": 0.5073170731707317,
+      "grad_norm": 1.6083660125732422,
+      "learning_rate": 4.968920459957453e-06,
+      "loss": 0.9702,
+      "step": 104
+    },
+    {
+      "epoch": 0.5121951219512195,
+      "grad_norm": 1.5247286558151245,
+      "learning_rate": 4.968315328364719e-06,
+      "loss": 1.0449,
+      "step": 105
+    },
+    {
+      "epoch": 0.5170731707317073,
+      "grad_norm": 1.354805588722229,
+      "learning_rate": 4.9677043999151e-06,
+      "loss": 1.1431,
+      "step": 106
+    },
+    {
+      "epoch": 0.5219512195121951,
+      "grad_norm": 1.088321328163147,
+      "learning_rate": 4.967087676043366e-06,
+      "loss": 0.519,
+      "step": 107
+    },
+    {
+      "epoch": 0.526829268292683,
+      "grad_norm": 1.5086662769317627,
+      "learning_rate": 4.966465158197897e-06,
+      "loss": 0.9357,
+      "step": 108
+    },
+    {
+      "epoch": 0.5317073170731708,
+      "grad_norm": 1.3161298036575317,
+      "learning_rate": 4.965836847840681e-06,
+      "loss": 0.7234,
+      "step": 109
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 1.4465640783309937,
+      "learning_rate": 4.96520274644731e-06,
+      "loss": 0.8911,
+      "step": 110
+    },
+    {
+      "epoch": 0.5414634146341464,
+      "grad_norm": 1.0576995611190796,
+      "learning_rate": 4.964562855506976e-06,
+      "loss": 0.7254,
+      "step": 111
+    },
+    {
+      "epoch": 0.5463414634146342,
+      "grad_norm": 1.1018916368484497,
+      "learning_rate": 4.963917176522466e-06,
+      "loss": 0.6603,
+      "step": 112
+    },
+    {
+      "epoch": 0.551219512195122,
+      "grad_norm": 2.150622606277466,
+      "learning_rate": 4.963265711010164e-06,
+      "loss": 1.0451,
+      "step": 113
+    },
+    {
+      "epoch": 0.5560975609756098,
+      "grad_norm": 1.7743186950683594,
+      "learning_rate": 4.9626084605000395e-06,
+      "loss": 0.8717,
+      "step": 114
+    },
+    {
+      "epoch": 0.5609756097560976,
+      "grad_norm": 1.205291509628296,
+      "learning_rate": 4.961945426535652e-06,
+      "loss": 0.5802,
+      "step": 115
+    },
+    {
+      "epoch": 0.5658536585365853,
+      "grad_norm": 1.3969353437423706,
+      "learning_rate": 4.961276610674141e-06,
+      "loss": 0.9158,
+      "step": 116
+    },
+    {
+      "epoch": 0.5707317073170731,
+      "grad_norm": 1.2318240404129028,
+      "learning_rate": 4.960602014486225e-06,
+      "loss": 1.0086,
+      "step": 117
+    },
+    {
+      "epoch": 0.5756097560975609,
+      "grad_norm": 1.2202470302581787,
+      "learning_rate": 4.959921639556199e-06,
+      "loss": 0.7888,
+      "step": 118
+    },
+    {
+      "epoch": 0.5804878048780487,
+      "grad_norm": 1.1564440727233887,
+      "learning_rate": 4.959235487481928e-06,
+      "loss": 1.0053,
+      "step": 119
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 1.2278865575790405,
+      "learning_rate": 4.958543559874846e-06,
+      "loss": 0.5486,
+      "step": 120
+    },
+    {
+      "epoch": 0.5902439024390244,
+      "grad_norm": 1.5465888977050781,
+      "learning_rate": 4.9578458583599495e-06,
+      "loss": 0.8232,
+      "step": 121
+    },
+    {
+      "epoch": 0.5951219512195122,
+      "grad_norm": 1.6284047365188599,
+      "learning_rate": 4.957142384575795e-06,
+      "loss": 0.7773,
+      "step": 122
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1794490814208984,
+      "learning_rate": 4.956433140174498e-06,
+      "loss": 0.8236,
+      "step": 123
+    },
+    {
+      "epoch": 0.6048780487804878,
+      "grad_norm": 1.2404091358184814,
+      "learning_rate": 4.9557181268217225e-06,
+      "loss": 0.8611,
+      "step": 124
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 1.2188373804092407,
+      "learning_rate": 4.954997346196683e-06,
+      "loss": 1.2922,
+      "step": 125
+    },
+    {
+      "epoch": 0.6146341463414634,
+      "grad_norm": 1.1514503955841064,
+      "learning_rate": 4.954270799992138e-06,
+      "loss": 0.7073,
+      "step": 126
+    },
+    {
+      "epoch": 0.6195121951219512,
+      "grad_norm": 1.285913109779358,
+      "learning_rate": 4.953538489914387e-06,
+      "loss": 0.729,
+      "step": 127
+    },
+    {
+      "epoch": 0.624390243902439,
+      "grad_norm": 1.8677104711532593,
+      "learning_rate": 4.9528004176832654e-06,
+      "loss": 0.6211,
+      "step": 128
+    },
+    {
+      "epoch": 0.6292682926829268,
+      "grad_norm": 1.2369698286056519,
+      "learning_rate": 4.952056585032142e-06,
+      "loss": 1.0311,
+      "step": 129
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 1.186990737915039,
+      "learning_rate": 4.951306993707913e-06,
+      "loss": 0.8207,
+      "step": 130
+    },
+    {
+      "epoch": 0.6390243902439025,
+      "grad_norm": 1.189424991607666,
+      "learning_rate": 4.950551645470998e-06,
+      "loss": 0.7853,
+      "step": 131
+    },
+    {
+      "epoch": 0.6439024390243903,
+      "grad_norm": 1.3477216958999634,
+      "learning_rate": 4.9497905420953406e-06,
+      "loss": 0.7271,
+      "step": 132
+    },
+    {
+      "epoch": 0.6487804878048781,
+      "grad_norm": 1.368592619895935,
+      "learning_rate": 4.949023685368395e-06,
+      "loss": 0.7394,
+      "step": 133
+    },
+    {
+      "epoch": 0.6536585365853659,
+      "grad_norm": 1.2769527435302734,
+      "learning_rate": 4.948251077091131e-06,
+      "loss": 1.0713,
+      "step": 134
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "grad_norm": 1.1477972269058228,
+      "learning_rate": 4.947472719078025e-06,
+      "loss": 0.841,
+      "step": 135
+    },
+    {
+      "epoch": 0.6634146341463415,
+      "grad_norm": 1.0983368158340454,
+      "learning_rate": 4.9466886131570565e-06,
+      "loss": 0.8665,
+      "step": 136
+    },
+    {
+      "epoch": 0.6682926829268293,
+      "grad_norm": 1.2526847124099731,
+      "learning_rate": 4.945898761169704e-06,
+      "loss": 1.0613,
+      "step": 137
+    },
+    {
+      "epoch": 0.6731707317073171,
+      "grad_norm": 1.1426396369934082,
+      "learning_rate": 4.945103164970941e-06,
+      "loss": 0.6248,
+      "step": 138
+    },
+    {
+      "epoch": 0.6780487804878049,
+      "grad_norm": 1.3275880813598633,
+      "learning_rate": 4.9443018264292304e-06,
+      "loss": 0.755,
+      "step": 139
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 1.4942073822021484,
+      "learning_rate": 4.9434947474265225e-06,
+      "loss": 0.9451,
+      "step": 140
+    },
+    {
+      "epoch": 0.6878048780487804,
+      "grad_norm": 1.1777600049972534,
+      "learning_rate": 4.942681929858249e-06,
+      "loss": 1.0505,
+      "step": 141
+    },
+    {
+      "epoch": 0.6926829268292682,
+      "grad_norm": 1.2474116086959839,
+      "learning_rate": 4.941863375633315e-06,
+      "loss": 0.9174,
+      "step": 142
+    },
+    {
+      "epoch": 0.697560975609756,
+      "grad_norm": 1.5067697763442993,
+      "learning_rate": 4.9410390866741056e-06,
+      "loss": 0.7737,
+      "step": 143
+    },
+    {
+      "epoch": 0.7024390243902439,
+      "grad_norm": 1.3016574382781982,
+      "learning_rate": 4.9402090649164655e-06,
+      "loss": 0.7588,
+      "step": 144
+    },
+    {
+      "epoch": 0.7073170731707317,
+      "grad_norm": 1.652600884437561,
+      "learning_rate": 4.9393733123097085e-06,
+      "loss": 1.0588,
+      "step": 145
+    },
+    {
+      "epoch": 0.7121951219512195,
+      "grad_norm": 1.267997145652771,
+      "learning_rate": 4.9385318308166065e-06,
+      "loss": 0.8996,
+      "step": 146
+    },
+    {
+      "epoch": 0.7170731707317073,
+      "grad_norm": 1.8560484647750854,
+      "learning_rate": 4.937684622413385e-06,
+      "loss": 0.6286,
+      "step": 147
+    },
+    {
+      "epoch": 0.7219512195121951,
+      "grad_norm": 1.4419782161712646,
+      "learning_rate": 4.9368316890897185e-06,
+      "loss": 0.9818,
+      "step": 148
+    },
+    {
+      "epoch": 0.7268292682926829,
+      "grad_norm": 1.134084701538086,
+      "learning_rate": 4.9359730328487264e-06,
+      "loss": 0.5246,
+      "step": 149
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 1.0102615356445312,
+      "learning_rate": 4.935108655706972e-06,
+      "loss": 0.7948,
+      "step": 150
+    },
+    {
+      "epoch": 0.7365853658536585,
+      "grad_norm": 1.3480703830718994,
+      "learning_rate": 4.934238559694448e-06,
+      "loss": 1.0951,
+      "step": 151
+    },
+    {
+      "epoch": 0.7414634146341463,
+      "grad_norm": 1.4133951663970947,
+      "learning_rate": 4.9333627468545845e-06,
+      "loss": 0.6936,
+      "step": 152
+    },
+    {
+      "epoch": 0.7463414634146341,
+      "grad_norm": 1.3072413206100464,
+      "learning_rate": 4.932481219244231e-06,
+      "loss": 0.799,
+      "step": 153
+    },
+    {
+      "epoch": 0.751219512195122,
+      "grad_norm": 1.3893049955368042,
+      "learning_rate": 4.931593978933666e-06,
+      "loss": 0.7375,
+      "step": 154
+    },
+    {
+      "epoch": 0.7560975609756098,
+      "grad_norm": 1.2313531637191772,
+      "learning_rate": 4.930701028006577e-06,
+      "loss": 0.9487,
+      "step": 155
+    },
+    {
+      "epoch": 0.7609756097560976,
+      "grad_norm": 1.3426295518875122,
+      "learning_rate": 4.929802368560066e-06,
+      "loss": 0.7542,
+      "step": 156
+    },
+    {
+      "epoch": 0.7658536585365854,
+      "grad_norm": 1.5280004739761353,
+      "learning_rate": 4.928898002704642e-06,
+      "loss": 0.8784,
+      "step": 157
+    },
+    {
+      "epoch": 0.7707317073170732,
+      "grad_norm": 1.3149527311325073,
+      "learning_rate": 4.927987932564215e-06,
+      "loss": 0.7247,
+      "step": 158
+    },
+    {
+      "epoch": 0.775609756097561,
+      "grad_norm": 1.073188304901123,
+      "learning_rate": 4.927072160276092e-06,
+      "loss": 0.7826,
+      "step": 159
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 1.426188588142395,
+      "learning_rate": 4.926150687990969e-06,
+      "loss": 0.6129,
+      "step": 160
+    },
+    {
+      "epoch": 0.7853658536585366,
+      "grad_norm": 1.2348767518997192,
+      "learning_rate": 4.925223517872934e-06,
+      "loss": 0.9191,
+      "step": 161
+    },
+    {
+      "epoch": 0.7902439024390244,
+      "grad_norm": 1.599665641784668,
+      "learning_rate": 4.9242906520994484e-06,
+      "loss": 1.0177,
+      "step": 162
+    },
+    {
+      "epoch": 0.7951219512195122,
+      "grad_norm": 1.1841332912445068,
+      "learning_rate": 4.923352092861358e-06,
+      "loss": 0.8342,
+      "step": 163
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0213048458099365,
+      "learning_rate": 4.922407842362875e-06,
+      "loss": 0.6292,
+      "step": 164
+    },
+    {
+      "epoch": 0.8048780487804879,
+      "grad_norm": 1.1878992319107056,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.9357,
+      "step": 165
+    },
+    {
+      "epoch": 0.8097560975609757,
+      "grad_norm": 1.297462821006775,
+      "learning_rate": 4.920502276468408e-06,
+      "loss": 0.8829,
+      "step": 166
+    },
+    {
+      "epoch": 0.8146341463414634,
+      "grad_norm": 1.1800835132598877,
+      "learning_rate": 4.9195409655476605e-06,
+      "loss": 0.712,
+      "step": 167
+    },
+    {
+      "epoch": 0.8195121951219512,
+      "grad_norm": 1.4254546165466309,
+      "learning_rate": 4.918573972316982e-06,
+      "loss": 0.9997,
+      "step": 168
+    },
+    {
+      "epoch": 0.824390243902439,
+      "grad_norm": 1.3243224620819092,
+      "learning_rate": 4.917601299047361e-06,
+      "loss": 0.7944,
+      "step": 169
+    },
+    {
+      "epoch": 0.8292682926829268,
+      "grad_norm": 1.3879033327102661,
+      "learning_rate": 4.916622948023129e-06,
+      "loss": 0.7778,
+      "step": 170
+    },
+    {
+      "epoch": 0.8341463414634146,
+      "grad_norm": 1.245430588722229,
+      "learning_rate": 4.915638921541952e-06,
+      "loss": 0.6247,
+      "step": 171
+    },
+    {
+      "epoch": 0.8390243902439024,
+      "grad_norm": 1.3728258609771729,
+      "learning_rate": 4.914649221914822e-06,
+      "loss": 0.8762,
+      "step": 172
+    },
+    {
+      "epoch": 0.8439024390243902,
+      "grad_norm": 1.3080862760543823,
+      "learning_rate": 4.913653851466057e-06,
+      "loss": 0.6381,
+      "step": 173
+    },
+    {
+      "epoch": 0.848780487804878,
+      "grad_norm": 1.5109484195709229,
+      "learning_rate": 4.912652812533291e-06,
+      "loss": 0.8127,
+      "step": 174
+    },
+    {
+      "epoch": 0.8536585365853658,
+      "grad_norm": 1.237879753112793,
+      "learning_rate": 4.911646107467472e-06,
+      "loss": 0.8257,
+      "step": 175
+    },
+    {
+      "epoch": 0.8585365853658536,
+      "grad_norm": 1.2725176811218262,
+      "learning_rate": 4.9106337386328524e-06,
+      "loss": 0.9758,
+      "step": 176
+    },
+    {
+      "epoch": 0.8634146341463415,
+      "grad_norm": 1.271756887435913,
+      "learning_rate": 4.909615708406991e-06,
+      "loss": 0.8436,
+      "step": 177
+    },
+    {
+      "epoch": 0.8682926829268293,
+      "grad_norm": 1.0920095443725586,
+      "learning_rate": 4.908592019180738e-06,
+      "loss": 0.6657,
+      "step": 178
+    },
+    {
+      "epoch": 0.8731707317073171,
+      "grad_norm": 0.9080491065979004,
+      "learning_rate": 4.907562673358234e-06,
+      "loss": 0.6322,
+      "step": 179
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.9868524074554443,
+      "learning_rate": 4.906527673356907e-06,
+      "loss": 0.5918,
+      "step": 180
+    },
+    {
+      "epoch": 0.8829268292682927,
+      "grad_norm": 1.49118173122406,
+      "learning_rate": 4.905487021607462e-06,
+      "loss": 0.4939,
+      "step": 181
+    },
+    {
+      "epoch": 0.8878048780487805,
+      "grad_norm": 1.3323795795440674,
+      "learning_rate": 4.904440720553876e-06,
+      "loss": 0.8444,
+      "step": 182
+    },
+    {
+      "epoch": 0.8926829268292683,
+      "grad_norm": 1.340374231338501,
+      "learning_rate": 4.903388772653396e-06,
+      "loss": 0.765,
+      "step": 183
+    },
+    {
+      "epoch": 0.8975609756097561,
+      "grad_norm": 1.2728081941604614,
+      "learning_rate": 4.902331180376529e-06,
+      "loss": 0.8126,
+      "step": 184
+    },
+    {
+      "epoch": 0.9024390243902439,
+      "grad_norm": 1.154461145401001,
+      "learning_rate": 4.901267946207038e-06,
+      "loss": 0.9256,
+      "step": 185
+    },
+    {
+      "epoch": 0.9073170731707317,
+      "grad_norm": 1.0781828165054321,
+      "learning_rate": 4.900199072641937e-06,
+      "loss": 0.7057,
+      "step": 186
+    },
+    {
+      "epoch": 0.9121951219512195,
+      "grad_norm": 1.0474439859390259,
+      "learning_rate": 4.899124562191484e-06,
+      "loss": 0.6024,
+      "step": 187
+    },
+    {
+      "epoch": 0.9170731707317074,
+      "grad_norm": 1.019089937210083,
+      "learning_rate": 4.8980444173791735e-06,
+      "loss": 0.5001,
+      "step": 188
+    },
+    {
+      "epoch": 0.9219512195121952,
+      "grad_norm": 1.3556936979293823,
+      "learning_rate": 4.896958640741735e-06,
+      "loss": 0.8636,
+      "step": 189
+    },
+    {
+      "epoch": 0.926829268292683,
+      "grad_norm": 1.2974662780761719,
+      "learning_rate": 4.895867234829121e-06,
+      "loss": 0.9257,
+      "step": 190
+    },
+    {
+      "epoch": 0.9317073170731708,
+      "grad_norm": 1.3130805492401123,
+      "learning_rate": 4.894770202204509e-06,
+      "loss": 0.7026,
+      "step": 191
+    },
+    {
+      "epoch": 0.9365853658536586,
+      "grad_norm": 1.5521293878555298,
+      "learning_rate": 4.893667545444285e-06,
+      "loss": 0.8671,
+      "step": 192
+    },
+    {
+      "epoch": 0.9414634146341463,
+      "grad_norm": 1.0167640447616577,
+      "learning_rate": 4.8925592671380495e-06,
+      "loss": 0.6643,
+      "step": 193
+    },
+    {
+      "epoch": 0.9463414634146341,
+      "grad_norm": 0.8992295861244202,
+      "learning_rate": 4.891445369888601e-06,
+      "loss": 0.5294,
+      "step": 194
+    },
+    {
+      "epoch": 0.9512195121951219,
+      "grad_norm": 1.053918480873108,
+      "learning_rate": 4.890325856311936e-06,
+      "loss": 0.8734,
+      "step": 195
+    },
+    {
+      "epoch": 0.9560975609756097,
+      "grad_norm": 1.1650863885879517,
+      "learning_rate": 4.889200729037241e-06,
+      "loss": 0.7858,
+      "step": 196
+    },
+    {
+      "epoch": 0.9609756097560975,
+      "grad_norm": 1.0390702486038208,
+      "learning_rate": 4.888069990706884e-06,
+      "loss": 0.6428,
+      "step": 197
+    },
+    {
+      "epoch": 0.9658536585365853,
+      "grad_norm": 1.4749332666397095,
+      "learning_rate": 4.886933643976414e-06,
+      "loss": 0.55,
+      "step": 198
+    },
+    {
+      "epoch": 0.9707317073170731,
+      "grad_norm": 0.9483368992805481,
+      "learning_rate": 4.885791691514548e-06,
+      "loss": 0.4786,
+      "step": 199
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.0259203910827637,
+      "learning_rate": 4.884644136003172e-06,
+      "loss": 0.6137,
+      "step": 200
+    },
+    {
+      "epoch": 0.9804878048780488,
+      "grad_norm": 1.1431037187576294,
+      "learning_rate": 4.883490980137327e-06,
+      "loss": 1.2973,
+      "step": 201
+    },
+    {
+      "epoch": 0.9853658536585366,
+      "grad_norm": 1.1985281705856323,
+      "learning_rate": 4.882332226625208e-06,
+      "loss": 0.7734,
+      "step": 202
+    },
+    {
+      "epoch": 0.9902439024390244,
+      "grad_norm": 0.9396414160728455,
+      "learning_rate": 4.881167878188158e-06,
+      "loss": 0.8172,
+      "step": 203
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "grad_norm": 1.3293070793151855,
+      "learning_rate": 4.8799979375606565e-06,
+      "loss": 0.727,
+      "step": 204
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0133116245269775,
+      "learning_rate": 4.878822407490319e-06,
+      "loss": 0.7099,
+      "step": 205
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 208,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.049419025291674e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-2050/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 %}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/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 %}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "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": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.55.0"
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/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
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-410/trainer_state.json

@@ -0,0 +1,2904 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 410,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004878048780487805,
+      "grad_norm": 37.90617752075195,
+      "learning_rate": 5e-06,
+      "loss": 5.3731,
+      "step": 1
+    },
+    {
+      "epoch": 0.00975609756097561,
+      "grad_norm": 32.92101287841797,
+      "learning_rate": 4.999997064365715e-06,
+      "loss": 3.7922,
+      "step": 2
+    },
+    {
+      "epoch": 0.014634146341463415,
+      "grad_norm": 28.488866806030273,
+      "learning_rate": 4.999988257469751e-06,
+      "loss": 3.3238,
+      "step": 3
+    },
+    {
+      "epoch": 0.01951219512195122,
+      "grad_norm": 28.274654388427734,
+      "learning_rate": 4.999973579332793e-06,
+      "loss": 3.5405,
+      "step": 4
+    },
+    {
+      "epoch": 0.024390243902439025,
+      "grad_norm": 18.761985778808594,
+      "learning_rate": 4.999953029989312e-06,
+      "loss": 2.7492,
+      "step": 5
+    },
+    {
+      "epoch": 0.02926829268292683,
+      "grad_norm": 9.646541595458984,
+      "learning_rate": 4.999926609487568e-06,
+      "loss": 1.7146,
+      "step": 6
+    },
+    {
+      "epoch": 0.03414634146341464,
+      "grad_norm": 15.763612747192383,
+      "learning_rate": 4.9998943178896106e-06,
+      "loss": 2.8485,
+      "step": 7
+    },
+    {
+      "epoch": 0.03902439024390244,
+      "grad_norm": 13.853349685668945,
+      "learning_rate": 4.999856155271276e-06,
+      "loss": 3.0975,
+      "step": 8
+    },
+    {
+      "epoch": 0.04390243902439024,
+      "grad_norm": 16.893617630004883,
+      "learning_rate": 4.999812121722191e-06,
+      "loss": 2.8534,
+      "step": 9
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 15.47554874420166,
+      "learning_rate": 4.999762217345766e-06,
+      "loss": 3.4569,
+      "step": 10
+    },
+    {
+      "epoch": 0.05365853658536585,
+      "grad_norm": 6.277958393096924,
+      "learning_rate": 4.999706442259205e-06,
+      "loss": 1.8088,
+      "step": 11
+    },
+    {
+      "epoch": 0.05853658536585366,
+      "grad_norm": 5.451688289642334,
+      "learning_rate": 4.999644796593492e-06,
+      "loss": 1.8104,
+      "step": 12
+    },
+    {
+      "epoch": 0.06341463414634146,
+      "grad_norm": 4.333822727203369,
+      "learning_rate": 4.999577280493407e-06,
+      "loss": 1.7201,
+      "step": 13
+    },
+    {
+      "epoch": 0.06829268292682927,
+      "grad_norm": 4.488610744476318,
+      "learning_rate": 4.99950389411751e-06,
+      "loss": 1.9804,
+      "step": 14
+    },
+    {
+      "epoch": 0.07317073170731707,
+      "grad_norm": 1.8763024806976318,
+      "learning_rate": 4.999424637638148e-06,
+      "loss": 0.9227,
+      "step": 15
+    },
+    {
+      "epoch": 0.07804878048780488,
+      "grad_norm": 2.98995304107666,
+      "learning_rate": 4.999339511241458e-06,
+      "loss": 1.2368,
+      "step": 16
+    },
+    {
+      "epoch": 0.08292682926829269,
+      "grad_norm": 5.778397083282471,
+      "learning_rate": 4.9992485151273584e-06,
+      "loss": 2.5745,
+      "step": 17
+    },
+    {
+      "epoch": 0.08780487804878048,
+      "grad_norm": 5.222808361053467,
+      "learning_rate": 4.999151649509554e-06,
+      "loss": 2.0987,
+      "step": 18
+    },
+    {
+      "epoch": 0.09268292682926829,
+      "grad_norm": 4.075173377990723,
+      "learning_rate": 4.9990489146155356e-06,
+      "loss": 1.7732,
+      "step": 19
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 4.210625171661377,
+      "learning_rate": 4.9989403106865765e-06,
+      "loss": 1.8928,
+      "step": 20
+    },
+    {
+      "epoch": 0.1024390243902439,
+      "grad_norm": 1.7968504428863525,
+      "learning_rate": 4.9988258379777334e-06,
+      "loss": 1.0457,
+      "step": 21
+    },
+    {
+      "epoch": 0.1073170731707317,
+      "grad_norm": 2.494248151779175,
+      "learning_rate": 4.998705496757846e-06,
+      "loss": 1.3236,
+      "step": 22
+    },
+    {
+      "epoch": 0.11219512195121951,
+      "grad_norm": 4.312766075134277,
+      "learning_rate": 4.998579287309538e-06,
+      "loss": 2.4289,
+      "step": 23
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 5.361437797546387,
+      "learning_rate": 4.998447209929211e-06,
+      "loss": 1.7608,
+      "step": 24
+    },
+    {
+      "epoch": 0.12195121951219512,
+      "grad_norm": 1.4642046689987183,
+      "learning_rate": 4.998309264927053e-06,
+      "loss": 0.7571,
+      "step": 25
+    },
+    {
+      "epoch": 0.12682926829268293,
+      "grad_norm": 3.642005205154419,
+      "learning_rate": 4.998165452627025e-06,
+      "loss": 1.0634,
+      "step": 26
+    },
+    {
+      "epoch": 0.13170731707317074,
+      "grad_norm": 3.2727863788604736,
+      "learning_rate": 4.998015773366874e-06,
+      "loss": 1.4016,
+      "step": 27
+    },
+    {
+      "epoch": 0.13658536585365855,
+      "grad_norm": 1.5661338567733765,
+      "learning_rate": 4.997860227498122e-06,
+      "loss": 0.8305,
+      "step": 28
+    },
+    {
+      "epoch": 0.14146341463414633,
+      "grad_norm": 3.3989508152008057,
+      "learning_rate": 4.99769881538607e-06,
+      "loss": 1.8744,
+      "step": 29
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 3.512221574783325,
+      "learning_rate": 4.997531537409794e-06,
+      "loss": 1.7701,
+      "step": 30
+    },
+    {
+      "epoch": 0.15121951219512195,
+      "grad_norm": 2.261887311935425,
+      "learning_rate": 4.99735839396215e-06,
+      "loss": 1.0653,
+      "step": 31
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 2.2495696544647217,
+      "learning_rate": 4.9971793854497655e-06,
+      "loss": 1.1914,
+      "step": 32
+    },
+    {
+      "epoch": 0.16097560975609757,
+      "grad_norm": 4.262424468994141,
+      "learning_rate": 4.996994512293042e-06,
+      "loss": 1.7311,
+      "step": 33
+    },
+    {
+      "epoch": 0.16585365853658537,
+      "grad_norm": 3.361311674118042,
+      "learning_rate": 4.996803774926157e-06,
+      "loss": 1.4482,
+      "step": 34
+    },
+    {
+      "epoch": 0.17073170731707318,
+      "grad_norm": 1.5855786800384521,
+      "learning_rate": 4.996607173797059e-06,
+      "loss": 1.3959,
+      "step": 35
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 2.5001468658447266,
+      "learning_rate": 4.996404709367466e-06,
+      "loss": 1.3452,
+      "step": 36
+    },
+    {
+      "epoch": 0.18048780487804877,
+      "grad_norm": 2.7903096675872803,
+      "learning_rate": 4.996196382112868e-06,
+      "loss": 1.018,
+      "step": 37
+    },
+    {
+      "epoch": 0.18536585365853658,
+      "grad_norm": 2.7586171627044678,
+      "learning_rate": 4.9959821925225235e-06,
+      "loss": 1.291,
+      "step": 38
+    },
+    {
+      "epoch": 0.1902439024390244,
+      "grad_norm": 2.873840808868408,
+      "learning_rate": 4.995762141099456e-06,
+      "loss": 1.1418,
+      "step": 39
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 1.6896076202392578,
+      "learning_rate": 4.995536228360461e-06,
+      "loss": 1.1662,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4597285985946655,
+      "learning_rate": 4.995304454836095e-06,
+      "loss": 1.0373,
+      "step": 41
+    },
+    {
+      "epoch": 0.2048780487804878,
+      "grad_norm": 2.4222421646118164,
+      "learning_rate": 4.9950668210706795e-06,
+      "loss": 1.1895,
+      "step": 42
+    },
+    {
+      "epoch": 0.2097560975609756,
+      "grad_norm": 3.295085906982422,
+      "learning_rate": 4.994823327622299e-06,
+      "loss": 1.4166,
+      "step": 43
+    },
+    {
+      "epoch": 0.2146341463414634,
+      "grad_norm": 1.8216716051101685,
+      "learning_rate": 4.9945739750628e-06,
+      "loss": 1.0009,
+      "step": 44
+    },
+    {
+      "epoch": 0.21951219512195122,
+      "grad_norm": 2.2421364784240723,
+      "learning_rate": 4.994318763977789e-06,
+      "loss": 1.1999,
+      "step": 45
+    },
+    {
+      "epoch": 0.22439024390243903,
+      "grad_norm": 5.6812744140625,
+      "learning_rate": 4.994057694966632e-06,
+      "loss": 1.3831,
+      "step": 46
+    },
+    {
+      "epoch": 0.22926829268292684,
+      "grad_norm": 1.477816104888916,
+      "learning_rate": 4.993790768642449e-06,
+      "loss": 1.1419,
+      "step": 47
+    },
+    {
+      "epoch": 0.23414634146341465,
+      "grad_norm": 4.485177993774414,
+      "learning_rate": 4.99351798563212e-06,
+      "loss": 1.9434,
+      "step": 48
+    },
+    {
+      "epoch": 0.23902439024390243,
+      "grad_norm": 2.770219326019287,
+      "learning_rate": 4.993239346576278e-06,
+      "loss": 1.3214,
+      "step": 49
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 2.721611976623535,
+      "learning_rate": 4.99295485212931e-06,
+      "loss": 1.4329,
+      "step": 50
+    },
+    {
+      "epoch": 0.24878048780487805,
+      "grad_norm": 3.714306592941284,
+      "learning_rate": 4.992664502959351e-06,
+      "loss": 1.372,
+      "step": 51
+    },
+    {
+      "epoch": 0.25365853658536586,
+      "grad_norm": 1.2679803371429443,
+      "learning_rate": 4.99236829974829e-06,
+      "loss": 0.8086,
+      "step": 52
+    },
+    {
+      "epoch": 0.25853658536585367,
+      "grad_norm": 1.6986169815063477,
+      "learning_rate": 4.992066243191762e-06,
+      "loss": 1.2012,
+      "step": 53
+    },
+    {
+      "epoch": 0.2634146341463415,
+      "grad_norm": 1.3443604707717896,
+      "learning_rate": 4.991758333999148e-06,
+      "loss": 0.8986,
+      "step": 54
+    },
+    {
+      "epoch": 0.2682926829268293,
+      "grad_norm": 2.0896975994110107,
+      "learning_rate": 4.991444572893575e-06,
+      "loss": 0.8819,
+      "step": 55
+    },
+    {
+      "epoch": 0.2731707317073171,
+      "grad_norm": 1.255516529083252,
+      "learning_rate": 4.991124960611916e-06,
+      "loss": 0.6255,
+      "step": 56
+    },
+    {
+      "epoch": 0.2780487804878049,
+      "grad_norm": 2.125410318374634,
+      "learning_rate": 4.99079949790478e-06,
+      "loss": 0.9983,
+      "step": 57
+    },
+    {
+      "epoch": 0.28292682926829266,
+      "grad_norm": 2.0312907695770264,
+      "learning_rate": 4.99046818553652e-06,
+      "loss": 1.1137,
+      "step": 58
+    },
+    {
+      "epoch": 0.28780487804878047,
+      "grad_norm": 2.904625177383423,
+      "learning_rate": 4.9901310242852246e-06,
+      "loss": 1.2009,
+      "step": 59
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 2.512932777404785,
+      "learning_rate": 4.9897880149427206e-06,
+      "loss": 1.2234,
+      "step": 60
+    },
+    {
+      "epoch": 0.2975609756097561,
+      "grad_norm": 2.5621752738952637,
+      "learning_rate": 4.989439158314566e-06,
+      "loss": 1.2354,
+      "step": 61
+    },
+    {
+      "epoch": 0.3024390243902439,
+      "grad_norm": 1.0051912069320679,
+      "learning_rate": 4.989084455220056e-06,
+      "loss": 0.614,
+      "step": 62
+    },
+    {
+      "epoch": 0.3073170731707317,
+      "grad_norm": 1.5008565187454224,
+      "learning_rate": 4.988723906492212e-06,
+      "loss": 1.002,
+      "step": 63
+    },
+    {
+      "epoch": 0.3121951219512195,
+      "grad_norm": 1.1436376571655273,
+      "learning_rate": 4.988357512977785e-06,
+      "loss": 0.6483,
+      "step": 64
+    },
+    {
+      "epoch": 0.3170731707317073,
+      "grad_norm": 1.16792893409729,
+      "learning_rate": 4.987985275537252e-06,
+      "loss": 0.638,
+      "step": 65
+    },
+    {
+      "epoch": 0.32195121951219513,
+      "grad_norm": 1.5670536756515503,
+      "learning_rate": 4.9876071950448185e-06,
+      "loss": 1.0274,
+      "step": 66
+    },
+    {
+      "epoch": 0.32682926829268294,
+      "grad_norm": 1.357515811920166,
+      "learning_rate": 4.987223272388407e-06,
+      "loss": 0.7612,
+      "step": 67
+    },
+    {
+      "epoch": 0.33170731707317075,
+      "grad_norm": 1.8383222818374634,
+      "learning_rate": 4.986833508469663e-06,
+      "loss": 1.1496,
+      "step": 68
+    },
+    {
+      "epoch": 0.33658536585365856,
+      "grad_norm": 2.8976657390594482,
+      "learning_rate": 4.98643790420395e-06,
+      "loss": 0.9924,
+      "step": 69
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 1.7679390907287598,
+      "learning_rate": 4.986036460520348e-06,
+      "loss": 0.9408,
+      "step": 70
+    },
+    {
+      "epoch": 0.3463414634146341,
+      "grad_norm": 2.3815059661865234,
+      "learning_rate": 4.98562917836165e-06,
+      "loss": 1.2923,
+      "step": 71
+    },
+    {
+      "epoch": 0.35121951219512193,
+      "grad_norm": 1.679026484489441,
+      "learning_rate": 4.985216058684362e-06,
+      "loss": 0.8476,
+      "step": 72
+    },
+    {
+      "epoch": 0.35609756097560974,
+      "grad_norm": 1.7254586219787598,
+      "learning_rate": 4.984797102458697e-06,
+      "loss": 1.1775,
+      "step": 73
+    },
+    {
+      "epoch": 0.36097560975609755,
+      "grad_norm": 1.195844292640686,
+      "learning_rate": 4.984372310668579e-06,
+      "loss": 0.6664,
+      "step": 74
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 1.754431128501892,
+      "learning_rate": 4.983941684311633e-06,
+      "loss": 1.4361,
+      "step": 75
+    },
+    {
+      "epoch": 0.37073170731707317,
+      "grad_norm": 1.8255788087844849,
+      "learning_rate": 4.983505224399188e-06,
+      "loss": 0.8977,
+      "step": 76
+    },
+    {
+      "epoch": 0.375609756097561,
+      "grad_norm": 1.340451717376709,
+      "learning_rate": 4.983062931956275e-06,
+      "loss": 0.9432,
+      "step": 77
+    },
+    {
+      "epoch": 0.3804878048780488,
+      "grad_norm": 1.7810503244400024,
+      "learning_rate": 4.9826148080216195e-06,
+      "loss": 1.0463,
+      "step": 78
+    },
+    {
+      "epoch": 0.3853658536585366,
+      "grad_norm": 1.729826807975769,
+      "learning_rate": 4.9821608536476445e-06,
+      "loss": 1.4451,
+      "step": 79
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 2.6638681888580322,
+      "learning_rate": 4.981701069900465e-06,
+      "loss": 1.0409,
+      "step": 80
+    },
+    {
+      "epoch": 0.3951219512195122,
+      "grad_norm": 1.467076301574707,
+      "learning_rate": 4.9812354578598876e-06,
+      "loss": 0.8596,
+      "step": 81
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.453657627105713,
+      "learning_rate": 4.980764018619405e-06,
+      "loss": 0.9033,
+      "step": 82
+    },
+    {
+      "epoch": 0.40487804878048783,
+      "grad_norm": 1.9025623798370361,
+      "learning_rate": 4.980286753286196e-06,
+      "loss": 1.0586,
+      "step": 83
+    },
+    {
+      "epoch": 0.4097560975609756,
+      "grad_norm": 1.4698103666305542,
+      "learning_rate": 4.97980366298112e-06,
+      "loss": 0.8611,
+      "step": 84
+    },
+    {
+      "epoch": 0.4146341463414634,
+      "grad_norm": 1.6086381673812866,
+      "learning_rate": 4.97931474883872e-06,
+      "loss": 0.8884,
+      "step": 85
+    },
+    {
+      "epoch": 0.4195121951219512,
+      "grad_norm": 1.6679224967956543,
+      "learning_rate": 4.978820012007213e-06,
+      "loss": 0.969,
+      "step": 86
+    },
+    {
+      "epoch": 0.424390243902439,
+      "grad_norm": 1.5308334827423096,
+      "learning_rate": 4.978319453648495e-06,
+      "loss": 1.0345,
+      "step": 87
+    },
+    {
+      "epoch": 0.4292682926829268,
+      "grad_norm": 1.7788817882537842,
+      "learning_rate": 4.977813074938128e-06,
+      "loss": 0.9649,
+      "step": 88
+    },
+    {
+      "epoch": 0.43414634146341463,
+      "grad_norm": 1.591383934020996,
+      "learning_rate": 4.977300877065347e-06,
+      "loss": 0.9299,
+      "step": 89
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 1.525985836982727,
+      "learning_rate": 4.976782861233053e-06,
+      "loss": 0.7272,
+      "step": 90
+    },
+    {
+      "epoch": 0.44390243902439025,
+      "grad_norm": 2.7333128452301025,
+      "learning_rate": 4.976259028657812e-06,
+      "loss": 0.6694,
+      "step": 91
+    },
+    {
+      "epoch": 0.44878048780487806,
+      "grad_norm": 1.2718108892440796,
+      "learning_rate": 4.975729380569845e-06,
+      "loss": 0.8037,
+      "step": 92
+    },
+    {
+      "epoch": 0.45365853658536587,
+      "grad_norm": 1.157771110534668,
+      "learning_rate": 4.975193918213035e-06,
+      "loss": 0.52,
+      "step": 93
+    },
+    {
+      "epoch": 0.4585365853658537,
+      "grad_norm": 1.0602248907089233,
+      "learning_rate": 4.974652642844921e-06,
+      "loss": 0.7135,
+      "step": 94
+    },
+    {
+      "epoch": 0.4634146341463415,
+      "grad_norm": 2.418555974960327,
+      "learning_rate": 4.974105555736693e-06,
+      "loss": 1.0996,
+      "step": 95
+    },
+    {
+      "epoch": 0.4682926829268293,
+      "grad_norm": 1.1728110313415527,
+      "learning_rate": 4.973552658173186e-06,
+      "loss": 0.7268,
+      "step": 96
+    },
+    {
+      "epoch": 0.47317073170731705,
+      "grad_norm": 1.943113088607788,
+      "learning_rate": 4.972993951452887e-06,
+      "loss": 0.9091,
+      "step": 97
+    },
+    {
+      "epoch": 0.47804878048780486,
+      "grad_norm": 5.063096523284912,
+      "learning_rate": 4.9724294368879214e-06,
+      "loss": 0.8242,
+      "step": 98
+    },
+    {
+      "epoch": 0.48292682926829267,
+      "grad_norm": 1.5232555866241455,
+      "learning_rate": 4.971859115804055e-06,
+      "loss": 1.0543,
+      "step": 99
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 1.1453967094421387,
+      "learning_rate": 4.9712829895406935e-06,
+      "loss": 0.8209,
+      "step": 100
+    },
+    {
+      "epoch": 0.4926829268292683,
+      "grad_norm": 2.12345814704895,
+      "learning_rate": 4.970701059450872e-06,
+      "loss": 0.5849,
+      "step": 101
+    },
+    {
+      "epoch": 0.4975609756097561,
+      "grad_norm": 1.2201842069625854,
+      "learning_rate": 4.970113326901258e-06,
+      "loss": 0.9969,
+      "step": 102
+    },
+    {
+      "epoch": 0.5024390243902439,
+      "grad_norm": 1.3047524690628052,
+      "learning_rate": 4.9695197932721455e-06,
+      "loss": 0.9339,
+      "step": 103
+    },
+    {
+      "epoch": 0.5073170731707317,
+      "grad_norm": 1.6083660125732422,
+      "learning_rate": 4.968920459957453e-06,
+      "loss": 0.9702,
+      "step": 104
+    },
+    {
+      "epoch": 0.5121951219512195,
+      "grad_norm": 1.5247286558151245,
+      "learning_rate": 4.968315328364719e-06,
+      "loss": 1.0449,
+      "step": 105
+    },
+    {
+      "epoch": 0.5170731707317073,
+      "grad_norm": 1.354805588722229,
+      "learning_rate": 4.9677043999151e-06,
+      "loss": 1.1431,
+      "step": 106
+    },
+    {
+      "epoch": 0.5219512195121951,
+      "grad_norm": 1.088321328163147,
+      "learning_rate": 4.967087676043366e-06,
+      "loss": 0.519,
+      "step": 107
+    },
+    {
+      "epoch": 0.526829268292683,
+      "grad_norm": 1.5086662769317627,
+      "learning_rate": 4.966465158197897e-06,
+      "loss": 0.9357,
+      "step": 108
+    },
+    {
+      "epoch": 0.5317073170731708,
+      "grad_norm": 1.3161298036575317,
+      "learning_rate": 4.965836847840681e-06,
+      "loss": 0.7234,
+      "step": 109
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 1.4465640783309937,
+      "learning_rate": 4.96520274644731e-06,
+      "loss": 0.8911,
+      "step": 110
+    },
+    {
+      "epoch": 0.5414634146341464,
+      "grad_norm": 1.0576995611190796,
+      "learning_rate": 4.964562855506976e-06,
+      "loss": 0.7254,
+      "step": 111
+    },
+    {
+      "epoch": 0.5463414634146342,
+      "grad_norm": 1.1018916368484497,
+      "learning_rate": 4.963917176522466e-06,
+      "loss": 0.6603,
+      "step": 112
+    },
+    {
+      "epoch": 0.551219512195122,
+      "grad_norm": 2.150622606277466,
+      "learning_rate": 4.963265711010164e-06,
+      "loss": 1.0451,
+      "step": 113
+    },
+    {
+      "epoch": 0.5560975609756098,
+      "grad_norm": 1.7743186950683594,
+      "learning_rate": 4.9626084605000395e-06,
+      "loss": 0.8717,
+      "step": 114
+    },
+    {
+      "epoch": 0.5609756097560976,
+      "grad_norm": 1.205291509628296,
+      "learning_rate": 4.961945426535652e-06,
+      "loss": 0.5802,
+      "step": 115
+    },
+    {
+      "epoch": 0.5658536585365853,
+      "grad_norm": 1.3969353437423706,
+      "learning_rate": 4.961276610674141e-06,
+      "loss": 0.9158,
+      "step": 116
+    },
+    {
+      "epoch": 0.5707317073170731,
+      "grad_norm": 1.2318240404129028,
+      "learning_rate": 4.960602014486225e-06,
+      "loss": 1.0086,
+      "step": 117
+    },
+    {
+      "epoch": 0.5756097560975609,
+      "grad_norm": 1.2202470302581787,
+      "learning_rate": 4.959921639556199e-06,
+      "loss": 0.7888,
+      "step": 118
+    },
+    {
+      "epoch": 0.5804878048780487,
+      "grad_norm": 1.1564440727233887,
+      "learning_rate": 4.959235487481928e-06,
+      "loss": 1.0053,
+      "step": 119
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 1.2278865575790405,
+      "learning_rate": 4.958543559874846e-06,
+      "loss": 0.5486,
+      "step": 120
+    },
+    {
+      "epoch": 0.5902439024390244,
+      "grad_norm": 1.5465888977050781,
+      "learning_rate": 4.9578458583599495e-06,
+      "loss": 0.8232,
+      "step": 121
+    },
+    {
+      "epoch": 0.5951219512195122,
+      "grad_norm": 1.6284047365188599,
+      "learning_rate": 4.957142384575795e-06,
+      "loss": 0.7773,
+      "step": 122
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1794490814208984,
+      "learning_rate": 4.956433140174498e-06,
+      "loss": 0.8236,
+      "step": 123
+    },
+    {
+      "epoch": 0.6048780487804878,
+      "grad_norm": 1.2404091358184814,
+      "learning_rate": 4.9557181268217225e-06,
+      "loss": 0.8611,
+      "step": 124
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 1.2188373804092407,
+      "learning_rate": 4.954997346196683e-06,
+      "loss": 1.2922,
+      "step": 125
+    },
+    {
+      "epoch": 0.6146341463414634,
+      "grad_norm": 1.1514503955841064,
+      "learning_rate": 4.954270799992138e-06,
+      "loss": 0.7073,
+      "step": 126
+    },
+    {
+      "epoch": 0.6195121951219512,
+      "grad_norm": 1.285913109779358,
+      "learning_rate": 4.953538489914387e-06,
+      "loss": 0.729,
+      "step": 127
+    },
+    {
+      "epoch": 0.624390243902439,
+      "grad_norm": 1.8677104711532593,
+      "learning_rate": 4.9528004176832654e-06,
+      "loss": 0.6211,
+      "step": 128
+    },
+    {
+      "epoch": 0.6292682926829268,
+      "grad_norm": 1.2369698286056519,
+      "learning_rate": 4.952056585032142e-06,
+      "loss": 1.0311,
+      "step": 129
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 1.186990737915039,
+      "learning_rate": 4.951306993707913e-06,
+      "loss": 0.8207,
+      "step": 130
+    },
+    {
+      "epoch": 0.6390243902439025,
+      "grad_norm": 1.189424991607666,
+      "learning_rate": 4.950551645470998e-06,
+      "loss": 0.7853,
+      "step": 131
+    },
+    {
+      "epoch": 0.6439024390243903,
+      "grad_norm": 1.3477216958999634,
+      "learning_rate": 4.9497905420953406e-06,
+      "loss": 0.7271,
+      "step": 132
+    },
+    {
+      "epoch": 0.6487804878048781,
+      "grad_norm": 1.368592619895935,
+      "learning_rate": 4.949023685368395e-06,
+      "loss": 0.7394,
+      "step": 133
+    },
+    {
+      "epoch": 0.6536585365853659,
+      "grad_norm": 1.2769527435302734,
+      "learning_rate": 4.948251077091131e-06,
+      "loss": 1.0713,
+      "step": 134
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "grad_norm": 1.1477972269058228,
+      "learning_rate": 4.947472719078025e-06,
+      "loss": 0.841,
+      "step": 135
+    },
+    {
+      "epoch": 0.6634146341463415,
+      "grad_norm": 1.0983368158340454,
+      "learning_rate": 4.9466886131570565e-06,
+      "loss": 0.8665,
+      "step": 136
+    },
+    {
+      "epoch": 0.6682926829268293,
+      "grad_norm": 1.2526847124099731,
+      "learning_rate": 4.945898761169704e-06,
+      "loss": 1.0613,
+      "step": 137
+    },
+    {
+      "epoch": 0.6731707317073171,
+      "grad_norm": 1.1426396369934082,
+      "learning_rate": 4.945103164970941e-06,
+      "loss": 0.6248,
+      "step": 138
+    },
+    {
+      "epoch": 0.6780487804878049,
+      "grad_norm": 1.3275880813598633,
+      "learning_rate": 4.9443018264292304e-06,
+      "loss": 0.755,
+      "step": 139
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 1.4942073822021484,
+      "learning_rate": 4.9434947474265225e-06,
+      "loss": 0.9451,
+      "step": 140
+    },
+    {
+      "epoch": 0.6878048780487804,
+      "grad_norm": 1.1777600049972534,
+      "learning_rate": 4.942681929858249e-06,
+      "loss": 1.0505,
+      "step": 141
+    },
+    {
+      "epoch": 0.6926829268292682,
+      "grad_norm": 1.2474116086959839,
+      "learning_rate": 4.941863375633315e-06,
+      "loss": 0.9174,
+      "step": 142
+    },
+    {
+      "epoch": 0.697560975609756,
+      "grad_norm": 1.5067697763442993,
+      "learning_rate": 4.9410390866741056e-06,
+      "loss": 0.7737,
+      "step": 143
+    },
+    {
+      "epoch": 0.7024390243902439,
+      "grad_norm": 1.3016574382781982,
+      "learning_rate": 4.9402090649164655e-06,
+      "loss": 0.7588,
+      "step": 144
+    },
+    {
+      "epoch": 0.7073170731707317,
+      "grad_norm": 1.652600884437561,
+      "learning_rate": 4.9393733123097085e-06,
+      "loss": 1.0588,
+      "step": 145
+    },
+    {
+      "epoch": 0.7121951219512195,
+      "grad_norm": 1.267997145652771,
+      "learning_rate": 4.9385318308166065e-06,
+      "loss": 0.8996,
+      "step": 146
+    },
+    {
+      "epoch": 0.7170731707317073,
+      "grad_norm": 1.8560484647750854,
+      "learning_rate": 4.937684622413385e-06,
+      "loss": 0.6286,
+      "step": 147
+    },
+    {
+      "epoch": 0.7219512195121951,
+      "grad_norm": 1.4419782161712646,
+      "learning_rate": 4.9368316890897185e-06,
+      "loss": 0.9818,
+      "step": 148
+    },
+    {
+      "epoch": 0.7268292682926829,
+      "grad_norm": 1.134084701538086,
+      "learning_rate": 4.9359730328487264e-06,
+      "loss": 0.5246,
+      "step": 149
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 1.0102615356445312,
+      "learning_rate": 4.935108655706972e-06,
+      "loss": 0.7948,
+      "step": 150
+    },
+    {
+      "epoch": 0.7365853658536585,
+      "grad_norm": 1.3480703830718994,
+      "learning_rate": 4.934238559694448e-06,
+      "loss": 1.0951,
+      "step": 151
+    },
+    {
+      "epoch": 0.7414634146341463,
+      "grad_norm": 1.4133951663970947,
+      "learning_rate": 4.9333627468545845e-06,
+      "loss": 0.6936,
+      "step": 152
+    },
+    {
+      "epoch": 0.7463414634146341,
+      "grad_norm": 1.3072413206100464,
+      "learning_rate": 4.932481219244231e-06,
+      "loss": 0.799,
+      "step": 153
+    },
+    {
+      "epoch": 0.751219512195122,
+      "grad_norm": 1.3893049955368042,
+      "learning_rate": 4.931593978933666e-06,
+      "loss": 0.7375,
+      "step": 154
+    },
+    {
+      "epoch": 0.7560975609756098,
+      "grad_norm": 1.2313531637191772,
+      "learning_rate": 4.930701028006577e-06,
+      "loss": 0.9487,
+      "step": 155
+    },
+    {
+      "epoch": 0.7609756097560976,
+      "grad_norm": 1.3426295518875122,
+      "learning_rate": 4.929802368560066e-06,
+      "loss": 0.7542,
+      "step": 156
+    },
+    {
+      "epoch": 0.7658536585365854,
+      "grad_norm": 1.5280004739761353,
+      "learning_rate": 4.928898002704642e-06,
+      "loss": 0.8784,
+      "step": 157
+    },
+    {
+      "epoch": 0.7707317073170732,
+      "grad_norm": 1.3149527311325073,
+      "learning_rate": 4.927987932564215e-06,
+      "loss": 0.7247,
+      "step": 158
+    },
+    {
+      "epoch": 0.775609756097561,
+      "grad_norm": 1.073188304901123,
+      "learning_rate": 4.927072160276092e-06,
+      "loss": 0.7826,
+      "step": 159
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 1.426188588142395,
+      "learning_rate": 4.926150687990969e-06,
+      "loss": 0.6129,
+      "step": 160
+    },
+    {
+      "epoch": 0.7853658536585366,
+      "grad_norm": 1.2348767518997192,
+      "learning_rate": 4.925223517872934e-06,
+      "loss": 0.9191,
+      "step": 161
+    },
+    {
+      "epoch": 0.7902439024390244,
+      "grad_norm": 1.599665641784668,
+      "learning_rate": 4.9242906520994484e-06,
+      "loss": 1.0177,
+      "step": 162
+    },
+    {
+      "epoch": 0.7951219512195122,
+      "grad_norm": 1.1841332912445068,
+      "learning_rate": 4.923352092861358e-06,
+      "loss": 0.8342,
+      "step": 163
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0213048458099365,
+      "learning_rate": 4.922407842362875e-06,
+      "loss": 0.6292,
+      "step": 164
+    },
+    {
+      "epoch": 0.8048780487804879,
+      "grad_norm": 1.1878992319107056,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.9357,
+      "step": 165
+    },
+    {
+      "epoch": 0.8097560975609757,
+      "grad_norm": 1.297462821006775,
+      "learning_rate": 4.920502276468408e-06,
+      "loss": 0.8829,
+      "step": 166
+    },
+    {
+      "epoch": 0.8146341463414634,
+      "grad_norm": 1.1800835132598877,
+      "learning_rate": 4.9195409655476605e-06,
+      "loss": 0.712,
+      "step": 167
+    },
+    {
+      "epoch": 0.8195121951219512,
+      "grad_norm": 1.4254546165466309,
+      "learning_rate": 4.918573972316982e-06,
+      "loss": 0.9997,
+      "step": 168
+    },
+    {
+      "epoch": 0.824390243902439,
+      "grad_norm": 1.3243224620819092,
+      "learning_rate": 4.917601299047361e-06,
+      "loss": 0.7944,
+      "step": 169
+    },
+    {
+      "epoch": 0.8292682926829268,
+      "grad_norm": 1.3879033327102661,
+      "learning_rate": 4.916622948023129e-06,
+      "loss": 0.7778,
+      "step": 170
+    },
+    {
+      "epoch": 0.8341463414634146,
+      "grad_norm": 1.245430588722229,
+      "learning_rate": 4.915638921541952e-06,
+      "loss": 0.6247,
+      "step": 171
+    },
+    {
+      "epoch": 0.8390243902439024,
+      "grad_norm": 1.3728258609771729,
+      "learning_rate": 4.914649221914822e-06,
+      "loss": 0.8762,
+      "step": 172
+    },
+    {
+      "epoch": 0.8439024390243902,
+      "grad_norm": 1.3080862760543823,
+      "learning_rate": 4.913653851466057e-06,
+      "loss": 0.6381,
+      "step": 173
+    },
+    {
+      "epoch": 0.848780487804878,
+      "grad_norm": 1.5109484195709229,
+      "learning_rate": 4.912652812533291e-06,
+      "loss": 0.8127,
+      "step": 174
+    },
+    {
+      "epoch": 0.8536585365853658,
+      "grad_norm": 1.237879753112793,
+      "learning_rate": 4.911646107467472e-06,
+      "loss": 0.8257,
+      "step": 175
+    },
+    {
+      "epoch": 0.8585365853658536,
+      "grad_norm": 1.2725176811218262,
+      "learning_rate": 4.9106337386328524e-06,
+      "loss": 0.9758,
+      "step": 176
+    },
+    {
+      "epoch": 0.8634146341463415,
+      "grad_norm": 1.271756887435913,
+      "learning_rate": 4.909615708406991e-06,
+      "loss": 0.8436,
+      "step": 177
+    },
+    {
+      "epoch": 0.8682926829268293,
+      "grad_norm": 1.0920095443725586,
+      "learning_rate": 4.908592019180738e-06,
+      "loss": 0.6657,
+      "step": 178
+    },
+    {
+      "epoch": 0.8731707317073171,
+      "grad_norm": 0.9080491065979004,
+      "learning_rate": 4.907562673358234e-06,
+      "loss": 0.6322,
+      "step": 179
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.9868524074554443,
+      "learning_rate": 4.906527673356907e-06,
+      "loss": 0.5918,
+      "step": 180
+    },
+    {
+      "epoch": 0.8829268292682927,
+      "grad_norm": 1.49118173122406,
+      "learning_rate": 4.905487021607462e-06,
+      "loss": 0.4939,
+      "step": 181
+    },
+    {
+      "epoch": 0.8878048780487805,
+      "grad_norm": 1.3323795795440674,
+      "learning_rate": 4.904440720553876e-06,
+      "loss": 0.8444,
+      "step": 182
+    },
+    {
+      "epoch": 0.8926829268292683,
+      "grad_norm": 1.340374231338501,
+      "learning_rate": 4.903388772653396e-06,
+      "loss": 0.765,
+      "step": 183
+    },
+    {
+      "epoch": 0.8975609756097561,
+      "grad_norm": 1.2728081941604614,
+      "learning_rate": 4.902331180376529e-06,
+      "loss": 0.8126,
+      "step": 184
+    },
+    {
+      "epoch": 0.9024390243902439,
+      "grad_norm": 1.154461145401001,
+      "learning_rate": 4.901267946207038e-06,
+      "loss": 0.9256,
+      "step": 185
+    },
+    {
+      "epoch": 0.9073170731707317,
+      "grad_norm": 1.0781828165054321,
+      "learning_rate": 4.900199072641937e-06,
+      "loss": 0.7057,
+      "step": 186
+    },
+    {
+      "epoch": 0.9121951219512195,
+      "grad_norm": 1.0474439859390259,
+      "learning_rate": 4.899124562191484e-06,
+      "loss": 0.6024,
+      "step": 187
+    },
+    {
+      "epoch": 0.9170731707317074,
+      "grad_norm": 1.019089937210083,
+      "learning_rate": 4.8980444173791735e-06,
+      "loss": 0.5001,
+      "step": 188
+    },
+    {
+      "epoch": 0.9219512195121952,
+      "grad_norm": 1.3556936979293823,
+      "learning_rate": 4.896958640741735e-06,
+      "loss": 0.8636,
+      "step": 189
+    },
+    {
+      "epoch": 0.926829268292683,
+      "grad_norm": 1.2974662780761719,
+      "learning_rate": 4.895867234829121e-06,
+      "loss": 0.9257,
+      "step": 190
+    },
+    {
+      "epoch": 0.9317073170731708,
+      "grad_norm": 1.3130805492401123,
+      "learning_rate": 4.894770202204509e-06,
+      "loss": 0.7026,
+      "step": 191
+    },
+    {
+      "epoch": 0.9365853658536586,
+      "grad_norm": 1.5521293878555298,
+      "learning_rate": 4.893667545444285e-06,
+      "loss": 0.8671,
+      "step": 192
+    },
+    {
+      "epoch": 0.9414634146341463,
+      "grad_norm": 1.0167640447616577,
+      "learning_rate": 4.8925592671380495e-06,
+      "loss": 0.6643,
+      "step": 193
+    },
+    {
+      "epoch": 0.9463414634146341,
+      "grad_norm": 0.8992295861244202,
+      "learning_rate": 4.891445369888601e-06,
+      "loss": 0.5294,
+      "step": 194
+    },
+    {
+      "epoch": 0.9512195121951219,
+      "grad_norm": 1.053918480873108,
+      "learning_rate": 4.890325856311936e-06,
+      "loss": 0.8734,
+      "step": 195
+    },
+    {
+      "epoch": 0.9560975609756097,
+      "grad_norm": 1.1650863885879517,
+      "learning_rate": 4.889200729037241e-06,
+      "loss": 0.7858,
+      "step": 196
+    },
+    {
+      "epoch": 0.9609756097560975,
+      "grad_norm": 1.0390702486038208,
+      "learning_rate": 4.888069990706884e-06,
+      "loss": 0.6428,
+      "step": 197
+    },
+    {
+      "epoch": 0.9658536585365853,
+      "grad_norm": 1.4749332666397095,
+      "learning_rate": 4.886933643976414e-06,
+      "loss": 0.55,
+      "step": 198
+    },
+    {
+      "epoch": 0.9707317073170731,
+      "grad_norm": 0.9483368992805481,
+      "learning_rate": 4.885791691514548e-06,
+      "loss": 0.4786,
+      "step": 199
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.0259203910827637,
+      "learning_rate": 4.884644136003172e-06,
+      "loss": 0.6137,
+      "step": 200
+    },
+    {
+      "epoch": 0.9804878048780488,
+      "grad_norm": 1.1431037187576294,
+      "learning_rate": 4.883490980137327e-06,
+      "loss": 1.2973,
+      "step": 201
+    },
+    {
+      "epoch": 0.9853658536585366,
+      "grad_norm": 1.1985281705856323,
+      "learning_rate": 4.882332226625208e-06,
+      "loss": 0.7734,
+      "step": 202
+    },
+    {
+      "epoch": 0.9902439024390244,
+      "grad_norm": 0.9396414160728455,
+      "learning_rate": 4.881167878188158e-06,
+      "loss": 0.8172,
+      "step": 203
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "grad_norm": 1.3293070793151855,
+      "learning_rate": 4.8799979375606565e-06,
+      "loss": 0.727,
+      "step": 204
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0133116245269775,
+      "learning_rate": 4.878822407490319e-06,
+      "loss": 0.7099,
+      "step": 205
+    },
+    {
+      "epoch": 1.0048780487804878,
+      "grad_norm": 1.0823330879211426,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.6611,
+      "step": 206
+    },
+    {
+      "epoch": 1.0097560975609756,
+      "grad_norm": 0.9297066926956177,
+      "learning_rate": 4.876454590077216e-06,
+      "loss": 0.5825,
+      "step": 207
+    },
+    {
+      "epoch": 1.0146341463414634,
+      "grad_norm": 1.0025253295898438,
+      "learning_rate": 4.875262308295289e-06,
+      "loss": 0.8154,
+      "step": 208
+    },
+    {
+      "epoch": 1.0195121951219512,
+      "grad_norm": 1.1356369256973267,
+      "learning_rate": 4.874064448192185e-06,
+      "loss": 0.7126,
+      "step": 209
+    },
+    {
+      "epoch": 1.024390243902439,
+      "grad_norm": 1.4361388683319092,
+      "learning_rate": 4.872861012581088e-06,
+      "loss": 0.6323,
+      "step": 210
+    },
+    {
+      "epoch": 1.0292682926829269,
+      "grad_norm": 1.2314097881317139,
+      "learning_rate": 4.871652004288275e-06,
+      "loss": 0.6683,
+      "step": 211
+    },
+    {
+      "epoch": 1.0341463414634147,
+      "grad_norm": 1.1820945739746094,
+      "learning_rate": 4.870437426153113e-06,
+      "loss": 0.6659,
+      "step": 212
+    },
+    {
+      "epoch": 1.0390243902439025,
+      "grad_norm": 1.1955009698867798,
+      "learning_rate": 4.869217281028045e-06,
+      "loss": 0.8964,
+      "step": 213
+    },
+    {
+      "epoch": 1.0439024390243903,
+      "grad_norm": 1.2589020729064941,
+      "learning_rate": 4.867991571778592e-06,
+      "loss": 0.894,
+      "step": 214
+    },
+    {
+      "epoch": 1.048780487804878,
+      "grad_norm": 0.8933411836624146,
+      "learning_rate": 4.866760301283342e-06,
+      "loss": 0.5199,
+      "step": 215
+    },
+    {
+      "epoch": 1.053658536585366,
+      "grad_norm": 1.126219630241394,
+      "learning_rate": 4.865523472433942e-06,
+      "loss": 0.7014,
+      "step": 216
+    },
+    {
+      "epoch": 1.0585365853658537,
+      "grad_norm": 1.1173880100250244,
+      "learning_rate": 4.8642810881350935e-06,
+      "loss": 0.6085,
+      "step": 217
+    },
+    {
+      "epoch": 1.0634146341463415,
+      "grad_norm": 0.9508454203605652,
+      "learning_rate": 4.863033151304546e-06,
+      "loss": 0.6333,
+      "step": 218
+    },
+    {
+      "epoch": 1.0682926829268293,
+      "grad_norm": 1.8204004764556885,
+      "learning_rate": 4.861779664873088e-06,
+      "loss": 0.8899,
+      "step": 219
+    },
+    {
+      "epoch": 1.0731707317073171,
+      "grad_norm": 1.5721564292907715,
+      "learning_rate": 4.8605206317845425e-06,
+      "loss": 0.8105,
+      "step": 220
+    },
+    {
+      "epoch": 1.078048780487805,
+      "grad_norm": 1.3572758436203003,
+      "learning_rate": 4.859256054995758e-06,
+      "loss": 0.8634,
+      "step": 221
+    },
+    {
+      "epoch": 1.0829268292682928,
+      "grad_norm": 0.8531430959701538,
+      "learning_rate": 4.8579859374766e-06,
+      "loss": 0.4826,
+      "step": 222
+    },
+    {
+      "epoch": 1.0878048780487806,
+      "grad_norm": 0.771088719367981,
+      "learning_rate": 4.856710282209952e-06,
+      "loss": 0.4085,
+      "step": 223
+    },
+    {
+      "epoch": 1.0926829268292684,
+      "grad_norm": 1.0056614875793457,
+      "learning_rate": 4.855429092191698e-06,
+      "loss": 0.7168,
+      "step": 224
+    },
+    {
+      "epoch": 1.0975609756097562,
+      "grad_norm": 0.9825501441955566,
+      "learning_rate": 4.854142370430725e-06,
+      "loss": 0.6276,
+      "step": 225
+    },
+    {
+      "epoch": 1.102439024390244,
+      "grad_norm": 1.0209708213806152,
+      "learning_rate": 4.8528501199489045e-06,
+      "loss": 0.6521,
+      "step": 226
+    },
+    {
+      "epoch": 1.1073170731707318,
+      "grad_norm": 1.3162622451782227,
+      "learning_rate": 4.851552343781099e-06,
+      "loss": 0.8244,
+      "step": 227
+    },
+    {
+      "epoch": 1.1121951219512196,
+      "grad_norm": 1.150299072265625,
+      "learning_rate": 4.850249044975145e-06,
+      "loss": 0.7804,
+      "step": 228
+    },
+    {
+      "epoch": 1.1170731707317074,
+      "grad_norm": 1.142996907234192,
+      "learning_rate": 4.848940226591849e-06,
+      "loss": 0.9935,
+      "step": 229
+    },
+    {
+      "epoch": 1.1219512195121952,
+      "grad_norm": 0.9757675528526306,
+      "learning_rate": 4.847625891704982e-06,
+      "loss": 0.6041,
+      "step": 230
+    },
+    {
+      "epoch": 1.126829268292683,
+      "grad_norm": 1.1686437129974365,
+      "learning_rate": 4.846306043401268e-06,
+      "loss": 0.6873,
+      "step": 231
+    },
+    {
+      "epoch": 1.1317073170731708,
+      "grad_norm": 1.4826396703720093,
+      "learning_rate": 4.844980684780381e-06,
+      "loss": 0.6412,
+      "step": 232
+    },
+    {
+      "epoch": 1.1365853658536587,
+      "grad_norm": 1.204198956489563,
+      "learning_rate": 4.8436498189549345e-06,
+      "loss": 0.5779,
+      "step": 233
+    },
+    {
+      "epoch": 1.1414634146341462,
+      "grad_norm": 0.8927454948425293,
+      "learning_rate": 4.842313449050477e-06,
+      "loss": 0.5894,
+      "step": 234
+    },
+    {
+      "epoch": 1.146341463414634,
+      "grad_norm": 0.9504485726356506,
+      "learning_rate": 4.840971578205486e-06,
+      "loss": 0.5195,
+      "step": 235
+    },
+    {
+      "epoch": 1.1512195121951219,
+      "grad_norm": 0.8682957291603088,
+      "learning_rate": 4.839624209571352e-06,
+      "loss": 0.3927,
+      "step": 236
+    },
+    {
+      "epoch": 1.1560975609756097,
+      "grad_norm": 1.0243151187896729,
+      "learning_rate": 4.838271346312381e-06,
+      "loss": 0.8549,
+      "step": 237
+    },
+    {
+      "epoch": 1.1609756097560975,
+      "grad_norm": 0.9931624531745911,
+      "learning_rate": 4.836912991605782e-06,
+      "loss": 0.8616,
+      "step": 238
+    },
+    {
+      "epoch": 1.1658536585365853,
+      "grad_norm": 1.0424671173095703,
+      "learning_rate": 4.835549148641663e-06,
+      "loss": 0.5675,
+      "step": 239
+    },
+    {
+      "epoch": 1.170731707317073,
+      "grad_norm": 0.9706572890281677,
+      "learning_rate": 4.834179820623018e-06,
+      "loss": 0.6444,
+      "step": 240
+    },
+    {
+      "epoch": 1.175609756097561,
+      "grad_norm": 0.9557904601097107,
+      "learning_rate": 4.832805010765724e-06,
+      "loss": 0.6006,
+      "step": 241
+    },
+    {
+      "epoch": 1.1804878048780487,
+      "grad_norm": 1.2297061681747437,
+      "learning_rate": 4.831424722298531e-06,
+      "loss": 0.6897,
+      "step": 242
+    },
+    {
+      "epoch": 1.1853658536585365,
+      "grad_norm": 1.3953443765640259,
+      "learning_rate": 4.830038958463061e-06,
+      "loss": 0.772,
+      "step": 243
+    },
+    {
+      "epoch": 1.1902439024390243,
+      "grad_norm": 2.120232105255127,
+      "learning_rate": 4.828647722513785e-06,
+      "loss": 0.9361,
+      "step": 244
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 1.4457300901412964,
+      "learning_rate": 4.827251017718034e-06,
+      "loss": 0.8036,
+      "step": 245
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.0927690267562866,
+      "learning_rate": 4.8258488473559794e-06,
+      "loss": 0.8354,
+      "step": 246
+    },
+    {
+      "epoch": 1.2048780487804878,
+      "grad_norm": 1.4953900575637817,
+      "learning_rate": 4.824441214720629e-06,
+      "loss": 0.9083,
+      "step": 247
+    },
+    {
+      "epoch": 1.2097560975609756,
+      "grad_norm": 0.9229385852813721,
+      "learning_rate": 4.823028123117818e-06,
+      "loss": 0.441,
+      "step": 248
+    },
+    {
+      "epoch": 1.2146341463414634,
+      "grad_norm": 1.8001827001571655,
+      "learning_rate": 4.8216095758662015e-06,
+      "loss": 0.7975,
+      "step": 249
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 1.0904715061187744,
+      "learning_rate": 4.82018557629725e-06,
+      "loss": 0.8526,
+      "step": 250
+    },
+    {
+      "epoch": 1.224390243902439,
+      "grad_norm": 1.3482294082641602,
+      "learning_rate": 4.8187561277552376e-06,
+      "loss": 0.6198,
+      "step": 251
+    },
+    {
+      "epoch": 1.2292682926829268,
+      "grad_norm": 0.9257897138595581,
+      "learning_rate": 4.817321233597232e-06,
+      "loss": 0.8115,
+      "step": 252
+    },
+    {
+      "epoch": 1.2341463414634146,
+      "grad_norm": 1.1533488035202026,
+      "learning_rate": 4.815880897193095e-06,
+      "loss": 0.5524,
+      "step": 253
+    },
+    {
+      "epoch": 1.2390243902439024,
+      "grad_norm": 1.2778701782226562,
+      "learning_rate": 4.814435121925466e-06,
+      "loss": 0.802,
+      "step": 254
+    },
+    {
+      "epoch": 1.2439024390243902,
+      "grad_norm": 1.037063717842102,
+      "learning_rate": 4.812983911189761e-06,
+      "loss": 0.696,
+      "step": 255
+    },
+    {
+      "epoch": 1.248780487804878,
+      "grad_norm": 1.0112067461013794,
+      "learning_rate": 4.811527268394157e-06,
+      "loss": 0.5189,
+      "step": 256
+    },
+    {
+      "epoch": 1.2536585365853659,
+      "grad_norm": 1.1271675825119019,
+      "learning_rate": 4.810065196959591e-06,
+      "loss": 0.6292,
+      "step": 257
+    },
+    {
+      "epoch": 1.2585365853658537,
+      "grad_norm": 1.0987378358840942,
+      "learning_rate": 4.8085977003197496e-06,
+      "loss": 0.8452,
+      "step": 258
+    },
+    {
+      "epoch": 1.2634146341463415,
+      "grad_norm": 1.5386906862258911,
+      "learning_rate": 4.807124781921059e-06,
+      "loss": 1.1094,
+      "step": 259
+    },
+    {
+      "epoch": 1.2682926829268293,
+      "grad_norm": 0.9946249127388,
+      "learning_rate": 4.805646445222679e-06,
+      "loss": 0.6367,
+      "step": 260
+    },
+    {
+      "epoch": 1.273170731707317,
+      "grad_norm": 0.9774323105812073,
+      "learning_rate": 4.804162693696494e-06,
+      "loss": 0.6157,
+      "step": 261
+    },
+    {
+      "epoch": 1.278048780487805,
+      "grad_norm": 1.9447377920150757,
+      "learning_rate": 4.802673530827105e-06,
+      "loss": 0.6076,
+      "step": 262
+    },
+    {
+      "epoch": 1.2829268292682927,
+      "grad_norm": 0.7815698981285095,
+      "learning_rate": 4.801178960111823e-06,
+      "loss": 0.5985,
+      "step": 263
+    },
+    {
+      "epoch": 1.2878048780487805,
+      "grad_norm": 1.014426589012146,
+      "learning_rate": 4.799678985060658e-06,
+      "loss": 0.851,
+      "step": 264
+    },
+    {
+      "epoch": 1.2926829268292683,
+      "grad_norm": 0.9904977083206177,
+      "learning_rate": 4.798173609196314e-06,
+      "loss": 0.8511,
+      "step": 265
+    },
+    {
+      "epoch": 1.2975609756097561,
+      "grad_norm": 1.0354292392730713,
+      "learning_rate": 4.796662836054176e-06,
+      "loss": 0.4885,
+      "step": 266
+    },
+    {
+      "epoch": 1.302439024390244,
+      "grad_norm": 0.9485008120536804,
+      "learning_rate": 4.795146669182304e-06,
+      "loss": 0.6486,
+      "step": 267
+    },
+    {
+      "epoch": 1.3073170731707318,
+      "grad_norm": 0.9609008431434631,
+      "learning_rate": 4.793625112141431e-06,
+      "loss": 0.5446,
+      "step": 268
+    },
+    {
+      "epoch": 1.3121951219512196,
+      "grad_norm": 0.8880930542945862,
+      "learning_rate": 4.792098168504943e-06,
+      "loss": 0.5741,
+      "step": 269
+    },
+    {
+      "epoch": 1.3170731707317074,
+      "grad_norm": 0.8475173711776733,
+      "learning_rate": 4.790565841858879e-06,
+      "loss": 0.488,
+      "step": 270
+    },
+    {
+      "epoch": 1.3219512195121952,
+      "grad_norm": 1.04447603225708,
+      "learning_rate": 4.789028135801919e-06,
+      "loss": 0.7792,
+      "step": 271
+    },
+    {
+      "epoch": 1.326829268292683,
+      "grad_norm": 1.2021688222885132,
+      "learning_rate": 4.787485053945377e-06,
+      "loss": 0.8513,
+      "step": 272
+    },
+    {
+      "epoch": 1.3317073170731708,
+      "grad_norm": 0.9609706401824951,
+      "learning_rate": 4.785936599913193e-06,
+      "loss": 0.7186,
+      "step": 273
+    },
+    {
+      "epoch": 1.3365853658536586,
+      "grad_norm": 0.9922477602958679,
+      "learning_rate": 4.784382777341922e-06,
+      "loss": 0.7355,
+      "step": 274
+    },
+    {
+      "epoch": 1.3414634146341464,
+      "grad_norm": 1.2870302200317383,
+      "learning_rate": 4.782823589880729e-06,
+      "loss": 1.0985,
+      "step": 275
+    },
+    {
+      "epoch": 1.346341463414634,
+      "grad_norm": 0.9369707107543945,
+      "learning_rate": 4.7812590411913755e-06,
+      "loss": 0.7729,
+      "step": 276
+    },
+    {
+      "epoch": 1.3512195121951218,
+      "grad_norm": 1.1406941413879395,
+      "learning_rate": 4.779689134948217e-06,
+      "loss": 1.1142,
+      "step": 277
+    },
+    {
+      "epoch": 1.3560975609756096,
+      "grad_norm": 1.1078243255615234,
+      "learning_rate": 4.77811387483819e-06,
+      "loss": 0.5348,
+      "step": 278
+    },
+    {
+      "epoch": 1.3609756097560974,
+      "grad_norm": 1.1744791269302368,
+      "learning_rate": 4.776533264560804e-06,
+      "loss": 0.7202,
+      "step": 279
+    },
+    {
+      "epoch": 1.3658536585365852,
+      "grad_norm": 1.2643998861312866,
+      "learning_rate": 4.774947307828134e-06,
+      "loss": 0.9659,
+      "step": 280
+    },
+    {
+      "epoch": 1.370731707317073,
+      "grad_norm": 1.069071888923645,
+      "learning_rate": 4.773356008364812e-06,
+      "loss": 0.6257,
+      "step": 281
+    },
+    {
+      "epoch": 1.3756097560975609,
+      "grad_norm": 0.8661286234855652,
+      "learning_rate": 4.771759369908017e-06,
+      "loss": 0.4138,
+      "step": 282
+    },
+    {
+      "epoch": 1.3804878048780487,
+      "grad_norm": 0.9560813903808594,
+      "learning_rate": 4.7701573962074635e-06,
+      "loss": 0.6435,
+      "step": 283
+    },
+    {
+      "epoch": 1.3853658536585365,
+      "grad_norm": 1.0229038000106812,
+      "learning_rate": 4.7685500910254015e-06,
+      "loss": 0.5709,
+      "step": 284
+    },
+    {
+      "epoch": 1.3902439024390243,
+      "grad_norm": 1.7641900777816772,
+      "learning_rate": 4.766937458136598e-06,
+      "loss": 0.7815,
+      "step": 285
+    },
+    {
+      "epoch": 1.395121951219512,
+      "grad_norm": 1.011093258857727,
+      "learning_rate": 4.765319501328332e-06,
+      "loss": 0.7428,
+      "step": 286
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.0194127559661865,
+      "learning_rate": 4.763696224400391e-06,
+      "loss": 0.542,
+      "step": 287
+    },
+    {
+      "epoch": 1.4048780487804877,
+      "grad_norm": 0.9469794034957886,
+      "learning_rate": 4.762067631165049e-06,
+      "loss": 0.5758,
+      "step": 288
+    },
+    {
+      "epoch": 1.4097560975609755,
+      "grad_norm": 1.1177825927734375,
+      "learning_rate": 4.760433725447071e-06,
+      "loss": 0.8141,
+      "step": 289
+    },
+    {
+      "epoch": 1.4146341463414633,
+      "grad_norm": 1.388083577156067,
+      "learning_rate": 4.758794511083697e-06,
+      "loss": 0.8286,
+      "step": 290
+    },
+    {
+      "epoch": 1.4195121951219511,
+      "grad_norm": 1.1623952388763428,
+      "learning_rate": 4.757149991924633e-06,
+      "loss": 0.6733,
+      "step": 291
+    },
+    {
+      "epoch": 1.424390243902439,
+      "grad_norm": 1.328235149383545,
+      "learning_rate": 4.755500171832045e-06,
+      "loss": 0.5397,
+      "step": 292
+    },
+    {
+      "epoch": 1.4292682926829268,
+      "grad_norm": 1.0121268033981323,
+      "learning_rate": 4.753845054680548e-06,
+      "loss": 0.6813,
+      "step": 293
+    },
+    {
+      "epoch": 1.4341463414634146,
+      "grad_norm": 1.0799837112426758,
+      "learning_rate": 4.752184644357197e-06,
+      "loss": 0.5136,
+      "step": 294
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.010602593421936,
+      "learning_rate": 4.750518944761477e-06,
+      "loss": 0.5768,
+      "step": 295
+    },
+    {
+      "epoch": 1.4439024390243902,
+      "grad_norm": 1.1127134561538696,
+      "learning_rate": 4.748847959805297e-06,
+      "loss": 0.5663,
+      "step": 296
+    },
+    {
+      "epoch": 1.448780487804878,
+      "grad_norm": 0.9182597398757935,
+      "learning_rate": 4.7471716934129774e-06,
+      "loss": 0.5599,
+      "step": 297
+    },
+    {
+      "epoch": 1.4536585365853658,
+      "grad_norm": 1.0173683166503906,
+      "learning_rate": 4.745490149521242e-06,
+      "loss": 0.5155,
+      "step": 298
+    },
+    {
+      "epoch": 1.4585365853658536,
+      "grad_norm": 0.9683080911636353,
+      "learning_rate": 4.743803332079209e-06,
+      "loss": 0.5744,
+      "step": 299
+    },
+    {
+      "epoch": 1.4634146341463414,
+      "grad_norm": 0.9615181684494019,
+      "learning_rate": 4.742111245048382e-06,
+      "loss": 0.5961,
+      "step": 300
+    },
+    {
+      "epoch": 1.4682926829268292,
+      "grad_norm": 1.1113585233688354,
+      "learning_rate": 4.740413892402639e-06,
+      "loss": 0.5751,
+      "step": 301
+    },
+    {
+      "epoch": 1.473170731707317,
+      "grad_norm": 1.1533280611038208,
+      "learning_rate": 4.738711278128228e-06,
+      "loss": 0.6668,
+      "step": 302
+    },
+    {
+      "epoch": 1.4780487804878049,
+      "grad_norm": 1.086147665977478,
+      "learning_rate": 4.7370034062237476e-06,
+      "loss": 0.4249,
+      "step": 303
+    },
+    {
+      "epoch": 1.4829268292682927,
+      "grad_norm": 3.0501999855041504,
+      "learning_rate": 4.73529028070015e-06,
+      "loss": 0.6284,
+      "step": 304
+    },
+    {
+      "epoch": 1.4878048780487805,
+      "grad_norm": 1.2545751333236694,
+      "learning_rate": 4.733571905580723e-06,
+      "loss": 0.8968,
+      "step": 305
+    },
+    {
+      "epoch": 1.4926829268292683,
+      "grad_norm": 0.9740838408470154,
+      "learning_rate": 4.731848284901082e-06,
+      "loss": 0.7402,
+      "step": 306
+    },
+    {
+      "epoch": 1.497560975609756,
+      "grad_norm": 1.0430322885513306,
+      "learning_rate": 4.730119422709165e-06,
+      "loss": 0.4697,
+      "step": 307
+    },
+    {
+      "epoch": 1.502439024390244,
+      "grad_norm": 1.2707469463348389,
+      "learning_rate": 4.728385323065215e-06,
+      "loss": 0.7548,
+      "step": 308
+    },
+    {
+      "epoch": 1.5073170731707317,
+      "grad_norm": 0.9956101775169373,
+      "learning_rate": 4.7266459900417815e-06,
+      "loss": 0.5444,
+      "step": 309
+    },
+    {
+      "epoch": 1.5121951219512195,
+      "grad_norm": 1.0116164684295654,
+      "learning_rate": 4.724901427723698e-06,
+      "loss": 0.7939,
+      "step": 310
+    },
+    {
+      "epoch": 1.5170731707317073,
+      "grad_norm": 1.0668343305587769,
+      "learning_rate": 4.723151640208084e-06,
+      "loss": 0.3966,
+      "step": 311
+    },
+    {
+      "epoch": 1.5219512195121951,
+      "grad_norm": 0.9897716045379639,
+      "learning_rate": 4.721396631604327e-06,
+      "loss": 0.4675,
+      "step": 312
+    },
+    {
+      "epoch": 1.526829268292683,
+      "grad_norm": 0.9885281920433044,
+      "learning_rate": 4.7196364060340785e-06,
+      "loss": 0.5411,
+      "step": 313
+    },
+    {
+      "epoch": 1.5317073170731708,
+      "grad_norm": 1.1385118961334229,
+      "learning_rate": 4.7178709676312416e-06,
+      "loss": 0.8041,
+      "step": 314
+    },
+    {
+      "epoch": 1.5365853658536586,
+      "grad_norm": 1.2253623008728027,
+      "learning_rate": 4.716100320541961e-06,
+      "loss": 1.0583,
+      "step": 315
+    },
+    {
+      "epoch": 1.5414634146341464,
+      "grad_norm": 1.1313822269439697,
+      "learning_rate": 4.714324468924614e-06,
+      "loss": 0.7701,
+      "step": 316
+    },
+    {
+      "epoch": 1.5463414634146342,
+      "grad_norm": 1.120343804359436,
+      "learning_rate": 4.712543416949803e-06,
+      "loss": 0.7407,
+      "step": 317
+    },
+    {
+      "epoch": 1.551219512195122,
+      "grad_norm": 1.5084882974624634,
+      "learning_rate": 4.71075716880034e-06,
+      "loss": 0.753,
+      "step": 318
+    },
+    {
+      "epoch": 1.5560975609756098,
+      "grad_norm": 1.3213189840316772,
+      "learning_rate": 4.708965728671243e-06,
+      "loss": 0.8935,
+      "step": 319
+    },
+    {
+      "epoch": 1.5609756097560976,
+      "grad_norm": 1.170746922492981,
+      "learning_rate": 4.7071691007697214e-06,
+      "loss": 0.6782,
+      "step": 320
+    },
+    {
+      "epoch": 1.5658536585365854,
+      "grad_norm": 1.2023199796676636,
+      "learning_rate": 4.705367289315172e-06,
+      "loss": 0.8011,
+      "step": 321
+    },
+    {
+      "epoch": 1.5707317073170732,
+      "grad_norm": 1.0213698148727417,
+      "learning_rate": 4.703560298539158e-06,
+      "loss": 0.5011,
+      "step": 322
+    },
+    {
+      "epoch": 1.575609756097561,
+      "grad_norm": 1.045581579208374,
+      "learning_rate": 4.701748132685415e-06,
+      "loss": 0.5501,
+      "step": 323
+    },
+    {
+      "epoch": 1.5804878048780489,
+      "grad_norm": 0.9141654372215271,
+      "learning_rate": 4.699930796009825e-06,
+      "loss": 0.5551,
+      "step": 324
+    },
+    {
+      "epoch": 1.5853658536585367,
+      "grad_norm": 1.3005549907684326,
+      "learning_rate": 4.698108292780418e-06,
+      "loss": 0.7293,
+      "step": 325
+    },
+    {
+      "epoch": 1.5902439024390245,
+      "grad_norm": 0.985907793045044,
+      "learning_rate": 4.696280627277356e-06,
+      "loss": 0.5366,
+      "step": 326
+    },
+    {
+      "epoch": 1.5951219512195123,
+      "grad_norm": 0.9095384478569031,
+      "learning_rate": 4.6944478037929255e-06,
+      "loss": 0.5508,
+      "step": 327
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.346676230430603,
+      "learning_rate": 4.692609826631525e-06,
+      "loss": 0.6719,
+      "step": 328
+    },
+    {
+      "epoch": 1.604878048780488,
+      "grad_norm": 1.088921308517456,
+      "learning_rate": 4.690766700109659e-06,
+      "loss": 0.4088,
+      "step": 329
+    },
+    {
+      "epoch": 1.6097560975609757,
+      "grad_norm": 0.8905205726623535,
+      "learning_rate": 4.6889184285559234e-06,
+      "loss": 0.4671,
+      "step": 330
+    },
+    {
+      "epoch": 1.6146341463414635,
+      "grad_norm": 1.2066144943237305,
+      "learning_rate": 4.687065016310996e-06,
+      "loss": 0.7891,
+      "step": 331
+    },
+    {
+      "epoch": 1.6195121951219513,
+      "grad_norm": 1.0449296236038208,
+      "learning_rate": 4.685206467727631e-06,
+      "loss": 0.6103,
+      "step": 332
+    },
+    {
+      "epoch": 1.6243902439024391,
+      "grad_norm": 1.15915048122406,
+      "learning_rate": 4.683342787170644e-06,
+      "loss": 0.605,
+      "step": 333
+    },
+    {
+      "epoch": 1.629268292682927,
+      "grad_norm": 1.0918726921081543,
+      "learning_rate": 4.6814739790169006e-06,
+      "loss": 0.5444,
+      "step": 334
+    },
+    {
+      "epoch": 1.6341463414634148,
+      "grad_norm": 1.0298805236816406,
+      "learning_rate": 4.679600047655313e-06,
+      "loss": 0.7902,
+      "step": 335
+    },
+    {
+      "epoch": 1.6390243902439026,
+      "grad_norm": 1.3017504215240479,
+      "learning_rate": 4.6777209974868194e-06,
+      "loss": 1.1195,
+      "step": 336
+    },
+    {
+      "epoch": 1.6439024390243904,
+      "grad_norm": 1.45652174949646,
+      "learning_rate": 4.675836832924387e-06,
+      "loss": 0.6358,
+      "step": 337
+    },
+    {
+      "epoch": 1.6487804878048782,
+      "grad_norm": 0.8610002398490906,
+      "learning_rate": 4.673947558392989e-06,
+      "loss": 0.4196,
+      "step": 338
+    },
+    {
+      "epoch": 1.653658536585366,
+      "grad_norm": 0.8891443014144897,
+      "learning_rate": 4.6720531783296e-06,
+      "loss": 0.5593,
+      "step": 339
+    },
+    {
+      "epoch": 1.6585365853658538,
+      "grad_norm": 0.9679135680198669,
+      "learning_rate": 4.670153697183185e-06,
+      "loss": 0.6149,
+      "step": 340
+    },
+    {
+      "epoch": 1.6634146341463416,
+      "grad_norm": 1.019687294960022,
+      "learning_rate": 4.668249119414692e-06,
+      "loss": 0.5855,
+      "step": 341
+    },
+    {
+      "epoch": 1.6682926829268294,
+      "grad_norm": 0.9645085334777832,
+      "learning_rate": 4.666339449497033e-06,
+      "loss": 0.6321,
+      "step": 342
+    },
+    {
+      "epoch": 1.6731707317073172,
+      "grad_norm": 1.1760913133621216,
+      "learning_rate": 4.664424691915084e-06,
+      "loss": 0.5839,
+      "step": 343
+    },
+    {
+      "epoch": 1.678048780487805,
+      "grad_norm": 1.1706181764602661,
+      "learning_rate": 4.6625048511656675e-06,
+      "loss": 0.5806,
+      "step": 344
+    },
+    {
+      "epoch": 1.6829268292682928,
+      "grad_norm": 1.1575871706008911,
+      "learning_rate": 4.660579931757543e-06,
+      "loss": 0.4945,
+      "step": 345
+    },
+    {
+      "epoch": 1.6878048780487804,
+      "grad_norm": 0.9929284453392029,
+      "learning_rate": 4.6586499382113985e-06,
+      "loss": 0.5662,
+      "step": 346
+    },
+    {
+      "epoch": 1.6926829268292682,
+      "grad_norm": 0.9940921068191528,
+      "learning_rate": 4.6567148750598375e-06,
+      "loss": 0.8166,
+      "step": 347
+    },
+    {
+      "epoch": 1.697560975609756,
+      "grad_norm": 1.1893478631973267,
+      "learning_rate": 4.6547747468473705e-06,
+      "loss": 0.9291,
+      "step": 348
+    },
+    {
+      "epoch": 1.7024390243902439,
+      "grad_norm": 0.8776846528053284,
+      "learning_rate": 4.652829558130404e-06,
+      "loss": 0.4457,
+      "step": 349
+    },
+    {
+      "epoch": 1.7073170731707317,
+      "grad_norm": 1.2133142948150635,
+      "learning_rate": 4.6508793134772265e-06,
+      "loss": 0.6364,
+      "step": 350
+    },
+    {
+      "epoch": 1.7121951219512195,
+      "grad_norm": 0.8865175247192383,
+      "learning_rate": 4.648924017468003e-06,
+      "loss": 0.5514,
+      "step": 351
+    },
+    {
+      "epoch": 1.7170731707317073,
+      "grad_norm": 1.3637226819992065,
+      "learning_rate": 4.646963674694761e-06,
+      "loss": 0.8656,
+      "step": 352
+    },
+    {
+      "epoch": 1.721951219512195,
+      "grad_norm": 0.875629723072052,
+      "learning_rate": 4.64499828976138e-06,
+      "loss": 0.3992,
+      "step": 353
+    },
+    {
+      "epoch": 1.726829268292683,
+      "grad_norm": 1.0361976623535156,
+      "learning_rate": 4.64302786728358e-06,
+      "loss": 0.5056,
+      "step": 354
+    },
+    {
+      "epoch": 1.7317073170731707,
+      "grad_norm": 0.9224256873130798,
+      "learning_rate": 4.641052411888913e-06,
+      "loss": 0.5352,
+      "step": 355
+    },
+    {
+      "epoch": 1.7365853658536585,
+      "grad_norm": 1.2034342288970947,
+      "learning_rate": 4.6390719282167515e-06,
+      "loss": 0.4753,
+      "step": 356
+    },
+    {
+      "epoch": 1.7414634146341463,
+      "grad_norm": 1.056547999382019,
+      "learning_rate": 4.637086420918276e-06,
+      "loss": 0.7975,
+      "step": 357
+    },
+    {
+      "epoch": 1.7463414634146341,
+      "grad_norm": 0.9398707151412964,
+      "learning_rate": 4.635095894656465e-06,
+      "loss": 0.6944,
+      "step": 358
+    },
+    {
+      "epoch": 1.751219512195122,
+      "grad_norm": 1.3796380758285522,
+      "learning_rate": 4.633100354106085e-06,
+      "loss": 0.377,
+      "step": 359
+    },
+    {
+      "epoch": 1.7560975609756098,
+      "grad_norm": 1.1999366283416748,
+      "learning_rate": 4.631099803953677e-06,
+      "loss": 0.8488,
+      "step": 360
+    },
+    {
+      "epoch": 1.7609756097560976,
+      "grad_norm": 1.1613068580627441,
+      "learning_rate": 4.629094248897546e-06,
+      "loss": 0.4856,
+      "step": 361
+    },
+    {
+      "epoch": 1.7658536585365854,
+      "grad_norm": 1.407758116722107,
+      "learning_rate": 4.627083693647757e-06,
+      "loss": 0.5932,
+      "step": 362
+    },
+    {
+      "epoch": 1.7707317073170732,
+      "grad_norm": 1.1262705326080322,
+      "learning_rate": 4.625068142926111e-06,
+      "loss": 0.862,
+      "step": 363
+    },
+    {
+      "epoch": 1.775609756097561,
+      "grad_norm": 1.0207730531692505,
+      "learning_rate": 4.623047601466144e-06,
+      "loss": 0.7695,
+      "step": 364
+    },
+    {
+      "epoch": 1.7804878048780488,
+      "grad_norm": 1.0084431171417236,
+      "learning_rate": 4.621022074013114e-06,
+      "loss": 0.6608,
+      "step": 365
+    },
+    {
+      "epoch": 1.7853658536585366,
+      "grad_norm": 1.044545292854309,
+      "learning_rate": 4.618991565323987e-06,
+      "loss": 0.5231,
+      "step": 366
+    },
+    {
+      "epoch": 1.7902439024390244,
+      "grad_norm": 0.9962389469146729,
+      "learning_rate": 4.616956080167426e-06,
+      "loss": 0.5736,
+      "step": 367
+    },
+    {
+      "epoch": 1.7951219512195122,
+      "grad_norm": 1.3212288618087769,
+      "learning_rate": 4.614915623323786e-06,
+      "loss": 0.9586,
+      "step": 368
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.9554499983787537,
+      "learning_rate": 4.612870199585092e-06,
+      "loss": 0.4346,
+      "step": 369
+    },
+    {
+      "epoch": 1.8048780487804879,
+      "grad_norm": 1.082366943359375,
+      "learning_rate": 4.610819813755038e-06,
+      "loss": 0.505,
+      "step": 370
+    },
+    {
+      "epoch": 1.8097560975609757,
+      "grad_norm": 1.225993037223816,
+      "learning_rate": 4.608764470648971e-06,
+      "loss": 0.4801,
+      "step": 371
+    },
+    {
+      "epoch": 1.8146341463414632,
+      "grad_norm": 1.0881706476211548,
+      "learning_rate": 4.606704175093879e-06,
+      "loss": 0.4478,
+      "step": 372
+    },
+    {
+      "epoch": 1.819512195121951,
+      "grad_norm": 1.114046335220337,
+      "learning_rate": 4.604638931928383e-06,
+      "loss": 0.8015,
+      "step": 373
+    },
+    {
+      "epoch": 1.8243902439024389,
+      "grad_norm": 0.9838706851005554,
+      "learning_rate": 4.602568746002718e-06,
+      "loss": 0.5204,
+      "step": 374
+    },
+    {
+      "epoch": 1.8292682926829267,
+      "grad_norm": 1.038713812828064,
+      "learning_rate": 4.600493622178734e-06,
+      "loss": 0.8388,
+      "step": 375
+    },
+    {
+      "epoch": 1.8341463414634145,
+      "grad_norm": 1.0684245824813843,
+      "learning_rate": 4.598413565329876e-06,
+      "loss": 0.5744,
+      "step": 376
+    },
+    {
+      "epoch": 1.8390243902439023,
+      "grad_norm": 0.8907456994056702,
+      "learning_rate": 4.596328580341169e-06,
+      "loss": 0.5621,
+      "step": 377
+    },
+    {
+      "epoch": 1.84390243902439,
+      "grad_norm": 0.9921515583992004,
+      "learning_rate": 4.5942386721092195e-06,
+      "loss": 0.6967,
+      "step": 378
+    },
+    {
+      "epoch": 1.848780487804878,
+      "grad_norm": 1.1683647632598877,
+      "learning_rate": 4.592143845542189e-06,
+      "loss": 0.6489,
+      "step": 379
+    },
+    {
+      "epoch": 1.8536585365853657,
+      "grad_norm": 1.0409291982650757,
+      "learning_rate": 4.590044105559797e-06,
+      "loss": 0.8945,
+      "step": 380
+    },
+    {
+      "epoch": 1.8585365853658535,
+      "grad_norm": 1.0684564113616943,
+      "learning_rate": 4.587939457093296e-06,
+      "loss": 0.5476,
+      "step": 381
+    },
+    {
+      "epoch": 1.8634146341463413,
+      "grad_norm": 1.3661733865737915,
+      "learning_rate": 4.585829905085468e-06,
+      "loss": 0.6763,
+      "step": 382
+    },
+    {
+      "epoch": 1.8682926829268292,
+      "grad_norm": 1.1465227603912354,
+      "learning_rate": 4.5837154544906135e-06,
+      "loss": 0.7817,
+      "step": 383
+    },
+    {
+      "epoch": 1.873170731707317,
+      "grad_norm": 1.0232677459716797,
+      "learning_rate": 4.581596110274535e-06,
+      "loss": 0.7276,
+      "step": 384
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "grad_norm": 1.0359809398651123,
+      "learning_rate": 4.579471877414527e-06,
+      "loss": 0.9635,
+      "step": 385
+    },
+    {
+      "epoch": 1.8829268292682926,
+      "grad_norm": 1.2472409009933472,
+      "learning_rate": 4.577342760899368e-06,
+      "loss": 0.6782,
+      "step": 386
+    },
+    {
+      "epoch": 1.8878048780487804,
+      "grad_norm": 0.9241912961006165,
+      "learning_rate": 4.575208765729302e-06,
+      "loss": 0.5327,
+      "step": 387
+    },
+    {
+      "epoch": 1.8926829268292682,
+      "grad_norm": 1.3745805025100708,
+      "learning_rate": 4.573069896916035e-06,
+      "loss": 0.8436,
+      "step": 388
+    },
+    {
+      "epoch": 1.897560975609756,
+      "grad_norm": 1.0620322227478027,
+      "learning_rate": 4.5709261594827125e-06,
+      "loss": 0.659,
+      "step": 389
+    },
+    {
+      "epoch": 1.9024390243902438,
+      "grad_norm": 1.3068687915802002,
+      "learning_rate": 4.568777558463922e-06,
+      "loss": 0.5219,
+      "step": 390
+    },
+    {
+      "epoch": 1.9073170731707316,
+      "grad_norm": 1.0368698835372925,
+      "learning_rate": 4.566624098905665e-06,
+      "loss": 0.7099,
+      "step": 391
+    },
+    {
+      "epoch": 1.9121951219512194,
+      "grad_norm": 1.0876407623291016,
+      "learning_rate": 4.564465785865359e-06,
+      "loss": 0.5276,
+      "step": 392
+    },
+    {
+      "epoch": 1.9170731707317072,
+      "grad_norm": 0.9230280518531799,
+      "learning_rate": 4.56230262441182e-06,
+      "loss": 0.4292,
+      "step": 393
+    },
+    {
+      "epoch": 1.921951219512195,
+      "grad_norm": 0.9985240697860718,
+      "learning_rate": 4.560134619625247e-06,
+      "loss": 0.6602,
+      "step": 394
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 0.8872730135917664,
+      "learning_rate": 4.5579617765972155e-06,
+      "loss": 0.5711,
+      "step": 395
+    },
+    {
+      "epoch": 1.9317073170731707,
+      "grad_norm": 0.9474479556083679,
+      "learning_rate": 4.555784100430662e-06,
+      "loss": 0.5299,
+      "step": 396
+    },
+    {
+      "epoch": 1.9365853658536585,
+      "grad_norm": 1.0377358198165894,
+      "learning_rate": 4.553601596239877e-06,
+      "loss": 0.4649,
+      "step": 397
+    },
+    {
+      "epoch": 1.9414634146341463,
+      "grad_norm": 1.0765342712402344,
+      "learning_rate": 4.551414269150489e-06,
+      "loss": 0.5578,
+      "step": 398
+    },
+    {
+      "epoch": 1.946341463414634,
+      "grad_norm": 1.0844486951828003,
+      "learning_rate": 4.54922212429945e-06,
+      "loss": 0.5486,
+      "step": 399
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 1.1640657186508179,
+      "learning_rate": 4.547025166835027e-06,
+      "loss": 0.7462,
+      "step": 400
+    },
+    {
+      "epoch": 1.9560975609756097,
+      "grad_norm": 1.2733076810836792,
+      "learning_rate": 4.544823401916794e-06,
+      "loss": 0.881,
+      "step": 401
+    },
+    {
+      "epoch": 1.9609756097560975,
+      "grad_norm": 1.155869960784912,
+      "learning_rate": 4.542616834715612e-06,
+      "loss": 0.6374,
+      "step": 402
+    },
+    {
+      "epoch": 1.9658536585365853,
+      "grad_norm": 0.8623374700546265,
+      "learning_rate": 4.540405470413618e-06,
+      "loss": 0.4188,
+      "step": 403
+    },
+    {
+      "epoch": 1.9707317073170731,
+      "grad_norm": 1.0502699613571167,
+      "learning_rate": 4.53818931420422e-06,
+      "loss": 0.7233,
+      "step": 404
+    },
+    {
+      "epoch": 1.975609756097561,
+      "grad_norm": 0.8630202412605286,
+      "learning_rate": 4.535968371292076e-06,
+      "loss": 0.5896,
+      "step": 405
+    },
+    {
+      "epoch": 1.9804878048780488,
+      "grad_norm": 1.1017824411392212,
+      "learning_rate": 4.533742646893086e-06,
+      "loss": 0.6971,
+      "step": 406
+    },
+    {
+      "epoch": 1.9853658536585366,
+      "grad_norm": 0.9387734532356262,
+      "learning_rate": 4.531512146234383e-06,
+      "loss": 0.6718,
+      "step": 407
+    },
+    {
+      "epoch": 1.9902439024390244,
+      "grad_norm": 1.0347439050674438,
+      "learning_rate": 4.529276874554312e-06,
+      "loss": 0.8829,
+      "step": 408
+    },
+    {
+      "epoch": 1.9951219512195122,
+      "grad_norm": 1.0173542499542236,
+      "learning_rate": 4.527036837102426e-06,
+      "loss": 0.5154,
+      "step": 409
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1297523975372314,
+      "learning_rate": 4.524792039139471e-06,
+      "loss": 0.7721,
+      "step": 410
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 208,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2119917182163354e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/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
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/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 %}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "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": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.55.0"
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/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"
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/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
+  }
+}

qwen_2_5_7b_math_instruct/limo/checkpoint-820/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
+}