Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 version3_speech/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+makto_v1_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

makto_v1_2/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
+}

makto_v1_2/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- 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\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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 %}

makto_v1_2/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "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": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

makto_v1_2/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

makto_v1_2/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ad316240c93f7627c216a5cef0e69d54e63c1c40cb1f3b00b62039097ed263
+size 4877660672

makto_v1_2/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341276669b9801395cba3f9a60863de611c49d4b26cdcacac41624f5ab49ce44
+size 4932750888

makto_v1_2/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1235f302b6d30ae6d395ea01c261390777fc662cb256532b03726c7671906709
+size 4330865088

makto_v1_2/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1746b9c8977a7e2e172821b0fb5d349bb26cb6b814649e3bd9874bdf825d0d
+size 1089994880

makto_v1_2/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

makto_v1_2/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

makto_v1_2/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

makto_v1_2/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

makto_v1_2/trainer_state.json

@@ -0,0 +1,634 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5954045954045954,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03996003996003996,
+      "grad_norm": 145.49264526367188,
+      "kl": 0.0,
+      "learning_rate": 7.96812749003984e-09,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -168.0703125,
+      "logps/rejected": -251.4671875,
+      "loss": 0.5,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.07992007992007992,
+      "grad_norm": 195.10842895507812,
+      "kl": 0.02949218824505806,
+      "learning_rate": 2.589641434262948e-08,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -168.1484375,
+      "logps/rejected": -244.04375,
+      "loss": 0.4972,
+      "rewards/chosen": 0.010936927795410157,
+      "rewards/margins": 0.018865442276000975,
+      "rewards/rejected": -0.00792851448059082,
+      "step": 20
+    },
+    {
+      "epoch": 0.11988011988011989,
+      "grad_norm": 87.73217010498047,
+      "kl": 0.3169921934604645,
+      "learning_rate": 4.581673306772908e-08,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -164.6984375,
+      "logps/rejected": -254.0,
+      "loss": 0.4583,
+      "rewards/chosen": 0.16596946716308594,
+      "rewards/margins": 0.2544544219970703,
+      "rewards/rejected": -0.08848495483398437,
+      "step": 30
+    },
+    {
+      "epoch": 0.15984015984015984,
+      "grad_norm": 83.8915023803711,
+      "kl": 0.31914061307907104,
+      "learning_rate": 6.573705179282868e-08,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -161.20625,
+      "logps/rejected": -258.0171875,
+      "loss": 0.2981,
+      "rewards/chosen": 0.6698822021484375,
+      "rewards/margins": 1.5003173828125,
+      "rewards/rejected": -0.8304351806640625,
+      "step": 40
+    },
+    {
+      "epoch": 0.1998001998001998,
+      "grad_norm": 42.92097473144531,
+      "kl": 0.38310545682907104,
+      "learning_rate": 8.565737051792828e-08,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -146.9046875,
+      "logps/rejected": -274.6921875,
+      "loss": 0.1132,
+      "rewards/chosen": 1.64951171875,
+      "rewards/margins": 3.7609741210937497,
+      "rewards/rejected": -2.11146240234375,
+      "step": 50
+    },
+    {
+      "epoch": 0.23976023976023977,
+      "grad_norm": 2.370267868041992,
+      "kl": 0.12558594346046448,
+      "learning_rate": 1.0557768924302789e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -120.8265625,
+      "logps/rejected": -306.45625,
+      "loss": 0.0125,
+      "rewards/chosen": 3.5962890625,
+      "rewards/margins": 8.2150146484375,
+      "rewards/rejected": -4.6187255859375,
+      "step": 60
+    },
+    {
+      "epoch": 0.27972027972027974,
+      "grad_norm": 0.07267259061336517,
+      "kl": 0.19921875,
+      "learning_rate": 1.2549800796812748e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -100.9265625,
+      "logps/rejected": -332.590625,
+      "loss": 0.0021,
+      "rewards/chosen": 5.341015625,
+      "rewards/margins": 11.84072265625,
+      "rewards/rejected": -6.49970703125,
+      "step": 70
+    },
+    {
+      "epoch": 0.3196803196803197,
+      "grad_norm": 0.033463943749666214,
+      "kl": 0.0,
+      "learning_rate": 1.454183266932271e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -79.3359375,
+      "logps/rejected": -360.596875,
+      "loss": 0.0001,
+      "rewards/chosen": 6.237890625,
+      "rewards/margins": 15.56435546875,
+      "rewards/rejected": -9.32646484375,
+      "step": 80
+    },
+    {
+      "epoch": 0.3596403596403596,
+      "grad_norm": 0.0,
+      "kl": 0.009570312686264515,
+      "learning_rate": 1.6533864541832668e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -65.28203125,
+      "logps/rejected": -381.234375,
+      "loss": 0.0,
+      "rewards/chosen": 6.9796875,
+      "rewards/margins": 16.589453125,
+      "rewards/rejected": -9.609765625,
+      "step": 90
+    },
+    {
+      "epoch": 0.3996003996003996,
+      "grad_norm": 0.0,
+      "kl": 0.01738281175494194,
+      "learning_rate": 1.852589641434263e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -61.1265625,
+      "logps/rejected": -379.978125,
+      "loss": 0.0,
+      "rewards/chosen": 8.98544921875,
+      "rewards/margins": 18.9291015625,
+      "rewards/rejected": -9.94365234375,
+      "step": 100
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 2.051792828685259e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -60.972265625,
+      "logps/rejected": -390.265625,
+      "loss": 0.0,
+      "rewards/chosen": 8.40986328125,
+      "rewards/margins": 18.4115234375,
+      "rewards/rejected": -10.00166015625,
+      "step": 110
+    },
+    {
+      "epoch": 0.47952047952047955,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 2.2509960159362547e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -60.60703125,
+      "logps/rejected": -379.790625,
+      "loss": 0.0,
+      "rewards/chosen": 7.9267578125,
+      "rewards/margins": 18.69560546875,
+      "rewards/rejected": -10.76884765625,
+      "step": 120
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 2.450199203187251e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -61.63203125,
+      "logps/rejected": -393.49375,
+      "loss": 0.0,
+      "rewards/chosen": 7.6341796875,
+      "rewards/margins": 19.5283203125,
+      "rewards/rejected": -11.894140625,
+      "step": 130
+    },
+    {
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 2.649402390438247e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.3125,
+      "logps/rejected": -395.55625,
+      "loss": 0.0,
+      "rewards/chosen": 8.711328125,
+      "rewards/margins": 20.4107421875,
+      "rewards/rejected": -11.6994140625,
+      "step": 140
+    },
+    {
+      "epoch": 0.5994005994005994,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 2.848605577689243e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.9609375,
+      "logps/rejected": -399.084375,
+      "loss": 0.0,
+      "rewards/chosen": 7.990625,
+      "rewards/margins": 20.00322265625,
+      "rewards/rejected": -12.01259765625,
+      "step": 150
+    },
+    {
+      "epoch": 0.6393606393606394,
+      "grad_norm": 0.010647507384419441,
+      "kl": 0.0,
+      "learning_rate": 3.047808764940239e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -59.187890625,
+      "logps/rejected": -397.334375,
+      "loss": 0.0,
+      "rewards/chosen": 8.16240234375,
+      "rewards/margins": 19.8697265625,
+      "rewards/rejected": -11.70732421875,
+      "step": 160
+    },
+    {
+      "epoch": 0.6793206793206793,
+      "grad_norm": 0.013742036186158657,
+      "kl": 0.0,
+      "learning_rate": 3.247011952191235e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -60.387890625,
+      "logps/rejected": -399.60625,
+      "loss": 0.0,
+      "rewards/chosen": 9.07216796875,
+      "rewards/margins": 20.65322265625,
+      "rewards/rejected": -11.5810546875,
+      "step": 170
+    },
+    {
+      "epoch": 0.7192807192807192,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 3.446215139442231e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -57.88046875,
+      "logps/rejected": -392.115625,
+      "loss": 0.0,
+      "rewards/chosen": 7.6841796875,
+      "rewards/margins": 19.47451171875,
+      "rewards/rejected": -11.79033203125,
+      "step": 180
+    },
+    {
+      "epoch": 0.7592407592407593,
+      "grad_norm": 0.025016600266098976,
+      "kl": 0.0,
+      "learning_rate": 3.645418326693227e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -56.318359375,
+      "logps/rejected": -400.178125,
+      "loss": 0.0004,
+      "rewards/chosen": 8.82265625,
+      "rewards/margins": -361631.55234375,
+      "rewards/rejected": 361640.375,
+      "step": 190
+    },
+    {
+      "epoch": 0.7992007992007992,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 3.844621513944223e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -59.637890625,
+      "logps/rejected": -398.59375,
+      "loss": 0.0,
+      "rewards/chosen": 8.75927734375,
+      "rewards/margins": 19.46064453125,
+      "rewards/rejected": -10.7013671875,
+      "step": 200
+    },
+    {
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.008635389618575573,
+      "kl": 0.05009765550494194,
+      "learning_rate": 4.043824701195219e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -62.78046875,
+      "logps/rejected": -392.159375,
+      "loss": 0.0,
+      "rewards/chosen": 8.67294921875,
+      "rewards/margins": 2199305.2729492188,
+      "rewards/rejected": -2199296.6,
+      "step": 210
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.0,
+      "kl": 0.04121093824505806,
+      "learning_rate": 4.243027888446215e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -59.266015625,
+      "logps/rejected": -384.66875,
+      "loss": 0.0,
+      "rewards/chosen": 8.003125,
+      "rewards/margins": 17.73837890625,
+      "rewards/rejected": -9.73525390625,
+      "step": 220
+    },
+    {
+      "epoch": 0.919080919080919,
+      "grad_norm": 0.02473275735974312,
+      "kl": 0.2950195372104645,
+      "learning_rate": 4.4422310756972107e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.1234375,
+      "logps/rejected": -374.159375,
+      "loss": 0.0004,
+      "rewards/chosen": 8.7650390625,
+      "rewards/margins": 18.366406249999997,
+      "rewards/rejected": -9.6013671875,
+      "step": 230
+    },
+    {
+      "epoch": 0.9590409590409591,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.641434262948207e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -59.889453125,
+      "logps/rejected": -402.1625,
+      "loss": 0.0,
+      "rewards/chosen": 8.244921875,
+      "rewards/margins": 19.9560546875,
+      "rewards/rejected": -11.7111328125,
+      "step": 240
+    },
+    {
+      "epoch": 0.999000999000999,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.840637450199203e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -60.51875,
+      "logps/rejected": -413.496875,
+      "loss": 0.0,
+      "rewards/chosen": 8.7904296875,
+      "rewards/margins": 20.22265625,
+      "rewards/rejected": -11.4322265625,
+      "step": 250
+    },
+    {
+      "epoch": 1.035964035964036,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.999990329765451e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.745777027027025,
+      "logps/rejected": -416.89864864864865,
+      "loss": 0.0001,
+      "rewards/chosen": 8.26097972972973,
+      "rewards/margins": 22.23553631756757,
+      "rewards/rejected": -13.974556587837839,
+      "step": 260
+    },
+    {
+      "epoch": 1.075924075924076,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.999651879411306e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.033203125,
+      "logps/rejected": -418.81875,
+      "loss": 0.0,
+      "rewards/chosen": 8.83095703125,
+      "rewards/margins": 21.48671875,
+      "rewards/rejected": -12.65576171875,
+      "step": 270
+    },
+    {
+      "epoch": 1.115884115884116,
+      "grad_norm": 0.020607709884643555,
+      "kl": 0.0,
+      "learning_rate": 4.998829992137867e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -57.5859375,
+      "logps/rejected": -432.121875,
+      "loss": 0.0,
+      "rewards/chosen": 9.31337890625,
+      "rewards/margins": 21.8962890625,
+      "rewards/rejected": -12.58291015625,
+      "step": 280
+    },
+    {
+      "epoch": 1.155844155844156,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.99752482689953e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.70546875,
+      "logps/rejected": -425.453125,
+      "loss": 0.0,
+      "rewards/chosen": 8.5599609375,
+      "rewards/margins": 22.2689453125,
+      "rewards/rejected": -13.708984375,
+      "step": 290
+    },
+    {
+      "epoch": 1.1958041958041958,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.995736636117468e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -56.37109375,
+      "logps/rejected": -433.30625,
+      "loss": 0.0,
+      "rewards/chosen": 9.1435546875,
+      "rewards/margins": 24.2537109375,
+      "rewards/rejected": -15.11015625,
+      "step": 300
+    },
+    {
+      "epoch": 1.2357642357642358,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.993465765630816e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -57.859375,
+      "logps/rejected": -424.49375,
+      "loss": 0.0,
+      "rewards/chosen": 8.37666015625,
+      "rewards/margins": 22.023046875,
+      "rewards/rejected": -13.64638671875,
+      "step": 310
+    },
+    {
+      "epoch": 1.2757242757242757,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.990712654629782e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -57.90390625,
+      "logps/rejected": -428.36875,
+      "loss": 0.0,
+      "rewards/chosen": 8.5109375,
+      "rewards/margins": 22.4271484375,
+      "rewards/rejected": -13.9162109375,
+      "step": 320
+    },
+    {
+      "epoch": 1.3156843156843157,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.987477835570711e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -56.8984375,
+      "logps/rejected": -428.9875,
+      "loss": 0.0,
+      "rewards/chosen": 7.8798828125,
+      "rewards/margins": 23.0630859375,
+      "rewards/rejected": -15.183203125,
+      "step": 330
+    },
+    {
+      "epoch": 1.3556443556443556,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.983761934073105e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -57.48046875,
+      "logps/rejected": -434.05625,
+      "loss": 0.0,
+      "rewards/chosen": 7.5537109375,
+      "rewards/margins": 21.5748046875,
+      "rewards/rejected": -14.02109375,
+      "step": 340
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.979565668798623e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -57.063671875,
+      "logps/rejected": -432.25625,
+      "loss": 0.0,
+      "rewards/chosen": 9.34931640625,
+      "rewards/margins": 23.62587890625,
+      "rewards/rejected": -14.2765625,
+      "step": 350
+    },
+    {
+      "epoch": 1.4355644355644355,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.974889851312097e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -59.19375,
+      "logps/rejected": -436.19375,
+      "loss": 0.0,
+      "rewards/chosen": 8.802734375,
+      "rewards/margins": 21.5962890625,
+      "rewards/rejected": -12.7935546875,
+      "step": 360
+    },
+    {
+      "epoch": 1.4755244755244754,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.969735385924573e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -58.88984375,
+      "logps/rejected": -424.05,
+      "loss": 0.0,
+      "rewards/chosen": 7.75869140625,
+      "rewards/margins": 22.02890625,
+      "rewards/rejected": -14.27021484375,
+      "step": 370
+    },
+    {
+      "epoch": 1.5154845154845153,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.96410326951841e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -60.644921875,
+      "logps/rejected": -430.296875,
+      "loss": 0.0,
+      "rewards/chosen": 8.31806640625,
+      "rewards/margins": 23.38759765625,
+      "rewards/rejected": -15.06953125,
+      "step": 380
+    },
+    {
+      "epoch": 1.5554445554445553,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.957994591354489e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -55.873828125,
+      "logps/rejected": -426.70625,
+      "loss": 0.0,
+      "rewards/chosen": 8.44287109375,
+      "rewards/margins": 22.2982421875,
+      "rewards/rejected": -13.85537109375,
+      "step": 390
+    },
+    {
+      "epoch": 1.5954045954045954,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 4.951410532861542e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -56.198828125,
+      "logps/rejected": -424.959375,
+      "loss": 0.0,
+      "rewards/chosen": 8.041796875,
+      "rewards/margins": 22.8931640625,
+      "rewards/rejected": -14.8513671875,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

makto_v1_2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6068cf7ddb147f187f3fa1e9ccc20eefd325cca8d8b6a0d594398e4adfb79b
+size 7441