Upload checkpoint-144

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6154a44ee95f654e107f92fe4697447d699afef6ec1700ff0c06dda51b889f
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa14dcc607d79be112c3652ab42a0515b8e90785866d0be542d5ec38b014b2e7
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de714d543f62451ceecbccbd401c37e19e031d17239bbe3424cce21ae5b448f1
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519dabf6e0f90e5bfd1fcc3c51b6a3a8bfd075009f2fb531c20f1c786369cfe1
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7daaea7f51f7b0500ec0d8153230c504e2c358ea089a4439024a9ac7d7df95
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a8511b7568989b30528616d3ce6b7bc3c1dcd8af5491820df669dfab0c6d47
+size 4733130504

model.safetensors.index.json

@@ -0,0 +1,450 @@
+{
+  "metadata": {
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

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
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "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
+}

trainer_state.json

@@ -0,0 +1,1042 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013888888888888888,
+      "grad_norm": 32.20025306755104,
+      "learning_rate": 0.0,
+      "loss": 1.6489,
+      "step": 1
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "grad_norm": 31.757967894129138,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 1.5608,
+      "step": 2
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 27.005592965716428,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 1.4318,
+      "step": 3
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 25.876596085278493,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 1.3459,
+      "step": 4
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 20.05325433673777,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.1116,
+      "step": 5
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 17.2745705787659,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.0695,
+      "step": 6
+    },
+    {
+      "epoch": 0.09722222222222222,
+      "grad_norm": 11.547654869877704,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.052,
+      "step": 7
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 7.017914033099854,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 1.0261,
+      "step": 8
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 6.79190992209115,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.9326,
+      "step": 9
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 6.623522507160447,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 1.012,
+      "step": 10
+    },
+    {
+      "epoch": 0.1527777777777778,
+      "grad_norm": 3.7533541005048554,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.809,
+      "step": 11
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.843755827537282,
+      "learning_rate": 5e-06,
+      "loss": 0.8047,
+      "step": 12
+    },
+    {
+      "epoch": 0.18055555555555555,
+      "grad_norm": 4.34940165800091,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.7493,
+      "step": 13
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": 2.6403288766736477,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.4881,
+      "step": 14
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 2.1536362938927005,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.5604,
+      "step": 15
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 2.943068061086033,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.6005,
+      "step": 16
+    },
+    {
+      "epoch": 0.2361111111111111,
+      "grad_norm": 2.4040059583348214,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.4677,
+      "step": 17
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.373878455942415,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.5283,
+      "step": 18
+    },
+    {
+      "epoch": 0.2638888888888889,
+      "grad_norm": 2.5632160548134713,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.4489,
+      "step": 19
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 2.5874585166377924,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.6012,
+      "step": 20
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 2.347060535429832,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.4817,
+      "step": 21
+    },
+    {
+      "epoch": 0.3055555555555556,
+      "grad_norm": 3.103950712452586,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.5688,
+      "step": 22
+    },
+    {
+      "epoch": 0.3194444444444444,
+      "grad_norm": 2.7722433588291966,
+      "learning_rate": 1e-05,
+      "loss": 0.494,
+      "step": 23
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.118018603780166,
+      "learning_rate": 9.999344418328161e-06,
+      "loss": 0.3882,
+      "step": 24
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 2.227514369635361,
+      "learning_rate": 9.997377845227577e-06,
+      "loss": 0.451,
+      "step": 25
+    },
+    {
+      "epoch": 0.3611111111111111,
+      "grad_norm": 1.8352056819401141,
+      "learning_rate": 9.994100796397954e-06,
+      "loss": 0.4151,
+      "step": 26
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 2.0303315554358488,
+      "learning_rate": 9.98951413118856e-06,
+      "loss": 0.383,
+      "step": 27
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 1.9876736681198277,
+      "learning_rate": 9.983619052372847e-06,
+      "loss": 0.3647,
+      "step": 28
+    },
+    {
+      "epoch": 0.4027777777777778,
+      "grad_norm": 1.7843457351766752,
+      "learning_rate": 9.97641710583307e-06,
+      "loss": 0.3629,
+      "step": 29
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 1.4930651496160667,
+      "learning_rate": 9.96791018015489e-06,
+      "loss": 0.3443,
+      "step": 30
+    },
+    {
+      "epoch": 0.4305555555555556,
+      "grad_norm": 1.5759590184712353,
+      "learning_rate": 9.958100506132127e-06,
+      "loss": 0.324,
+      "step": 31
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.705745384345177,
+      "learning_rate": 9.946990656181782e-06,
+      "loss": 0.3095,
+      "step": 32
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 2.0524444353062403,
+      "learning_rate": 9.934583543669454e-06,
+      "loss": 0.4268,
+      "step": 33
+    },
+    {
+      "epoch": 0.4722222222222222,
+      "grad_norm": 1.6876043891458643,
+      "learning_rate": 9.920882422145372e-06,
+      "loss": 0.4535,
+      "step": 34
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 1.7064855964835324,
+      "learning_rate": 9.905890884491196e-06,
+      "loss": 0.3926,
+      "step": 35
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.823753890056008,
+      "learning_rate": 9.889612861977855e-06,
+      "loss": 0.4343,
+      "step": 36
+    },
+    {
+      "epoch": 0.5138888888888888,
+      "grad_norm": 1.8529840016274717,
+      "learning_rate": 9.872052623234632e-06,
+      "loss": 0.4281,
+      "step": 37
+    },
+    {
+      "epoch": 0.5277777777777778,
+      "grad_norm": 1.955408547526647,
+      "learning_rate": 9.853214773129796e-06,
+      "loss": 0.4148,
+      "step": 38
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 1.6681385782954192,
+      "learning_rate": 9.833104251563058e-06,
+      "loss": 0.3554,
+      "step": 39
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.7455115554623304,
+      "learning_rate": 9.811726332170153e-06,
+      "loss": 0.3806,
+      "step": 40
+    },
+    {
+      "epoch": 0.5694444444444444,
+      "grad_norm": 1.808587406097976,
+      "learning_rate": 9.789086620939936e-06,
+      "loss": 0.318,
+      "step": 41
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.0415709012615637,
+      "learning_rate": 9.765191054744305e-06,
+      "loss": 0.403,
+      "step": 42
+    },
+    {
+      "epoch": 0.5972222222222222,
+      "grad_norm": 1.5062509351045965,
+      "learning_rate": 9.740045899781353e-06,
+      "loss": 0.3219,
+      "step": 43
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 1.8233835485592458,
+      "learning_rate": 9.713657749932172e-06,
+      "loss": 0.3496,
+      "step": 44
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.55248703557286,
+      "learning_rate": 9.68603352503172e-06,
+      "loss": 0.3158,
+      "step": 45
+    },
+    {
+      "epoch": 0.6388888888888888,
+      "grad_norm": 1.2775572351579332,
+      "learning_rate": 9.657180469054213e-06,
+      "loss": 0.3026,
+      "step": 46
+    },
+    {
+      "epoch": 0.6527777777777778,
+      "grad_norm": 1.6282146735823924,
+      "learning_rate": 9.627106148213521e-06,
+      "loss": 0.2771,
+      "step": 47
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.9376858537829651,
+      "learning_rate": 9.595818448979061e-06,
+      "loss": 0.2237,
+      "step": 48
+    },
+    {
+      "epoch": 0.6805555555555556,
+      "grad_norm": 1.6898368689684822,
+      "learning_rate": 9.563325576007702e-06,
+      "loss": 0.3631,
+      "step": 49
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 1.614524493713582,
+      "learning_rate": 9.529636049992235e-06,
+      "loss": 0.2762,
+      "step": 50
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 1.4097198478742305,
+      "learning_rate": 9.494758705426978e-06,
+      "loss": 0.2929,
+      "step": 51
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 1.2338452097484094,
+      "learning_rate": 9.458702688291072e-06,
+      "loss": 0.2741,
+      "step": 52
+    },
+    {
+      "epoch": 0.7361111111111112,
+      "grad_norm": 1.5056629548281208,
+      "learning_rate": 9.421477453650118e-06,
+      "loss": 0.2946,
+      "step": 53
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.597626165346704,
+      "learning_rate": 9.38309276317674e-06,
+      "loss": 0.3472,
+      "step": 54
+    },
+    {
+      "epoch": 0.7638888888888888,
+      "grad_norm": 1.2539185771603638,
+      "learning_rate": 9.343558682590757e-06,
+      "loss": 0.3247,
+      "step": 55
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 1.5073835531227189,
+      "learning_rate": 9.302885579019626e-06,
+      "loss": 0.3089,
+      "step": 56
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 1.1716436585494405,
+      "learning_rate": 9.261084118279846e-06,
+      "loss": 0.2243,
+      "step": 57
+    },
+    {
+      "epoch": 0.8055555555555556,
+      "grad_norm": 1.615562349308342,
+      "learning_rate": 9.218165262080024e-06,
+      "loss": 0.3813,
+      "step": 58
+    },
+    {
+      "epoch": 0.8194444444444444,
+      "grad_norm": 1.126432528226203,
+      "learning_rate": 9.174140265146356e-06,
+      "loss": 0.2131,
+      "step": 59
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 4.944982415856606,
+      "learning_rate": 9.129020672271283e-06,
+      "loss": 0.3533,
+      "step": 60
+    },
+    {
+      "epoch": 0.8472222222222222,
+      "grad_norm": 1.8627430033355397,
+      "learning_rate": 9.082818315286054e-06,
+      "loss": 0.2986,
+      "step": 61
+    },
+    {
+      "epoch": 0.8611111111111112,
+      "grad_norm": 1.247452599538563,
+      "learning_rate": 9.035545309958048e-06,
+      "loss": 0.309,
+      "step": 62
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.4040277782456316,
+      "learning_rate": 8.987214052813605e-06,
+      "loss": 0.3614,
+      "step": 63
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.726105636424933,
+      "learning_rate": 8.937837217887273e-06,
+      "loss": 0.2789,
+      "step": 64
+    },
+    {
+      "epoch": 0.9027777777777778,
+      "grad_norm": 1.3818975343126196,
+      "learning_rate": 8.887427753398249e-06,
+      "loss": 0.295,
+      "step": 65
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 1.40890129019135,
+      "learning_rate": 8.83599887835493e-06,
+      "loss": 0.3319,
+      "step": 66
+    },
+    {
+      "epoch": 0.9305555555555556,
+      "grad_norm": 1.1840920751941846,
+      "learning_rate": 8.783564079088478e-06,
+      "loss": 0.2327,
+      "step": 67
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 1.6408315149496815,
+      "learning_rate": 8.730137105716231e-06,
+      "loss": 0.3666,
+      "step": 68
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 1.3727819885809827,
+      "learning_rate": 8.675731968536004e-06,
+      "loss": 0.2455,
+      "step": 69
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 1.2514474549155656,
+      "learning_rate": 8.620362934352109e-06,
+      "loss": 0.2722,
+      "step": 70
+    },
+    {
+      "epoch": 0.9861111111111112,
+      "grad_norm": 1.7164065718751929,
+      "learning_rate": 8.564044522734147e-06,
+      "loss": 0.382,
+      "step": 71
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.471855648534107,
+      "learning_rate": 8.506791502209497e-06,
+      "loss": 0.2948,
+      "step": 72
+    },
+    {
+      "epoch": 1.0138888888888888,
+      "grad_norm": 0.9301287212201296,
+      "learning_rate": 8.448618886390523e-06,
+      "loss": 0.1474,
+      "step": 73
+    },
+    {
+      "epoch": 1.0277777777777777,
+      "grad_norm": 1.3078419454322334,
+      "learning_rate": 8.389541930037516e-06,
+      "loss": 0.1895,
+      "step": 74
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 1.2172523796628973,
+      "learning_rate": 8.329576125058406e-06,
+      "loss": 0.2487,
+      "step": 75
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 1.1087278861942516,
+      "learning_rate": 8.268737196446264e-06,
+      "loss": 0.157,
+      "step": 76
+    },
+    {
+      "epoch": 1.0694444444444444,
+      "grad_norm": 1.1299518077880732,
+      "learning_rate": 8.207041098155701e-06,
+      "loss": 0.2375,
+      "step": 77
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 1.0822564340528005,
+      "learning_rate": 8.144504008919224e-06,
+      "loss": 0.1659,
+      "step": 78
+    },
+    {
+      "epoch": 1.0972222222222223,
+      "grad_norm": 1.3112345018169005,
+      "learning_rate": 8.081142328004638e-06,
+      "loss": 0.224,
+      "step": 79
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.2763077943589756,
+      "learning_rate": 8.016972670914624e-06,
+      "loss": 0.2167,
+      "step": 80
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 1.3430559699696374,
+      "learning_rate": 7.952011865029614e-06,
+      "loss": 0.2392,
+      "step": 81
+    },
+    {
+      "epoch": 1.1388888888888888,
+      "grad_norm": 1.2018334484401647,
+      "learning_rate": 7.886276945195098e-06,
+      "loss": 0.2069,
+      "step": 82
+    },
+    {
+      "epoch": 1.1527777777777777,
+      "grad_norm": 1.036290700090147,
+      "learning_rate": 7.819785149254534e-06,
+      "loss": 0.1471,
+      "step": 83
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 1.1280595707414307,
+      "learning_rate": 7.752553913529019e-06,
+      "loss": 0.2057,
+      "step": 84
+    },
+    {
+      "epoch": 1.1805555555555556,
+      "grad_norm": 1.214652271680462,
+      "learning_rate": 7.68460086824492e-06,
+      "loss": 0.1965,
+      "step": 85
+    },
+    {
+      "epoch": 1.1944444444444444,
+      "grad_norm": 1.2598327043593027,
+      "learning_rate": 7.61594383291065e-06,
+      "loss": 0.1703,
+      "step": 86
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 1.2134283432839454,
+      "learning_rate": 7.546600811643816e-06,
+      "loss": 0.196,
+      "step": 87
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.3533098727352946,
+      "learning_rate": 7.476589988449939e-06,
+      "loss": 0.2001,
+      "step": 88
+    },
+    {
+      "epoch": 1.2361111111111112,
+      "grad_norm": 1.4766618558288398,
+      "learning_rate": 7.405929722454026e-06,
+      "loss": 0.2699,
+      "step": 89
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.0266767933675947,
+      "learning_rate": 7.334638543086203e-06,
+      "loss": 0.1974,
+      "step": 90
+    },
+    {
+      "epoch": 1.2638888888888888,
+      "grad_norm": 1.1946430741459986,
+      "learning_rate": 7.262735145222696e-06,
+      "loss": 0.2071,
+      "step": 91
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 1.088741034243188,
+      "learning_rate": 7.190238384283413e-06,
+      "loss": 0.1784,
+      "step": 92
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 1.2058899949869668,
+      "learning_rate": 7.117167271287453e-06,
+      "loss": 0.1919,
+      "step": 93
+    },
+    {
+      "epoch": 1.3055555555555556,
+      "grad_norm": 1.2812552163649695,
+      "learning_rate": 7.043540967867782e-06,
+      "loss": 0.2557,
+      "step": 94
+    },
+    {
+      "epoch": 1.3194444444444444,
+      "grad_norm": 1.153293550437067,
+      "learning_rate": 6.969378781246436e-06,
+      "loss": 0.196,
+      "step": 95
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.2650327267209625,
+      "learning_rate": 6.894700159171535e-06,
+      "loss": 0.2084,
+      "step": 96
+    },
+    {
+      "epoch": 1.3472222222222223,
+      "grad_norm": 1.419643472824945,
+      "learning_rate": 6.819524684817439e-06,
+      "loss": 0.2273,
+      "step": 97
+    },
+    {
+      "epoch": 1.3611111111111112,
+      "grad_norm": 1.311304155370212,
+      "learning_rate": 6.743872071649411e-06,
+      "loss": 0.2371,
+      "step": 98
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 1.29047515065847,
+      "learning_rate": 6.667762158254104e-06,
+      "loss": 0.2121,
+      "step": 99
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 1.0545245202437472,
+      "learning_rate": 6.591214903137221e-06,
+      "loss": 0.1825,
+      "step": 100
+    },
+    {
+      "epoch": 1.4027777777777777,
+      "grad_norm": 1.148615805854231,
+      "learning_rate": 6.514250379489754e-06,
+      "loss": 0.1796,
+      "step": 101
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 1.1846417241397067,
+      "learning_rate": 6.436888769924142e-06,
+      "loss": 0.2014,
+      "step": 102
+    },
+    {
+      "epoch": 1.4305555555555556,
+      "grad_norm": 0.955857633717501,
+      "learning_rate": 6.3591503611817155e-06,
+      "loss": 0.1732,
+      "step": 103
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.984712498915309,
+      "learning_rate": 6.281055538812861e-06,
+      "loss": 0.2064,
+      "step": 104
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 1.2434367138483469,
+      "learning_rate": 6.202624781831269e-06,
+      "loss": 0.171,
+      "step": 105
+    },
+    {
+      "epoch": 1.4722222222222223,
+      "grad_norm": 1.398866584019501,
+      "learning_rate": 6.123878657343648e-06,
+      "loss": 0.2194,
+      "step": 106
+    },
+    {
+      "epoch": 1.4861111111111112,
+      "grad_norm": 0.9074792928724427,
+      "learning_rate": 6.044837815156377e-06,
+      "loss": 0.1361,
+      "step": 107
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.095019701696862,
+      "learning_rate": 5.965522982360441e-06,
+      "loss": 0.15,
+      "step": 108
+    },
+    {
+      "epoch": 1.5138888888888888,
+      "grad_norm": 0.9623783171866812,
+      "learning_rate": 5.885954957896115e-06,
+      "loss": 0.1418,
+      "step": 109
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 1.1829230695836053,
+      "learning_rate": 5.806154607098799e-06,
+      "loss": 0.192,
+      "step": 110
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 1.1362402732847106,
+      "learning_rate": 5.726142856227453e-06,
+      "loss": 0.1664,
+      "step": 111
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.2625152001636257,
+      "learning_rate": 5.645940686977033e-06,
+      "loss": 0.2085,
+      "step": 112
+    },
+    {
+      "epoch": 1.5694444444444444,
+      "grad_norm": 1.1510624195725618,
+      "learning_rate": 5.5655691309764225e-06,
+      "loss": 0.1538,
+      "step": 113
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 1.229794711647949,
+      "learning_rate": 5.485049264273241e-06,
+      "loss": 0.1561,
+      "step": 114
+    },
+    {
+      "epoch": 1.5972222222222223,
+      "grad_norm": 1.3857203830431617,
+      "learning_rate": 5.404402201807022e-06,
+      "loss": 0.181,
+      "step": 115
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 1.2727585502342074,
+      "learning_rate": 5.323649091872179e-06,
+      "loss": 0.179,
+      "step": 116
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 1.0778825699382022,
+      "learning_rate": 5.242811110572243e-06,
+      "loss": 0.2143,
+      "step": 117
+    },
+    {
+      "epoch": 1.6388888888888888,
+      "grad_norm": 1.195532097387673,
+      "learning_rate": 5.161909456266781e-06,
+      "loss": 0.1725,
+      "step": 118
+    },
+    {
+      "epoch": 1.6527777777777777,
+      "grad_norm": 1.3708575186061502,
+      "learning_rate": 5.080965344012509e-06,
+      "loss": 0.2151,
+      "step": 119
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.1094569783026915,
+      "learning_rate": 5e-06,
+      "loss": 0.1856,
+      "step": 120
+    },
+    {
+      "epoch": 1.6805555555555556,
+      "grad_norm": 0.9572962419430803,
+      "learning_rate": 4.919034655987493e-06,
+      "loss": 0.1237,
+      "step": 121
+    },
+    {
+      "epoch": 1.6944444444444444,
+      "grad_norm": 1.3697526165030556,
+      "learning_rate": 4.838090543733222e-06,
+      "loss": 0.1917,
+      "step": 122
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.9797668524681393,
+      "learning_rate": 4.757188889427761e-06,
+      "loss": 0.1403,
+      "step": 123
+    },
+    {
+      "epoch": 1.7222222222222223,
+      "grad_norm": 1.1177025083917884,
+      "learning_rate": 4.6763509081278215e-06,
+      "loss": 0.1607,
+      "step": 124
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 0.8736820887389185,
+      "learning_rate": 4.59559779819298e-06,
+      "loss": 0.1283,
+      "step": 125
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.2109157586571146,
+      "learning_rate": 4.51495073572676e-06,
+      "loss": 0.1741,
+      "step": 126
+    },
+    {
+      "epoch": 1.7638888888888888,
+      "grad_norm": 1.2535877794776555,
+      "learning_rate": 4.434430869023579e-06,
+      "loss": 0.1698,
+      "step": 127
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.1351713435610022,
+      "learning_rate": 4.3540593130229695e-06,
+      "loss": 0.2004,
+      "step": 128
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 1.2258838345245995,
+      "learning_rate": 4.27385714377255e-06,
+      "loss": 0.1492,
+      "step": 129
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.9541560169459083,
+      "learning_rate": 4.1938453929012014e-06,
+      "loss": 0.1332,
+      "step": 130
+    },
+    {
+      "epoch": 1.8194444444444444,
+      "grad_norm": 0.9127960838926955,
+      "learning_rate": 4.1140450421038865e-06,
+      "loss": 0.1248,
+      "step": 131
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 1.1807911880234168,
+      "learning_rate": 4.034477017639561e-06,
+      "loss": 0.2108,
+      "step": 132
+    },
+    {
+      "epoch": 1.8472222222222223,
+      "grad_norm": 1.2833323008527484,
+      "learning_rate": 3.955162184843625e-06,
+      "loss": 0.1841,
+      "step": 133
+    },
+    {
+      "epoch": 1.8611111111111112,
+      "grad_norm": 0.9828910910855105,
+      "learning_rate": 3.8761213426563546e-06,
+      "loss": 0.1318,
+      "step": 134
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.186035054075873,
+      "learning_rate": 3.7973752181687336e-06,
+      "loss": 0.163,
+      "step": 135
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 1.1779706537877848,
+      "learning_rate": 3.7189444611871383e-06,
+      "loss": 0.1882,
+      "step": 136
+    },
+    {
+      "epoch": 1.9027777777777777,
+      "grad_norm": 1.1354177782906174,
+      "learning_rate": 3.6408496388182857e-06,
+      "loss": 0.2008,
+      "step": 137
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 1.4059571469655092,
+      "learning_rate": 3.5631112300758595e-06,
+      "loss": 0.1944,
+      "step": 138
+    },
+    {
+      "epoch": 1.9305555555555556,
+      "grad_norm": 1.2175488933819723,
+      "learning_rate": 3.4857496205102475e-06,
+      "loss": 0.1748,
+      "step": 139
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 1.5683237293883645,
+      "learning_rate": 3.4087850968627823e-06,
+      "loss": 0.2047,
+      "step": 140
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 1.0174411846084366,
+      "learning_rate": 3.3322378417458985e-06,
+      "loss": 0.1486,
+      "step": 141
+    },
+    {
+      "epoch": 1.9722222222222223,
+      "grad_norm": 1.103126125153067,
+      "learning_rate": 3.2561279283505888e-06,
+      "loss": 0.1531,
+      "step": 142
+    },
+    {
+      "epoch": 1.9861111111111112,
+      "grad_norm": 1.215924865841863,
+      "learning_rate": 3.180475315182563e-06,
+      "loss": 0.1923,
+      "step": 143
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3959859902744824,
+      "learning_rate": 3.1052998408284664e-06,
+      "loss": 0.1844,
+      "step": 144
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 54955507712000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ecba63668c41588f97ffa676ca5964f840ef8f16ec783a7975019e49c6fe139
+size 7544