Upload folder using huggingface_hub

.gitattributes

@@ -41,3 +41,4 @@ great-again/1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 great-again-m/1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 so_fun_time/434/loss_plot.png filter=lfs diff=lfs merge=lfs -text
 so_fun_time/434/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+so_fun_time/651/tokenizer.json filter=lfs diff=lfs merge=lfs -text

so_fun_time/651/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
+}

so_fun_time/651/chat_template.jinja

@@ -0,0 +1,93 @@
+{%- 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) %}
+{#- Determine the real last index: use provided value or default to messages length - 1 #}
+{%- if real_last_index is defined and real_last_index is not none %}
+    {%- set ns.real_last_index = real_last_index %}
+{%- else %}
+    {%- set ns.real_last_index = messages|length - 1 %}
+{%- endif %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.index0 == ns.real_last_index or (loop.index0 != ns.real_last_index 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' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n\n' }}
+    {%- endif %}
+{%- endif %}

so_fun_time/651/config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "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",
+    "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

so_fun_time/651/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151645
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.1",
+  "use_cache": false
+}

so_fun_time/651/model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddde535aab716ac6da0c246ff5243f1e650db35957fd3b33b9447a7abd23ea01
+size 4932307584

so_fun_time/651/model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8dc0649639905ae413a1f436451c5e6126c38e200d265567571e16ee2eead5
+size 4875989696

so_fun_time/651/model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11cac5dd77decdc9d78196b278a7decc523f82669c4af7e28fc6007c26b4656
+size 4875989720

so_fun_time/651/model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153d2f0e4eca3e02364d9dc1b9ab2b52767cfd3c3bfacfadbe9602752b64e625
+size 4875989752

so_fun_time/651/model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e15b9c115d1376964348d7968edf25bc8069fd6a781b60686ac1221309834f
+size 4875989752

so_fun_time/651/model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2099eab2261b885e0bdf6a75e8e028d97b6edf91c7cdefcac1b370d1671052e4
+size 4875989752

so_fun_time/651/model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9d38b761dd4ed17663402f0dcbea882126f7df665c857843013193931b5307
+size 4875989752

so_fun_time/651/model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c25cafb679a9902cf2746626f32da9f412a24f9ba0f83745f0303b5fbed61f1
+size 4875989752

so_fun_time/651/model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6cca4f616a016cd106e8545f2b9d871c3dc9444d2c56bc219b5ea87d1b9f17
+size 4875989752

so_fun_time/651/model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c52af2da2a868ad2810c3cdba572bfdf051db0c00bad2af3e10842f2ef166e6
+size 4875989752

so_fun_time/651/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a33bbf9a7e5c7c3e94a84095ec207295f2c8846c63d35145e0ac9f4b8d439d
+size 4875989752

so_fun_time/651/model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd5292c749fe9726d91514bcdf16269eeea9f89f2b5cfa9d0b38a52dcc61668
+size 4875989752

so_fun_time/651/model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647829947945c8b4081b10db08f84bdc2c40beed697bc83c9740c6aeaf437e0c
+size 4875989752

so_fun_time/651/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f923234313b2f901953675073c6e59dc4974dc5331a2ae4abc831bc4be9a38c
+size 2080144040

so_fun_time/651/model.safetensors.index.json

@@ -0,0 +1,715 @@
+{
+  "metadata": {
+    "total_parameters": 32762123264,
+    "total_size": 65524246528
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

so_fun_time/651/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e5228ca610bcac71f8c16d94943855b2972314410c1d13a39c200c90a0689c
+size 131049128700

so_fun_time/651/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce557af8b1051f57b9782a1b4b436e64dfdb1f1f009afe1192badb08b0855021
+size 65524487072

so_fun_time/651/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe6b873f1da64bb980afe982fc1c6b6bc461ad8c33073d856804323f64b26d9
+size 15429

so_fun_time/651/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13db4dd10b22b5464f5ef0b539152b46390eae6a827b355108cb54b1af2eb830
+size 15429

so_fun_time/651/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e293f13fb6e873e8081636b6b07115410b397c55f1ed08b8772b059c8eb74e
+size 15429

so_fun_time/651/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c595c077664f94b7f91088561951be20e39483e01865774a83bc46f3971a3152
+size 15429

so_fun_time/651/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d33e049e2c4db72faa5388c8ca1a7a4273cb4350965bb7279da047ead4b0197
+size 1465

so_fun_time/651/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
+  }
+}

so_fun_time/651/tokenizer.json

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

so_fun_time/651/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

so_fun_time/651/trainer_state.json

@@ -0,0 +1,1594 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0030849320350912,
+  "eval_steps": 500,
+  "global_step": 651,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007712330087727755,
+      "grad_norm": 0.84765625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 1.164,
+      "memory/device_reserved (GiB)": 246.45,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 5,
+      "tokens_per_second_per_gpu": 500.9,
+      "total_tokens": 1287402
+    },
+    {
+      "epoch": 0.01542466017545551,
+      "grad_norm": 0.9765625,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 1.1463,
+      "memory/device_reserved (GiB)": 246.57,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 10,
+      "tokens_per_second_per_gpu": 458.45,
+      "total_tokens": 2568739
+    },
+    {
+      "epoch": 0.023136990263183263,
+      "grad_norm": 0.91015625,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 1.1346,
+      "memory/device_reserved (GiB)": 246.57,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 15,
+      "tokens_per_second_per_gpu": 487.44,
+      "total_tokens": 3789106
+    },
+    {
+      "epoch": 0.03084932035091102,
+      "grad_norm": 0.90625,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.1363,
+      "memory/device_reserved (GiB)": 246.57,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 20,
+      "tokens_per_second_per_gpu": 514.12,
+      "total_tokens": 5093129
+    },
+    {
+      "epoch": 0.038561650438638774,
+      "grad_norm": 1.0,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.118,
+      "memory/device_reserved (GiB)": 246.57,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 25,
+      "tokens_per_second_per_gpu": 449.18,
+      "total_tokens": 6340204
+    },
+    {
+      "epoch": 0.046273980526366526,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.45e-06,
+      "loss": 1.1324,
+      "memory/device_reserved (GiB)": 246.57,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 30,
+      "tokens_per_second_per_gpu": 450.16,
+      "total_tokens": 7552866
+    },
+    {
+      "epoch": 0.053986310614094285,
+      "grad_norm": 0.76171875,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 1.1225,
+      "memory/device_reserved (GiB)": 246.57,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 35,
+      "tokens_per_second_per_gpu": 517.87,
+      "total_tokens": 8796011
+    },
+    {
+      "epoch": 0.06169864070182204,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 1.0583,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 40,
+      "tokens_per_second_per_gpu": 478.29,
+      "total_tokens": 10026103
+    },
+    {
+      "epoch": 0.06941097078954979,
+      "grad_norm": 0.7578125,
+      "learning_rate": 2.2e-06,
+      "loss": 1.0965,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 45,
+      "tokens_per_second_per_gpu": 470.47,
+      "total_tokens": 11340325
+    },
+    {
+      "epoch": 0.07712330087727755,
+      "grad_norm": 0.65625,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 1.1055,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 50,
+      "tokens_per_second_per_gpu": 447.61,
+      "total_tokens": 12618872
+    },
+    {
+      "epoch": 0.08483563096500531,
+      "grad_norm": 0.61328125,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 1.0971,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 55,
+      "tokens_per_second_per_gpu": 468.97,
+      "total_tokens": 13906030
+    },
+    {
+      "epoch": 0.09254796105273305,
+      "grad_norm": 0.51171875,
+      "learning_rate": 2.95e-06,
+      "loss": 1.0837,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 60,
+      "tokens_per_second_per_gpu": 443.28,
+      "total_tokens": 15157386
+    },
+    {
+      "epoch": 0.10026029114046081,
+      "grad_norm": 0.474609375,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.081,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 65,
+      "tokens_per_second_per_gpu": 434.55,
+      "total_tokens": 16483820
+    },
+    {
+      "epoch": 0.10797262122818857,
+      "grad_norm": 0.486328125,
+      "learning_rate": 3.45e-06,
+      "loss": 1.0501,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 70,
+      "tokens_per_second_per_gpu": 446.29,
+      "total_tokens": 17761687
+    },
+    {
+      "epoch": 0.11568495131591632,
+      "grad_norm": 0.37890625,
+      "learning_rate": 3.7e-06,
+      "loss": 1.0402,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 75,
+      "tokens_per_second_per_gpu": 499.21,
+      "total_tokens": 19043878
+    },
+    {
+      "epoch": 0.12339728140364407,
+      "grad_norm": 0.42578125,
+      "learning_rate": 3.95e-06,
+      "loss": 1.0604,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 80,
+      "tokens_per_second_per_gpu": 453.36,
+      "total_tokens": 20314866
+    },
+    {
+      "epoch": 0.13110961149137182,
+      "grad_norm": 0.373046875,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.0382,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 85,
+      "tokens_per_second_per_gpu": 453.89,
+      "total_tokens": 21555557
+    },
+    {
+      "epoch": 0.13882194157909958,
+      "grad_norm": 0.330078125,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 1.0753,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 90,
+      "tokens_per_second_per_gpu": 510.81,
+      "total_tokens": 22834764
+    },
+    {
+      "epoch": 0.14653427166682734,
+      "grad_norm": 0.373046875,
+      "learning_rate": 4.7e-06,
+      "loss": 1.021,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 95,
+      "tokens_per_second_per_gpu": 477.3,
+      "total_tokens": 24078719
+    },
+    {
+      "epoch": 0.1542466017545551,
+      "grad_norm": 0.271484375,
+      "learning_rate": 4.95e-06,
+      "loss": 1.0379,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 100,
+      "tokens_per_second_per_gpu": 495.26,
+      "total_tokens": 25368597
+    },
+    {
+      "epoch": 0.16195893184228285,
+      "grad_norm": 0.283203125,
+      "learning_rate": 4.999950130642566e-06,
+      "loss": 1.0399,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 105,
+      "tokens_per_second_per_gpu": 458.71,
+      "total_tokens": 26667382
+    },
+    {
+      "epoch": 0.16967126193001061,
+      "grad_norm": 0.27734375,
+      "learning_rate": 4.999747540342916e-06,
+      "loss": 1.0052,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 110,
+      "tokens_per_second_per_gpu": 454.85,
+      "total_tokens": 27935546
+    },
+    {
+      "epoch": 0.17738359201773837,
+      "grad_norm": 0.287109375,
+      "learning_rate": 4.999389126939546e-06,
+      "loss": 0.9942,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 115,
+      "tokens_per_second_per_gpu": 488.42,
+      "total_tokens": 29232061
+    },
+    {
+      "epoch": 0.1850959221054661,
+      "grad_norm": 0.263671875,
+      "learning_rate": 4.998874916411828e-06,
+      "loss": 1.0166,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 120,
+      "tokens_per_second_per_gpu": 479.94,
+      "total_tokens": 30496024
+    },
+    {
+      "epoch": 0.19280825219319386,
+      "grad_norm": 0.271484375,
+      "learning_rate": 4.99820494603199e-06,
+      "loss": 0.9909,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 125,
+      "tokens_per_second_per_gpu": 462.61,
+      "total_tokens": 31699870
+    },
+    {
+      "epoch": 0.20052058228092162,
+      "grad_norm": 0.259765625,
+      "learning_rate": 4.997379264362414e-06,
+      "loss": 0.9874,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 130,
+      "tokens_per_second_per_gpu": 467.47,
+      "total_tokens": 32956914
+    },
+    {
+      "epoch": 0.20823291236864938,
+      "grad_norm": 0.251953125,
+      "learning_rate": 4.996397931252118e-06,
+      "loss": 1.0041,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 135,
+      "tokens_per_second_per_gpu": 459.93,
+      "total_tokens": 34182303
+    },
+    {
+      "epoch": 0.21594524245637714,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 4.9952610178324206e-06,
+      "loss": 1.0227,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 140,
+      "tokens_per_second_per_gpu": 510.67,
+      "total_tokens": 35453388
+    },
+    {
+      "epoch": 0.2236575725441049,
+      "grad_norm": 0.2734375,
+      "learning_rate": 4.993968606511777e-06,
+      "loss": 1.0007,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 145,
+      "tokens_per_second_per_gpu": 448.95,
+      "total_tokens": 36723948
+    },
+    {
+      "epoch": 0.23136990263183263,
+      "grad_norm": 0.24609375,
+      "learning_rate": 4.9925207909698115e-06,
+      "loss": 0.9714,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 150,
+      "tokens_per_second_per_gpu": 460.62,
+      "total_tokens": 37953157
+    },
+    {
+      "epoch": 0.2390822327195604,
+      "grad_norm": 0.244140625,
+      "learning_rate": 4.990917676150527e-06,
+      "loss": 1.0193,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 155,
+      "tokens_per_second_per_gpu": 509.45,
+      "total_tokens": 39278804
+    },
+    {
+      "epoch": 0.24679456280728815,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 4.989159378254698e-06,
+      "loss": 0.9887,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 160,
+      "tokens_per_second_per_gpu": 491.62,
+      "total_tokens": 40562259
+    },
+    {
+      "epoch": 0.2545068928950159,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 4.9872460247314455e-06,
+      "loss": 0.9637,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 165,
+      "tokens_per_second_per_gpu": 423.64,
+      "total_tokens": 41779016
+    },
+    {
+      "epoch": 0.26221922298274364,
+      "grad_norm": 0.248046875,
+      "learning_rate": 4.9851777542690004e-06,
+      "loss": 0.9812,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 170,
+      "tokens_per_second_per_gpu": 504.59,
+      "total_tokens": 43071677
+    },
+    {
+      "epoch": 0.2699315530704714,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 4.9829547167846515e-06,
+      "loss": 0.9513,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 175,
+      "tokens_per_second_per_gpu": 440.97,
+      "total_tokens": 44311747
+    },
+    {
+      "epoch": 0.27764388315819916,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.9805770734138785e-06,
+      "loss": 0.9504,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 180,
+      "tokens_per_second_per_gpu": 463.76,
+      "total_tokens": 45513801
+    },
+    {
+      "epoch": 0.2853562132459269,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 4.978044996498671e-06,
+      "loss": 0.9967,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 185,
+      "tokens_per_second_per_gpu": 450.72,
+      "total_tokens": 46737916
+    },
+    {
+      "epoch": 0.2930685433336547,
+      "grad_norm": 0.32421875,
+      "learning_rate": 4.975358669575039e-06,
+      "loss": 0.9927,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 190,
+      "tokens_per_second_per_gpu": 482.76,
+      "total_tokens": 48020729
+    },
+    {
+      "epoch": 0.30078087342138243,
+      "grad_norm": 0.259765625,
+      "learning_rate": 4.972518287359707e-06,
+      "loss": 0.9893,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 195,
+      "tokens_per_second_per_gpu": 437.14,
+      "total_tokens": 49235773
+    },
+    {
+      "epoch": 0.3084932035091102,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 4.969524055735999e-06,
+      "loss": 0.9344,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 200,
+      "tokens_per_second_per_gpu": 428.14,
+      "total_tokens": 50485073
+    },
+    {
+      "epoch": 0.31620553359683795,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 4.9663761917389195e-06,
+      "loss": 0.9669,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 205,
+      "tokens_per_second_per_gpu": 513.34,
+      "total_tokens": 51774221
+    },
+    {
+      "epoch": 0.3239178636845657,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 4.9630749235394174e-06,
+      "loss": 1.0206,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 210,
+      "tokens_per_second_per_gpu": 470.02,
+      "total_tokens": 53055366
+    },
+    {
+      "epoch": 0.33163019377229347,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.959620490427851e-06,
+      "loss": 1.0136,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 215,
+      "tokens_per_second_per_gpu": 474.09,
+      "total_tokens": 54318548
+    },
+    {
+      "epoch": 0.33934252386002123,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 4.95601314279664e-06,
+      "loss": 0.98,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 220,
+      "tokens_per_second_per_gpu": 441.47,
+      "total_tokens": 55573941
+    },
+    {
+      "epoch": 0.347054853947749,
+      "grad_norm": 0.21875,
+      "learning_rate": 4.952253142122116e-06,
+      "loss": 0.9428,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 225,
+      "tokens_per_second_per_gpu": 446.8,
+      "total_tokens": 56816147
+    },
+    {
+      "epoch": 0.35476718403547675,
+      "grad_norm": 0.236328125,
+      "learning_rate": 4.948340760945575e-06,
+      "loss": 0.9925,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 230,
+      "tokens_per_second_per_gpu": 440.95,
+      "total_tokens": 58018929
+    },
+    {
+      "epoch": 0.36247951412320445,
+      "grad_norm": 0.216796875,
+      "learning_rate": 4.944276282853515e-06,
+      "loss": 1.0056,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 235,
+      "tokens_per_second_per_gpu": 437.83,
+      "total_tokens": 59236706
+    },
+    {
+      "epoch": 0.3701918442109322,
+      "grad_norm": 0.216796875,
+      "learning_rate": 4.940060002457083e-06,
+      "loss": 1.0271,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 240,
+      "tokens_per_second_per_gpu": 478.28,
+      "total_tokens": 60523938
+    },
+    {
+      "epoch": 0.37790417429865997,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 4.935692225370723e-06,
+      "loss": 0.9817,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 245,
+      "tokens_per_second_per_gpu": 461.75,
+      "total_tokens": 61782785
+    },
+    {
+      "epoch": 0.3856165043863877,
+      "grad_norm": 0.2265625,
+      "learning_rate": 4.9311732681900195e-06,
+      "loss": 1.0036,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 250,
+      "tokens_per_second_per_gpu": 455.35,
+      "total_tokens": 62995481
+    },
+    {
+      "epoch": 0.3933288344741155,
+      "grad_norm": 0.2109375,
+      "learning_rate": 4.926503458468756e-06,
+      "loss": 1.0026,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 255,
+      "tokens_per_second_per_gpu": 485.03,
+      "total_tokens": 64329450
+    },
+    {
+      "epoch": 0.40104116456184324,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 4.921683134695161e-06,
+      "loss": 1.0022,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 260,
+      "tokens_per_second_per_gpu": 462.42,
+      "total_tokens": 65577746
+    },
+    {
+      "epoch": 0.408753494649571,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 4.916712646267386e-06,
+      "loss": 1.0291,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 265,
+      "tokens_per_second_per_gpu": 467.37,
+      "total_tokens": 66836212
+    },
+    {
+      "epoch": 0.41646582473729876,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 4.91159235346817e-06,
+      "loss": 0.9912,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 270,
+      "tokens_per_second_per_gpu": 515.37,
+      "total_tokens": 68143788
+    },
+    {
+      "epoch": 0.4241781548250265,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 4.906322627438728e-06,
+      "loss": 0.965,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 275,
+      "tokens_per_second_per_gpu": 482.58,
+      "total_tokens": 69419203
+    },
+    {
+      "epoch": 0.4318904849127543,
+      "grad_norm": 0.251953125,
+      "learning_rate": 4.900903850151851e-06,
+      "loss": 0.9919,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 280,
+      "tokens_per_second_per_gpu": 476.95,
+      "total_tokens": 70708858
+    },
+    {
+      "epoch": 0.43960281500048204,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 4.895336414384216e-06,
+      "loss": 1.015,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 285,
+      "tokens_per_second_per_gpu": 488.29,
+      "total_tokens": 71965415
+    },
+    {
+      "epoch": 0.4473151450882098,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 4.889620723687917e-06,
+      "loss": 0.998,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 290,
+      "tokens_per_second_per_gpu": 501.89,
+      "total_tokens": 73325345
+    },
+    {
+      "epoch": 0.45502747517593756,
+      "grad_norm": 0.24609375,
+      "learning_rate": 4.883757192361212e-06,
+      "loss": 0.9773,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 295,
+      "tokens_per_second_per_gpu": 469.94,
+      "total_tokens": 74612028
+    },
+    {
+      "epoch": 0.46273980526366526,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 4.8777462454184985e-06,
+      "loss": 0.9877,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 300,
+      "tokens_per_second_per_gpu": 476.32,
+      "total_tokens": 75892822
+    },
+    {
+      "epoch": 0.470452135351393,
+      "grad_norm": 0.244140625,
+      "learning_rate": 4.871588318559497e-06,
+      "loss": 1.0243,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 305,
+      "tokens_per_second_per_gpu": 451.66,
+      "total_tokens": 77185408
+    },
+    {
+      "epoch": 0.4781644654391208,
+      "grad_norm": 0.220703125,
+      "learning_rate": 4.86528385813768e-06,
+      "loss": 0.9481,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 310,
+      "tokens_per_second_per_gpu": 441.19,
+      "total_tokens": 78404970
+    },
+    {
+      "epoch": 0.48587679552684854,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.8588333211279105e-06,
+      "loss": 0.9578,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 315,
+      "tokens_per_second_per_gpu": 466.55,
+      "total_tokens": 79635002
+    },
+    {
+      "epoch": 0.4935891256145763,
+      "grad_norm": 0.212890625,
+      "learning_rate": 4.852237175093324e-06,
+      "loss": 1.0071,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 320,
+      "tokens_per_second_per_gpu": 452.13,
+      "total_tokens": 80933611
+    },
+    {
+      "epoch": 0.5013014557023041,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 4.845495898151433e-06,
+      "loss": 0.944,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 325,
+      "tokens_per_second_per_gpu": 433.83,
+      "total_tokens": 82145228
+    },
+    {
+      "epoch": 0.5090137857900318,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 4.838609978939473e-06,
+      "loss": 1.0259,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 330,
+      "tokens_per_second_per_gpu": 453.14,
+      "total_tokens": 83357951
+    },
+    {
+      "epoch": 0.5167261158777595,
+      "grad_norm": 0.236328125,
+      "learning_rate": 4.831579916578984e-06,
+      "loss": 0.9701,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 335,
+      "tokens_per_second_per_gpu": 466.64,
+      "total_tokens": 84573768
+    },
+    {
+      "epoch": 0.5244384459654873,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 4.824406220639634e-06,
+      "loss": 1.005,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 340,
+      "tokens_per_second_per_gpu": 460.44,
+      "total_tokens": 85851432
+    },
+    {
+      "epoch": 0.532150776053215,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 4.817089411102277e-06,
+      "loss": 0.9687,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 345,
+      "tokens_per_second_per_gpu": 440.77,
+      "total_tokens": 87088346
+    },
+    {
+      "epoch": 0.5398631061409428,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 4.809630018321269e-06,
+      "loss": 0.9483,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 350,
+      "tokens_per_second_per_gpu": 480.0,
+      "total_tokens": 88317739
+    },
+    {
+      "epoch": 0.5475754362286706,
+      "grad_norm": 0.271484375,
+      "learning_rate": 4.802028582986024e-06,
+      "loss": 0.9666,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 355,
+      "tokens_per_second_per_gpu": 476.5,
+      "total_tokens": 89577574
+    },
+    {
+      "epoch": 0.5552877663163983,
+      "grad_norm": 0.240234375,
+      "learning_rate": 4.794285656081819e-06,
+      "loss": 0.9507,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 360,
+      "tokens_per_second_per_gpu": 497.81,
+      "total_tokens": 90828267
+    },
+    {
+      "epoch": 0.5630000964041261,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 4.786401798849861e-06,
+      "loss": 0.9405,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 365,
+      "tokens_per_second_per_gpu": 481.32,
+      "total_tokens": 92116882
+    },
+    {
+      "epoch": 0.5707124264918538,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 4.778377582746601e-06,
+      "loss": 1.0099,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 370,
+      "tokens_per_second_per_gpu": 459.13,
+      "total_tokens": 93354393
+    },
+    {
+      "epoch": 0.5784247565795816,
+      "grad_norm": 0.220703125,
+      "learning_rate": 4.770213589402317e-06,
+      "loss": 0.9608,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 375,
+      "tokens_per_second_per_gpu": 485.77,
+      "total_tokens": 94596707
+    },
+    {
+      "epoch": 0.5861370866673093,
+      "grad_norm": 0.2109375,
+      "learning_rate": 4.7619104105789525e-06,
+      "loss": 0.9747,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 380,
+      "tokens_per_second_per_gpu": 449.15,
+      "total_tokens": 95823690
+    },
+    {
+      "epoch": 0.5938494167550371,
+      "grad_norm": 0.234375,
+      "learning_rate": 4.753468648127223e-06,
+      "loss": 0.9593,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 385,
+      "tokens_per_second_per_gpu": 462.81,
+      "total_tokens": 97064318
+    },
+    {
+      "epoch": 0.6015617468427649,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 4.74488891394299e-06,
+      "loss": 0.984,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 390,
+      "tokens_per_second_per_gpu": 467.19,
+      "total_tokens": 98318680
+    },
+    {
+      "epoch": 0.6092740769304926,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.7361718299229125e-06,
+      "loss": 0.9446,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 395,
+      "tokens_per_second_per_gpu": 439.44,
+      "total_tokens": 99522489
+    },
+    {
+      "epoch": 0.6169864070182204,
+      "grad_norm": 0.2265625,
+      "learning_rate": 4.727318027919364e-06,
+      "loss": 0.9796,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 400,
+      "tokens_per_second_per_gpu": 441.41,
+      "total_tokens": 100785080
+    },
+    {
+      "epoch": 0.6246987371059481,
+      "grad_norm": 0.23046875,
+      "learning_rate": 4.718328149694636e-06,
+      "loss": 1.0054,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 405,
+      "tokens_per_second_per_gpu": 497.07,
+      "total_tokens": 102084350
+    },
+    {
+      "epoch": 0.6324110671936759,
+      "grad_norm": 0.236328125,
+      "learning_rate": 4.70920284687442e-06,
+      "loss": 0.9891,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 410,
+      "tokens_per_second_per_gpu": 482.3,
+      "total_tokens": 103357801
+    },
+    {
+      "epoch": 0.6401233972814037,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 4.699942780900575e-06,
+      "loss": 0.9616,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 415,
+      "tokens_per_second_per_gpu": 499.49,
+      "total_tokens": 104613606
+    },
+    {
+      "epoch": 0.6478357273691314,
+      "grad_norm": 0.212890625,
+      "learning_rate": 4.6905486229831814e-06,
+      "loss": 0.9559,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 420,
+      "tokens_per_second_per_gpu": 500.21,
+      "total_tokens": 105880634
+    },
+    {
+      "epoch": 0.6555480574568592,
+      "grad_norm": 0.220703125,
+      "learning_rate": 4.68102105405189e-06,
+      "loss": 0.9997,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 425,
+      "tokens_per_second_per_gpu": 473.56,
+      "total_tokens": 107115671
+    },
+    {
+      "epoch": 0.6632603875445869,
+      "grad_norm": 0.212890625,
+      "learning_rate": 4.671360764706566e-06,
+      "loss": 0.9785,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 430,
+      "tokens_per_second_per_gpu": 507.32,
+      "total_tokens": 108431881
+    },
+    {
+      "epoch": 0.6709727176323147,
+      "grad_norm": 0.21484375,
+      "learning_rate": 4.661568455167234e-06,
+      "loss": 0.9736,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 435,
+      "tokens_per_second_per_gpu": 446.16,
+      "total_tokens": 109661764
+    },
+    {
+      "epoch": 0.6786850477200425,
+      "grad_norm": 0.23046875,
+      "learning_rate": 4.6516448352233115e-06,
+      "loss": 0.9528,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 440,
+      "tokens_per_second_per_gpu": 464.06,
+      "total_tokens": 110893822
+    },
+    {
+      "epoch": 0.6863973778077702,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 4.641590624182177e-06,
+      "loss": 0.9679,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 445,
+      "tokens_per_second_per_gpu": 474.49,
+      "total_tokens": 112161956
+    },
+    {
+      "epoch": 0.694109707895498,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 4.631406550817017e-06,
+      "loss": 0.9598,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 450,
+      "tokens_per_second_per_gpu": 458.35,
+      "total_tokens": 113387998
+    },
+    {
+      "epoch": 0.7018220379832257,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.621093353314011e-06,
+      "loss": 0.9754,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 455,
+      "tokens_per_second_per_gpu": 458.23,
+      "total_tokens": 114644259
+    },
+    {
+      "epoch": 0.7095343680709535,
+      "grad_norm": 0.23828125,
+      "learning_rate": 4.610651779218818e-06,
+      "loss": 0.9744,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 460,
+      "tokens_per_second_per_gpu": 512.77,
+      "total_tokens": 115933303
+    },
+    {
+      "epoch": 0.7172466981586811,
+      "grad_norm": 0.296875,
+      "learning_rate": 4.600082585382396e-06,
+      "loss": 0.9725,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 465,
+      "tokens_per_second_per_gpu": 535.52,
+      "total_tokens": 117241165
+    },
+    {
+      "epoch": 0.7249590282464089,
+      "grad_norm": 0.1953125,
+      "learning_rate": 4.5893865379061375e-06,
+      "loss": 0.9523,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 470,
+      "tokens_per_second_per_gpu": 446.49,
+      "total_tokens": 118480571
+    },
+    {
+      "epoch": 0.7326713583341367,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 4.578564412086345e-06,
+      "loss": 0.9915,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 475,
+      "tokens_per_second_per_gpu": 447.33,
+      "total_tokens": 119748086
+    },
+    {
+      "epoch": 0.7403836884218644,
+      "grad_norm": 0.234375,
+      "learning_rate": 4.567616992358027e-06,
+      "loss": 0.9736,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 480,
+      "tokens_per_second_per_gpu": 455.33,
+      "total_tokens": 121010074
+    },
+    {
+      "epoch": 0.7480960185095922,
+      "grad_norm": 0.212890625,
+      "learning_rate": 4.556545072238046e-06,
+      "loss": 0.9755,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 485,
+      "tokens_per_second_per_gpu": 441.4,
+      "total_tokens": 122291737
+    },
+    {
+      "epoch": 0.7558083485973199,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 4.545349454267595e-06,
+      "loss": 0.9839,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 490,
+      "tokens_per_second_per_gpu": 451.9,
+      "total_tokens": 123604957
+    },
+    {
+      "epoch": 0.7635206786850477,
+      "grad_norm": 0.22265625,
+      "learning_rate": 4.534030949954029e-06,
+      "loss": 0.9801,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 495,
+      "tokens_per_second_per_gpu": 443.71,
+      "total_tokens": 124876147
+    },
+    {
+      "epoch": 0.7712330087727755,
+      "grad_norm": 0.212890625,
+      "learning_rate": 4.522590379712043e-06,
+      "loss": 0.966,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 500,
+      "tokens_per_second_per_gpu": 465.62,
+      "total_tokens": 126142017
+    },
+    {
+      "epoch": 0.7789453388605032,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 4.511028572804202e-06,
+      "loss": 0.9528,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 505,
+      "tokens_per_second_per_gpu": 474.94,
+      "total_tokens": 127354629
+    },
+    {
+      "epoch": 0.786657668948231,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 4.499346367280838e-06,
+      "loss": 0.9615,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 510,
+      "tokens_per_second_per_gpu": 495.08,
+      "total_tokens": 128638347
+    },
+    {
+      "epoch": 0.7943699990359587,
+      "grad_norm": 0.203125,
+      "learning_rate": 4.4875446099193e-06,
+      "loss": 0.9405,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 515,
+      "tokens_per_second_per_gpu": 444.79,
+      "total_tokens": 129925188
+    },
+    {
+      "epoch": 0.8020823291236865,
+      "grad_norm": 0.197265625,
+      "learning_rate": 4.475624156162578e-06,
+      "loss": 0.9918,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 520,
+      "tokens_per_second_per_gpu": 466.79,
+      "total_tokens": 131210797
+    },
+    {
+      "epoch": 0.8097946592114142,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 4.463585870057293e-06,
+      "loss": 0.9679,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 525,
+      "tokens_per_second_per_gpu": 460.59,
+      "total_tokens": 132460881
+    },
+    {
+      "epoch": 0.817506989299142,
+      "grad_norm": 0.23828125,
+      "learning_rate": 4.4514306241910716e-06,
+      "loss": 0.9684,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 530,
+      "tokens_per_second_per_gpu": 476.54,
+      "total_tokens": 133653075
+    },
+    {
+      "epoch": 0.8252193193868698,
+      "grad_norm": 0.201171875,
+      "learning_rate": 4.439159299629297e-06,
+      "loss": 0.9562,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 535,
+      "tokens_per_second_per_gpu": 486.69,
+      "total_tokens": 134977958
+    },
+    {
+      "epoch": 0.8329316494745975,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 4.426772785851242e-06,
+      "loss": 0.9743,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 540,
+      "tokens_per_second_per_gpu": 494.38,
+      "total_tokens": 136315997
+    },
+    {
+      "epoch": 0.8406439795623253,
+      "grad_norm": 0.21875,
+      "learning_rate": 4.414271980685597e-06,
+      "loss": 0.9508,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 545,
+      "tokens_per_second_per_gpu": 455.26,
+      "total_tokens": 137602622
+    },
+    {
+      "epoch": 0.848356309650053,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 4.401657790245395e-06,
+      "loss": 0.944,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 550,
+      "tokens_per_second_per_gpu": 452.81,
+      "total_tokens": 138895921
+    },
+    {
+      "epoch": 0.8560686397377808,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 4.388931128862326e-06,
+      "loss": 0.9463,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 555,
+      "tokens_per_second_per_gpu": 437.79,
+      "total_tokens": 140113031
+    },
+    {
+      "epoch": 0.8637809698255086,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 4.376092919020469e-06,
+      "loss": 0.9808,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 560,
+      "tokens_per_second_per_gpu": 463.15,
+      "total_tokens": 141376436
+    },
+    {
+      "epoch": 0.8714932999132363,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 4.363144091289421e-06,
+      "loss": 0.9739,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 565,
+      "tokens_per_second_per_gpu": 488.68,
+      "total_tokens": 142666491
+    },
+    {
+      "epoch": 0.8792056300009641,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.350085584256847e-06,
+      "loss": 0.9755,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 570,
+      "tokens_per_second_per_gpu": 444.08,
+      "total_tokens": 143931345
+    },
+    {
+      "epoch": 0.8869179600886918,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 4.336918344460451e-06,
+      "loss": 0.9615,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 575,
+      "tokens_per_second_per_gpu": 448.53,
+      "total_tokens": 145200618
+    },
+    {
+      "epoch": 0.8946302901764196,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 4.323643326319359e-06,
+      "loss": 0.9772,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 580,
+      "tokens_per_second_per_gpu": 484.18,
+      "total_tokens": 146502772
+    },
+    {
+      "epoch": 0.9023426202641474,
+      "grad_norm": 0.201171875,
+      "learning_rate": 4.310261492064944e-06,
+      "loss": 0.9755,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 585,
+      "tokens_per_second_per_gpu": 470.67,
+      "total_tokens": 147770982
+    },
+    {
+      "epoch": 0.9100549503518751,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 4.296773811671081e-06,
+      "loss": 0.9743,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 590,
+      "tokens_per_second_per_gpu": 467.73,
+      "total_tokens": 149068406
+    },
+    {
+      "epoch": 0.9177672804396028,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.283181262783832e-06,
+      "loss": 0.9361,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 595,
+      "tokens_per_second_per_gpu": 438.69,
+      "total_tokens": 150281330
+    },
+    {
+      "epoch": 0.9254796105273305,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.269484830650589e-06,
+      "loss": 0.9654,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 600,
+      "tokens_per_second_per_gpu": 453.7,
+      "total_tokens": 151550646
+    },
+    {
+      "epoch": 0.9331919406150583,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 4.255685508048654e-06,
+      "loss": 0.9209,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 605,
+      "tokens_per_second_per_gpu": 485.97,
+      "total_tokens": 152800147
+    },
+    {
+      "epoch": 0.940904270702786,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 4.241784295213281e-06,
+      "loss": 0.9228,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 610,
+      "tokens_per_second_per_gpu": 471.49,
+      "total_tokens": 154041877
+    },
+    {
+      "epoch": 0.9486166007905138,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 4.227782199765174e-06,
+      "loss": 0.97,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 615,
+      "tokens_per_second_per_gpu": 445.62,
+      "total_tokens": 155243285
+    },
+    {
+      "epoch": 0.9563289308782416,
+      "grad_norm": 0.2421875,
+      "learning_rate": 4.213680236637449e-06,
+      "loss": 1.0037,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 620,
+      "tokens_per_second_per_gpu": 499.17,
+      "total_tokens": 156517899
+    },
+    {
+      "epoch": 0.9640412609659693,
+      "grad_norm": 0.228515625,
+      "learning_rate": 4.19947942800207e-06,
+      "loss": 0.9686,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 625,
+      "tokens_per_second_per_gpu": 475.34,
+      "total_tokens": 157838358
+    },
+    {
+      "epoch": 0.9717535910536971,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 4.1851808031957545e-06,
+      "loss": 0.9373,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 630,
+      "tokens_per_second_per_gpu": 498.46,
+      "total_tokens": 159098939
+    },
+    {
+      "epoch": 0.9794659211414248,
+      "grad_norm": 0.2109375,
+      "learning_rate": 4.170785398645364e-06,
+      "loss": 0.99,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 635,
+      "tokens_per_second_per_gpu": 491.96,
+      "total_tokens": 160426067
+    },
+    {
+      "epoch": 0.9871782512291526,
+      "grad_norm": 0.220703125,
+      "learning_rate": 4.156294257792778e-06,
+      "loss": 0.9816,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 640,
+      "tokens_per_second_per_gpu": 470.02,
+      "total_tokens": 161645752
+    },
+    {
+      "epoch": 0.9948905813168804,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 4.141708431019264e-06,
+      "loss": 0.9631,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 645,
+      "tokens_per_second_per_gpu": 513.67,
+      "total_tokens": 162985387
+    },
+    {
+      "epoch": 1.0015424660175456,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 4.127028975569339e-06,
+      "loss": 0.9654,
+      "memory/device_reserved (GiB)": 246.75,
+      "memory/max_active (GiB)": 211.16,
+      "memory/max_allocated (GiB)": 211.16,
+      "step": 650,
+      "tokens_per_second_per_gpu": 398.45,
+      "total_tokens": 164082525
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1945,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 217,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6172120234563994e+20,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

so_fun_time/651/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739fcb0f187c86bba0364c5a0f0dc107598b2f1cf993047f8f4fd22304f2d1d1
+size 12433