Upload folder using huggingface_hub

.gitattributes

@@ -56,3 +56,4 @@ qwen2-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llama3-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3-gob-plan-122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-gob-plan122-2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3-8b-os-plan-123/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen3-8b-os-plan-123/README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen3-8b-os-plan-123
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen3-8b-os-plan-123
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen3-8B](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen3-8B) on the os-plan-123 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1394
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3353        | 0.2247 | 50   | 0.3119          |
+| 0.2313        | 0.4494 | 100  | 0.2241          |
+| 0.1928        | 0.6742 | 150  | 0.1874          |
+| 0.165         | 0.8989 | 200  | 0.1608          |
+| 0.1071        | 1.1213 | 250  | 0.1506          |
+| 0.1014        | 1.3461 | 300  | 0.1470          |
+| 0.0963        | 1.5708 | 350  | 0.1351          |
+| 0.095         | 1.7955 | 400  | 0.1267          |
+| 0.0752        | 2.0180 | 450  | 0.1241          |
+| 0.0501        | 2.2427 | 500  | 0.1364          |
+| 0.0478        | 2.4674 | 550  | 0.1376          |
+| 0.0414        | 2.6921 | 600  | 0.1405          |
+| 0.0433        | 2.9169 | 650  | 0.1394          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen3-8b-os-plan-123/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
+}

qwen3-8b-os-plan-123/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.13935185968875885,
+    "eval_runtime": 18.5082,
+    "eval_samples_per_second": 20.261,
+    "eval_steps_per_second": 2.539,
+    "total_flos": 75063201300480.0,
+    "train_loss": 0.1622678557318957,
+    "train_runtime": 4543.8481,
+    "train_samples_per_second": 4.701,
+    "train_steps_per_second": 0.147
+}

qwen3-8b-os-plan-123/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

qwen3-8b-os-plan-123/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "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
+}

qwen3-8b-os-plan-123/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.13935185968875885,
+    "eval_runtime": 18.5082,
+    "eval_samples_per_second": 20.261,
+    "eval_steps_per_second": 2.539
+}

qwen3-8b-os-plan-123/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

qwen3-8b-os-plan-123/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391a5024f3c096f8b1be5027d907e5a7ae85e93c56f8af6a34faa112d62afc5a
+size 4902257696

qwen3-8b-os-plan-123/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdcfe69b4913dd83374d5dd62b0dccdc6308b2fa85b2f7a77beed970d1de256
+size 4915960368

qwen3-8b-os-plan-123/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6cc25abcfb8f0c47ef12174e99fefed7c6a00c8048c7ee1e6e55c73a16e3ff
+size 4983068496

qwen3-8b-os-plan-123/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f0f23690e4313cf1da89c827e67ef2ac06610ce111b44e0fc99b6fe7b46252
+size 1580230264

qwen3-8b-os-plan-123/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

qwen3-8b-os-plan-123/runs/Jan24_01-39-35_hgx003/events.out.tfevents.1769190108.hgx003.2976978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7404f9d2d9955169e6ae198887d750ba678b71e0ef073cea30743fa2b22257
+size 24176

qwen3-8b-os-plan-123/runs/Jan24_01-39-35_hgx003/events.out.tfevents.1769194695.hgx003.2976978.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5fa9aca0d7f94e046aed9637b3b56abbde2dc6dda588f5c85f8556615b8a1c
+size 359

qwen3-8b-os-plan-123/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
+  }
+}

qwen3-8b-os-plan-123/tokenizer.json

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

qwen3-8b-os-plan-123/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen3-8b-os-plan-123/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 75063201300480.0,
+    "train_loss": 0.1622678557318957,
+    "train_runtime": 4543.8481,
+    "train_samples_per_second": 4.701,
+    "train_steps_per_second": 0.147
+}

qwen3-8b-os-plan-123/trainer_log.jsonl

@@ -0,0 +1,80 @@
+{"current_steps": 10, "total_steps": 669, "loss": 1.8793, "lr": 1.3432835820895524e-06, "epoch": 0.0449438202247191, "percentage": 1.49, "elapsed_time": "0:01:03", "remaining_time": "1:09:48"}
+{"current_steps": 20, "total_steps": 669, "loss": 1.0558, "lr": 2.835820895522388e-06, "epoch": 0.0898876404494382, "percentage": 2.99, "elapsed_time": "0:02:10", "remaining_time": "1:10:21"}
+{"current_steps": 30, "total_steps": 669, "loss": 0.556, "lr": 4.3283582089552236e-06, "epoch": 0.1348314606741573, "percentage": 4.48, "elapsed_time": "0:03:09", "remaining_time": "1:07:19"}
+{"current_steps": 40, "total_steps": 669, "loss": 0.3893, "lr": 5.820895522388061e-06, "epoch": 0.1797752808988764, "percentage": 5.98, "elapsed_time": "0:04:18", "remaining_time": "1:07:50"}
+{"current_steps": 50, "total_steps": 669, "loss": 0.3353, "lr": 7.313432835820896e-06, "epoch": 0.2247191011235955, "percentage": 7.47, "elapsed_time": "0:05:28", "remaining_time": "1:07:43"}
+{"current_steps": 50, "total_steps": 669, "eval_loss": 0.31193050742149353, "epoch": 0.2247191011235955, "percentage": 7.47, "elapsed_time": "0:05:46", "remaining_time": "1:11:34"}
+{"current_steps": 60, "total_steps": 669, "loss": 0.291, "lr": 8.805970149253732e-06, "epoch": 0.2696629213483146, "percentage": 8.97, "elapsed_time": "0:06:48", "remaining_time": "1:09:03"}
+{"current_steps": 70, "total_steps": 669, "loss": 0.2523, "lr": 9.999727665400876e-06, "epoch": 0.3146067415730337, "percentage": 10.46, "elapsed_time": "0:07:46", "remaining_time": "1:06:35"}
+{"current_steps": 80, "total_steps": 669, "loss": 0.2472, "lr": 9.990199069047216e-06, "epoch": 0.3595505617977528, "percentage": 11.96, "elapsed_time": "0:08:46", "remaining_time": "1:04:35"}
+{"current_steps": 90, "total_steps": 669, "loss": 0.2333, "lr": 9.967083394667763e-06, "epoch": 0.4044943820224719, "percentage": 13.45, "elapsed_time": "0:09:53", "remaining_time": "1:03:39"}
+{"current_steps": 100, "total_steps": 669, "loss": 0.2313, "lr": 9.93044358052752e-06, "epoch": 0.449438202247191, "percentage": 14.95, "elapsed_time": "0:10:53", "remaining_time": "1:01:58"}
+{"current_steps": 100, "total_steps": 669, "eval_loss": 0.2241148054599762, "epoch": 0.449438202247191, "percentage": 14.95, "elapsed_time": "0:11:12", "remaining_time": "1:03:44"}
+{"current_steps": 110, "total_steps": 669, "loss": 0.2119, "lr": 9.880379387779637e-06, "epoch": 0.4943820224719101, "percentage": 16.44, "elapsed_time": "0:12:13", "remaining_time": "1:02:07"}
+{"current_steps": 120, "total_steps": 669, "loss": 0.202, "lr": 9.817027128840462e-06, "epoch": 0.5393258426966292, "percentage": 17.94, "elapsed_time": "0:13:12", "remaining_time": "1:00:26"}
+{"current_steps": 130, "total_steps": 669, "loss": 0.1914, "lr": 9.740559296244543e-06, "epoch": 0.5842696629213483, "percentage": 19.43, "elapsed_time": "0:14:12", "remaining_time": "0:58:56"}
+{"current_steps": 140, "total_steps": 669, "loss": 0.1787, "lr": 9.651184092990109e-06, "epoch": 0.6292134831460674, "percentage": 20.93, "elapsed_time": "0:15:14", "remaining_time": "0:57:36"}
+{"current_steps": 150, "total_steps": 669, "loss": 0.1928, "lr": 9.5491448656538e-06, "epoch": 0.6741573033707865, "percentage": 22.42, "elapsed_time": "0:16:20", "remaining_time": "0:56:32"}
+{"current_steps": 150, "total_steps": 669, "eval_loss": 0.18743214011192322, "epoch": 0.6741573033707865, "percentage": 22.42, "elapsed_time": "0:16:39", "remaining_time": "0:57:37"}
+{"current_steps": 160, "total_steps": 669, "loss": 0.1757, "lr": 9.434719441818106e-06, "epoch": 0.7191011235955056, "percentage": 23.92, "elapsed_time": "0:17:39", "remaining_time": "0:56:10"}
+{"current_steps": 170, "total_steps": 669, "loss": 0.1812, "lr": 9.308219373615574e-06, "epoch": 0.7640449438202247, "percentage": 25.41, "elapsed_time": "0:18:45", "remaining_time": "0:55:02"}
+{"current_steps": 180, "total_steps": 669, "loss": 0.1635, "lr": 9.16998908944939e-06, "epoch": 0.8089887640449438, "percentage": 26.91, "elapsed_time": "0:19:48", "remaining_time": "0:53:49"}
+{"current_steps": 190, "total_steps": 669, "loss": 0.1629, "lr": 9.020404956200016e-06, "epoch": 0.8539325842696629, "percentage": 28.4, "elapsed_time": "0:20:49", "remaining_time": "0:52:29"}
+{"current_steps": 200, "total_steps": 669, "loss": 0.165, "lr": 8.85987425447124e-06, "epoch": 0.898876404494382, "percentage": 29.9, "elapsed_time": "0:21:48", "remaining_time": "0:51:08"}
+{"current_steps": 200, "total_steps": 669, "eval_loss": 0.16080424189567566, "epoch": 0.898876404494382, "percentage": 29.9, "elapsed_time": "0:22:07", "remaining_time": "0:51:51"}
+{"current_steps": 210, "total_steps": 669, "loss": 0.1748, "lr": 8.688834069665819e-06, "epoch": 0.9438202247191011, "percentage": 31.39, "elapsed_time": "0:23:06", "remaining_time": "0:50:30"}
+{"current_steps": 220, "total_steps": 669, "loss": 0.1459, "lr": 8.50775010191001e-06, "epoch": 0.9887640449438202, "percentage": 32.88, "elapsed_time": "0:24:11", "remaining_time": "0:49:22"}
+{"current_steps": 230, "total_steps": 669, "loss": 0.1235, "lr": 8.317115398067289e-06, "epoch": 1.0314606741573034, "percentage": 34.38, "elapsed_time": "0:25:09", "remaining_time": "0:48:01"}
+{"current_steps": 240, "total_steps": 669, "loss": 0.1065, "lr": 8.117449009293668e-06, "epoch": 1.0764044943820226, "percentage": 35.87, "elapsed_time": "0:26:10", "remaining_time": "0:46:47"}
+{"current_steps": 250, "total_steps": 669, "loss": 0.1071, "lr": 7.909294577789765e-06, "epoch": 1.1213483146067416, "percentage": 37.37, "elapsed_time": "0:27:06", "remaining_time": "0:45:26"}
+{"current_steps": 250, "total_steps": 669, "eval_loss": 0.15057042241096497, "epoch": 1.1213483146067416, "percentage": 37.37, "elapsed_time": "0:27:25", "remaining_time": "0:45:58"}
+{"current_steps": 260, "total_steps": 669, "loss": 0.1225, "lr": 7.693218856597515e-06, "epoch": 1.1662921348314608, "percentage": 38.86, "elapsed_time": "0:28:24", "remaining_time": "0:44:42"}
+{"current_steps": 270, "total_steps": 669, "loss": 0.1065, "lr": 7.469810166471802e-06, "epoch": 1.2112359550561798, "percentage": 40.36, "elapsed_time": "0:29:27", "remaining_time": "0:43:32"}
+{"current_steps": 280, "total_steps": 669, "loss": 0.1022, "lr": 7.239676794028526e-06, "epoch": 1.256179775280899, "percentage": 41.85, "elapsed_time": "0:30:35", "remaining_time": "0:42:29"}
+{"current_steps": 290, "total_steps": 669, "loss": 0.1017, "lr": 7.003445335530572e-06, "epoch": 1.301123595505618, "percentage": 43.35, "elapsed_time": "0:31:37", "remaining_time": "0:41:19"}
+{"current_steps": 300, "total_steps": 669, "loss": 0.1014, "lr": 6.761758990821143e-06, "epoch": 1.346067415730337, "percentage": 44.84, "elapsed_time": "0:32:36", "remaining_time": "0:40:06"}
+{"current_steps": 300, "total_steps": 669, "eval_loss": 0.1469641923904419, "epoch": 1.346067415730337, "percentage": 44.84, "elapsed_time": "0:32:54", "remaining_time": "0:40:29"}
+{"current_steps": 310, "total_steps": 669, "loss": 0.1044, "lr": 6.515275812049644e-06, "epoch": 1.3910112359550562, "percentage": 46.34, "elapsed_time": "0:33:53", "remaining_time": "0:39:15"}
+{"current_steps": 320, "total_steps": 669, "loss": 0.1002, "lr": 6.264666911958404e-06, "epoch": 1.4359550561797754, "percentage": 47.83, "elapsed_time": "0:34:52", "remaining_time": "0:38:02"}
+{"current_steps": 330, "total_steps": 669, "loss": 0.1015, "lr": 6.0106146366086514e-06, "epoch": 1.4808988764044944, "percentage": 49.33, "elapsed_time": "0:35:58", "remaining_time": "0:36:57"}
+{"current_steps": 340, "total_steps": 669, "loss": 0.1004, "lr": 5.753810707520918e-06, "epoch": 1.5258426966292133, "percentage": 50.82, "elapsed_time": "0:37:00", "remaining_time": "0:35:48"}
+{"current_steps": 350, "total_steps": 669, "loss": 0.0963, "lr": 5.494954338288404e-06, "epoch": 1.5707865168539326, "percentage": 52.32, "elapsed_time": "0:38:07", "remaining_time": "0:34:45"}
+{"current_steps": 350, "total_steps": 669, "eval_loss": 0.13507342338562012, "epoch": 1.5707865168539326, "percentage": 52.32, "elapsed_time": "0:38:27", "remaining_time": "0:35:03"}
+{"current_steps": 360, "total_steps": 669, "loss": 0.0948, "lr": 5.234750330791268e-06, "epoch": 1.6157303370786518, "percentage": 53.81, "elapsed_time": "0:39:34", "remaining_time": "0:33:57"}
+{"current_steps": 370, "total_steps": 669, "loss": 0.0965, "lr": 4.973907156195405e-06, "epoch": 1.6606741573033708, "percentage": 55.31, "elapsed_time": "0:40:35", "remaining_time": "0:32:47"}
+{"current_steps": 380, "total_steps": 669, "loss": 0.094, "lr": 4.713135025960652e-06, "epoch": 1.7056179775280897, "percentage": 56.8, "elapsed_time": "0:41:43", "remaining_time": "0:31:44"}
+{"current_steps": 390, "total_steps": 669, "loss": 0.0918, "lr": 4.4531439581106295e-06, "epoch": 1.750561797752809, "percentage": 58.3, "elapsed_time": "0:42:52", "remaining_time": "0:30:40"}
+{"current_steps": 400, "total_steps": 669, "loss": 0.095, "lr": 4.194641844029227e-06, "epoch": 1.7955056179775282, "percentage": 59.79, "elapsed_time": "0:43:53", "remaining_time": "0:29:30"}
+{"current_steps": 400, "total_steps": 669, "eval_loss": 0.12670810520648956, "epoch": 1.7955056179775282, "percentage": 59.79, "elapsed_time": "0:44:11", "remaining_time": "0:29:43"}
+{"current_steps": 410, "total_steps": 669, "loss": 0.086, "lr": 3.938332521047434e-06, "epoch": 1.8404494382022472, "percentage": 61.29, "elapsed_time": "0:45:10", "remaining_time": "0:28:32"}
+{"current_steps": 420, "total_steps": 669, "loss": 0.089, "lr": 3.6849138560683305e-06, "epoch": 1.8853932584269661, "percentage": 62.78, "elapsed_time": "0:46:08", "remaining_time": "0:27:21"}
+{"current_steps": 430, "total_steps": 669, "loss": 0.0875, "lr": 3.435075845448105e-06, "epoch": 1.9303370786516854, "percentage": 64.28, "elapsed_time": "0:47:12", "remaining_time": "0:26:14"}
+{"current_steps": 440, "total_steps": 669, "loss": 0.0807, "lr": 3.189498736306584e-06, "epoch": 1.9752808988764046, "percentage": 65.77, "elapsed_time": "0:48:11", "remaining_time": "0:25:05"}
+{"current_steps": 450, "total_steps": 669, "loss": 0.0752, "lr": 2.948851174382565e-06, "epoch": 2.0179775280898875, "percentage": 67.26, "elapsed_time": "0:49:10", "remaining_time": "0:23:55"}
+{"current_steps": 450, "total_steps": 669, "eval_loss": 0.12405496835708618, "epoch": 2.0179775280898875, "percentage": 67.26, "elapsed_time": "0:49:29", "remaining_time": "0:24:05"}
+{"current_steps": 460, "total_steps": 669, "loss": 0.048, "lr": 2.7137883834768076e-06, "epoch": 2.0629213483146067, "percentage": 68.76, "elapsed_time": "0:50:33", "remaining_time": "0:22:58"}
+{"current_steps": 470, "total_steps": 669, "loss": 0.0464, "lr": 2.4849503814396624e-06, "epoch": 2.107865168539326, "percentage": 70.25, "elapsed_time": "0:51:31", "remaining_time": "0:21:49"}
+{"current_steps": 480, "total_steps": 669, "loss": 0.0467, "lr": 2.2629602375607373e-06, "epoch": 2.152808988764045, "percentage": 71.75, "elapsed_time": "0:52:39", "remaining_time": "0:20:44"}
+{"current_steps": 490, "total_steps": 669, "loss": 0.0438, "lr": 2.048422376105299e-06, "epoch": 2.197752808988764, "percentage": 73.24, "elapsed_time": "0:53:43", "remaining_time": "0:19:37"}
+{"current_steps": 500, "total_steps": 669, "loss": 0.0501, "lr": 1.8419209306164653e-06, "epoch": 2.242696629213483, "percentage": 74.74, "elapsed_time": "0:54:42", "remaining_time": "0:18:29"}
+{"current_steps": 500, "total_steps": 669, "eval_loss": 0.13637585937976837, "epoch": 2.242696629213483, "percentage": 74.74, "elapsed_time": "0:55:01", "remaining_time": "0:18:35"}
+{"current_steps": 510, "total_steps": 669, "loss": 0.0454, "lr": 1.6440181534640277e-06, "epoch": 2.2876404494382023, "percentage": 76.23, "elapsed_time": "0:57:03", "remaining_time": "0:17:47"}
+{"current_steps": 520, "total_steps": 669, "loss": 0.047, "lr": 1.4552528849702852e-06, "epoch": 2.3325842696629215, "percentage": 77.73, "elapsed_time": "0:57:59", "remaining_time": "0:16:37"}
+{"current_steps": 530, "total_steps": 669, "loss": 0.0446, "lr": 1.2761390862810907e-06, "epoch": 2.3775280898876403, "percentage": 79.22, "elapsed_time": "0:59:02", "remaining_time": "0:15:29"}
+{"current_steps": 540, "total_steps": 669, "loss": 0.0459, "lr": 1.107164439976764e-06, "epoch": 2.4224719101123595, "percentage": 80.72, "elapsed_time": "1:00:03", "remaining_time": "0:14:20"}
+{"current_steps": 550, "total_steps": 669, "loss": 0.0478, "lr": 9.487890222330137e-07, "epoch": 2.4674157303370787, "percentage": 82.21, "elapsed_time": "1:01:04", "remaining_time": "0:13:12"}
+{"current_steps": 550, "total_steps": 669, "eval_loss": 0.13764135539531708, "epoch": 2.4674157303370787, "percentage": 82.21, "elapsed_time": "1:01:23", "remaining_time": "0:13:16"}
+{"current_steps": 560, "total_steps": 669, "loss": 0.0447, "lr": 8.014440501472909e-07, "epoch": 2.512359550561798, "percentage": 83.71, "elapsed_time": "1:02:27", "remaining_time": "0:12:09"}
+{"current_steps": 570, "total_steps": 669, "loss": 0.0433, "lr": 6.655307076412637e-07, "epoch": 2.5573033707865167, "percentage": 85.2, "elapsed_time": "1:03:34", "remaining_time": "0:11:02"}
+{"current_steps": 580, "total_steps": 669, "loss": 0.0426, "lr": 5.414190531362162e-07, "epoch": 2.602247191011236, "percentage": 86.7, "elapsed_time": "1:04:34", "remaining_time": "0:09:54"}
+{"current_steps": 590, "total_steps": 669, "loss": 0.0384, "lr": 4.29447011975474e-07, "epoch": 2.647191011235955, "percentage": 88.19, "elapsed_time": "1:05:35", "remaining_time": "0:08:47"}
+{"current_steps": 600, "total_steps": 669, "loss": 0.0414, "lr": 3.299194563372604e-07, "epoch": 2.692134831460674, "percentage": 89.69, "elapsed_time": "1:06:38", "remaining_time": "0:07:39"}
+{"current_steps": 600, "total_steps": 669, "eval_loss": 0.14047548174858093, "epoch": 2.692134831460674, "percentage": 89.69, "elapsed_time": "1:06:58", "remaining_time": "0:07:42"}
+{"current_steps": 610, "total_steps": 669, "loss": 0.0438, "lr": 2.431073751431529e-07, "epoch": 2.737078651685393, "percentage": 91.18, "elapsed_time": "1:08:09", "remaining_time": "0:06:35"}
+{"current_steps": 620, "total_steps": 669, "loss": 0.0444, "lr": 1.6924713622225975e-07, "epoch": 2.7820224719101123, "percentage": 92.68, "elapsed_time": "1:09:16", "remaining_time": "0:05:28"}
+{"current_steps": 630, "total_steps": 669, "loss": 0.0433, "lr": 1.0853984274007246e-07, "epoch": 2.8269662921348315, "percentage": 94.17, "elapsed_time": "1:10:16", "remaining_time": "0:04:20"}
+{"current_steps": 640, "total_steps": 669, "loss": 0.0406, "lr": 6.115078564427946e-08, "epoch": 2.8719101123595507, "percentage": 95.67, "elapsed_time": "1:11:16", "remaining_time": "0:03:13"}
+{"current_steps": 650, "total_steps": 669, "loss": 0.0433, "lr": 2.7208993618390578e-08, "epoch": 2.9168539325842695, "percentage": 97.16, "elapsed_time": "1:12:16", "remaining_time": "0:02:06"}
+{"current_steps": 650, "total_steps": 669, "eval_loss": 0.13943476974964142, "epoch": 2.9168539325842695, "percentage": 97.16, "elapsed_time": "1:12:35", "remaining_time": "0:02:07"}
+{"current_steps": 660, "total_steps": 669, "loss": 0.0424, "lr": 6.806881768539053e-09, "epoch": 2.9617977528089887, "percentage": 98.65, "elapsed_time": "1:13:36", "remaining_time": "0:01:00"}
+{"current_steps": 669, "total_steps": 669, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:15:43", "remaining_time": "0:00:00"}

qwen3-8b-os-plan-123/trainer_state.json

@@ -0,0 +1,609 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 669,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 29.53696011939943,
+      "learning_rate": 1.3432835820895524e-06,
+      "loss": 1.8793,
+      "step": 10
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 5.689948874400446,
+      "learning_rate": 2.835820895522388e-06,
+      "loss": 1.0558,
+      "step": 20
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 2.4191305888643653,
+      "learning_rate": 4.3283582089552236e-06,
+      "loss": 0.556,
+      "step": 30
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 2.1085786427509707,
+      "learning_rate": 5.820895522388061e-06,
+      "loss": 0.3893,
+      "step": 40
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 2.1939484099423487,
+      "learning_rate": 7.313432835820896e-06,
+      "loss": 0.3353,
+      "step": 50
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "eval_loss": 0.31193050742149353,
+      "eval_runtime": 18.6615,
+      "eval_samples_per_second": 20.095,
+      "eval_steps_per_second": 2.519,
+      "step": 50
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 1.6181649355691583,
+      "learning_rate": 8.805970149253732e-06,
+      "loss": 0.291,
+      "step": 60
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": 1.511294427515036,
+      "learning_rate": 9.999727665400876e-06,
+      "loss": 0.2523,
+      "step": 70
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 1.6520831644847196,
+      "learning_rate": 9.990199069047216e-06,
+      "loss": 0.2472,
+      "step": 80
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 1.608103800048045,
+      "learning_rate": 9.967083394667763e-06,
+      "loss": 0.2333,
+      "step": 90
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 1.832441984074982,
+      "learning_rate": 9.93044358052752e-06,
+      "loss": 0.2313,
+      "step": 100
+    },
+    {
+      "epoch": 0.449438202247191,
+      "eval_loss": 0.2241148054599762,
+      "eval_runtime": 18.7351,
+      "eval_samples_per_second": 20.016,
+      "eval_steps_per_second": 2.509,
+      "step": 100
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 1.2816420356354175,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 0.2119,
+      "step": 110
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 1.369823280511189,
+      "learning_rate": 9.817027128840462e-06,
+      "loss": 0.202,
+      "step": 120
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 1.2276608320329485,
+      "learning_rate": 9.740559296244543e-06,
+      "loss": 0.1914,
+      "step": 130
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 1.4669275871674892,
+      "learning_rate": 9.651184092990109e-06,
+      "loss": 0.1787,
+      "step": 140
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 1.3481237409594649,
+      "learning_rate": 9.5491448656538e-06,
+      "loss": 0.1928,
+      "step": 150
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "eval_loss": 0.18743214011192322,
+      "eval_runtime": 18.726,
+      "eval_samples_per_second": 20.026,
+      "eval_steps_per_second": 2.51,
+      "step": 150
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 1.3634853314360846,
+      "learning_rate": 9.434719441818106e-06,
+      "loss": 0.1757,
+      "step": 160
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 1.2558395720895434,
+      "learning_rate": 9.308219373615574e-06,
+      "loss": 0.1812,
+      "step": 170
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 1.3624869834436748,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 0.1635,
+      "step": 180
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 1.1142446837454514,
+      "learning_rate": 9.020404956200016e-06,
+      "loss": 0.1629,
+      "step": 190
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 1.1228833703246348,
+      "learning_rate": 8.85987425447124e-06,
+      "loss": 0.165,
+      "step": 200
+    },
+    {
+      "epoch": 0.898876404494382,
+      "eval_loss": 0.16080424189567566,
+      "eval_runtime": 18.6764,
+      "eval_samples_per_second": 20.079,
+      "eval_steps_per_second": 2.517,
+      "step": 200
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 1.4028311610210336,
+      "learning_rate": 8.688834069665819e-06,
+      "loss": 0.1748,
+      "step": 210
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 1.1185575730086355,
+      "learning_rate": 8.50775010191001e-06,
+      "loss": 0.1459,
+      "step": 220
+    },
+    {
+      "epoch": 1.0314606741573034,
+      "grad_norm": 1.1142351685836023,
+      "learning_rate": 8.317115398067289e-06,
+      "loss": 0.1235,
+      "step": 230
+    },
+    {
+      "epoch": 1.0764044943820226,
+      "grad_norm": 1.1201035352472384,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.1065,
+      "step": 240
+    },
+    {
+      "epoch": 1.1213483146067416,
+      "grad_norm": 0.9643199428377645,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 0.1071,
+      "step": 250
+    },
+    {
+      "epoch": 1.1213483146067416,
+      "eval_loss": 0.15057042241096497,
+      "eval_runtime": 18.7292,
+      "eval_samples_per_second": 20.022,
+      "eval_steps_per_second": 2.509,
+      "step": 250
+    },
+    {
+      "epoch": 1.1662921348314608,
+      "grad_norm": 1.023910202912419,
+      "learning_rate": 7.693218856597515e-06,
+      "loss": 0.1225,
+      "step": 260
+    },
+    {
+      "epoch": 1.2112359550561798,
+      "grad_norm": 0.9237161591864298,
+      "learning_rate": 7.469810166471802e-06,
+      "loss": 0.1065,
+      "step": 270
+    },
+    {
+      "epoch": 1.256179775280899,
+      "grad_norm": 1.107651353273177,
+      "learning_rate": 7.239676794028526e-06,
+      "loss": 0.1022,
+      "step": 280
+    },
+    {
+      "epoch": 1.301123595505618,
+      "grad_norm": 1.0257497864659006,
+      "learning_rate": 7.003445335530572e-06,
+      "loss": 0.1017,
+      "step": 290
+    },
+    {
+      "epoch": 1.346067415730337,
+      "grad_norm": 1.0755740018955657,
+      "learning_rate": 6.761758990821143e-06,
+      "loss": 0.1014,
+      "step": 300
+    },
+    {
+      "epoch": 1.346067415730337,
+      "eval_loss": 0.1469641923904419,
+      "eval_runtime": 18.6999,
+      "eval_samples_per_second": 20.054,
+      "eval_steps_per_second": 2.513,
+      "step": 300
+    },
+    {
+      "epoch": 1.3910112359550562,
+      "grad_norm": 0.8986295695479561,
+      "learning_rate": 6.515275812049644e-06,
+      "loss": 0.1044,
+      "step": 310
+    },
+    {
+      "epoch": 1.4359550561797754,
+      "grad_norm": 1.0576962596864514,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 0.1002,
+      "step": 320
+    },
+    {
+      "epoch": 1.4808988764044944,
+      "grad_norm": 0.9598931209002,
+      "learning_rate": 6.0106146366086514e-06,
+      "loss": 0.1015,
+      "step": 330
+    },
+    {
+      "epoch": 1.5258426966292133,
+      "grad_norm": 0.9245323780224234,
+      "learning_rate": 5.753810707520918e-06,
+      "loss": 0.1004,
+      "step": 340
+    },
+    {
+      "epoch": 1.5707865168539326,
+      "grad_norm": 1.0139214594929302,
+      "learning_rate": 5.494954338288404e-06,
+      "loss": 0.0963,
+      "step": 350
+    },
+    {
+      "epoch": 1.5707865168539326,
+      "eval_loss": 0.13507342338562012,
+      "eval_runtime": 19.582,
+      "eval_samples_per_second": 19.15,
+      "eval_steps_per_second": 2.4,
+      "step": 350
+    },
+    {
+      "epoch": 1.6157303370786518,
+      "grad_norm": 0.8396433223839983,
+      "learning_rate": 5.234750330791268e-06,
+      "loss": 0.0948,
+      "step": 360
+    },
+    {
+      "epoch": 1.6606741573033708,
+      "grad_norm": 0.9854690951634673,
+      "learning_rate": 4.973907156195405e-06,
+      "loss": 0.0965,
+      "step": 370
+    },
+    {
+      "epoch": 1.7056179775280897,
+      "grad_norm": 1.2590587440365115,
+      "learning_rate": 4.713135025960652e-06,
+      "loss": 0.094,
+      "step": 380
+    },
+    {
+      "epoch": 1.750561797752809,
+      "grad_norm": 0.9210276483157858,
+      "learning_rate": 4.4531439581106295e-06,
+      "loss": 0.0918,
+      "step": 390
+    },
+    {
+      "epoch": 1.7955056179775282,
+      "grad_norm": 0.8972026679444467,
+      "learning_rate": 4.194641844029227e-06,
+      "loss": 0.095,
+      "step": 400
+    },
+    {
+      "epoch": 1.7955056179775282,
+      "eval_loss": 0.12670810520648956,
+      "eval_runtime": 18.6817,
+      "eval_samples_per_second": 20.073,
+      "eval_steps_per_second": 2.516,
+      "step": 400
+    },
+    {
+      "epoch": 1.8404494382022472,
+      "grad_norm": 0.8452687128104964,
+      "learning_rate": 3.938332521047434e-06,
+      "loss": 0.086,
+      "step": 410
+    },
+    {
+      "epoch": 1.8853932584269661,
+      "grad_norm": 0.8865269866869628,
+      "learning_rate": 3.6849138560683305e-06,
+      "loss": 0.089,
+      "step": 420
+    },
+    {
+      "epoch": 1.9303370786516854,
+      "grad_norm": 0.829765372515964,
+      "learning_rate": 3.435075845448105e-06,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 1.9752808988764046,
+      "grad_norm": 0.7474037960817976,
+      "learning_rate": 3.189498736306584e-06,
+      "loss": 0.0807,
+      "step": 440
+    },
+    {
+      "epoch": 2.0179775280898875,
+      "grad_norm": 0.7067333924167869,
+      "learning_rate": 2.948851174382565e-06,
+      "loss": 0.0752,
+      "step": 450
+    },
+    {
+      "epoch": 2.0179775280898875,
+      "eval_loss": 0.12405496835708618,
+      "eval_runtime": 18.7264,
+      "eval_samples_per_second": 20.025,
+      "eval_steps_per_second": 2.51,
+      "step": 450
+    },
+    {
+      "epoch": 2.0629213483146067,
+      "grad_norm": 0.8202476842285161,
+      "learning_rate": 2.7137883834768076e-06,
+      "loss": 0.048,
+      "step": 460
+    },
+    {
+      "epoch": 2.107865168539326,
+      "grad_norm": 0.9736246189177716,
+      "learning_rate": 2.4849503814396624e-06,
+      "loss": 0.0464,
+      "step": 470
+    },
+    {
+      "epoch": 2.152808988764045,
+      "grad_norm": 0.9129346237369053,
+      "learning_rate": 2.2629602375607373e-06,
+      "loss": 0.0467,
+      "step": 480
+    },
+    {
+      "epoch": 2.197752808988764,
+      "grad_norm": 0.7375003539675674,
+      "learning_rate": 2.048422376105299e-06,
+      "loss": 0.0438,
+      "step": 490
+    },
+    {
+      "epoch": 2.242696629213483,
+      "grad_norm": 0.8183288973588433,
+      "learning_rate": 1.8419209306164653e-06,
+      "loss": 0.0501,
+      "step": 500
+    },
+    {
+      "epoch": 2.242696629213483,
+      "eval_loss": 0.13637585937976837,
+      "eval_runtime": 18.7063,
+      "eval_samples_per_second": 20.047,
+      "eval_steps_per_second": 2.513,
+      "step": 500
+    },
+    {
+      "epoch": 2.2876404494382023,
+      "grad_norm": 0.7513033540227285,
+      "learning_rate": 1.6440181534640277e-06,
+      "loss": 0.0454,
+      "step": 510
+    },
+    {
+      "epoch": 2.3325842696629215,
+      "grad_norm": 0.752117675634332,
+      "learning_rate": 1.4552528849702852e-06,
+      "loss": 0.047,
+      "step": 520
+    },
+    {
+      "epoch": 2.3775280898876403,
+      "grad_norm": 0.8286936733463574,
+      "learning_rate": 1.2761390862810907e-06,
+      "loss": 0.0446,
+      "step": 530
+    },
+    {
+      "epoch": 2.4224719101123595,
+      "grad_norm": 1.0847844736746832,
+      "learning_rate": 1.107164439976764e-06,
+      "loss": 0.0459,
+      "step": 540
+    },
+    {
+      "epoch": 2.4674157303370787,
+      "grad_norm": 0.8052367339972418,
+      "learning_rate": 9.487890222330137e-07,
+      "loss": 0.0478,
+      "step": 550
+    },
+    {
+      "epoch": 2.4674157303370787,
+      "eval_loss": 0.13764135539531708,
+      "eval_runtime": 18.7694,
+      "eval_samples_per_second": 19.979,
+      "eval_steps_per_second": 2.504,
+      "step": 550
+    },
+    {
+      "epoch": 2.512359550561798,
+      "grad_norm": 0.7113566668412943,
+      "learning_rate": 8.014440501472909e-07,
+      "loss": 0.0447,
+      "step": 560
+    },
+    {
+      "epoch": 2.5573033707865167,
+      "grad_norm": 0.9993646084279955,
+      "learning_rate": 6.655307076412637e-07,
+      "loss": 0.0433,
+      "step": 570
+    },
+    {
+      "epoch": 2.602247191011236,
+      "grad_norm": 1.0223391215385278,
+      "learning_rate": 5.414190531362162e-07,
+      "loss": 0.0426,
+      "step": 580
+    },
+    {
+      "epoch": 2.647191011235955,
+      "grad_norm": 0.7764396483377798,
+      "learning_rate": 4.29447011975474e-07,
+      "loss": 0.0384,
+      "step": 590
+    },
+    {
+      "epoch": 2.692134831460674,
+      "grad_norm": 0.7920135951056039,
+      "learning_rate": 3.299194563372604e-07,
+      "loss": 0.0414,
+      "step": 600
+    },
+    {
+      "epoch": 2.692134831460674,
+      "eval_loss": 0.14047548174858093,
+      "eval_runtime": 19.4086,
+      "eval_samples_per_second": 19.321,
+      "eval_steps_per_second": 2.422,
+      "step": 600
+    },
+    {
+      "epoch": 2.737078651685393,
+      "grad_norm": 0.844557979706594,
+      "learning_rate": 2.431073751431529e-07,
+      "loss": 0.0438,
+      "step": 610
+    },
+    {
+      "epoch": 2.7820224719101123,
+      "grad_norm": 1.1902283704513545,
+      "learning_rate": 1.6924713622225975e-07,
+      "loss": 0.0444,
+      "step": 620
+    },
+    {
+      "epoch": 2.8269662921348315,
+      "grad_norm": 0.8394915583483362,
+      "learning_rate": 1.0853984274007246e-07,
+      "loss": 0.0433,
+      "step": 630
+    },
+    {
+      "epoch": 2.8719101123595507,
+      "grad_norm": 1.1939506828788575,
+      "learning_rate": 6.115078564427946e-08,
+      "loss": 0.0406,
+      "step": 640
+    },
+    {
+      "epoch": 2.9168539325842695,
+      "grad_norm": 0.8563783532916059,
+      "learning_rate": 2.7208993618390578e-08,
+      "loss": 0.0433,
+      "step": 650
+    },
+    {
+      "epoch": 2.9168539325842695,
+      "eval_loss": 0.13943476974964142,
+      "eval_runtime": 18.7133,
+      "eval_samples_per_second": 20.039,
+      "eval_steps_per_second": 2.512,
+      "step": 650
+    },
+    {
+      "epoch": 2.9617977528089887,
+      "grad_norm": 0.9833275155777188,
+      "learning_rate": 6.806881768539053e-09,
+      "loss": 0.0424,
+      "step": 660
+    },
+    {
+      "epoch": 3.0,
+      "step": 669,
+      "total_flos": 75063201300480.0,
+      "train_loss": 0.1622678557318957,
+      "train_runtime": 4543.8481,
+      "train_samples_per_second": 4.701,
+      "train_steps_per_second": 0.147
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 669,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 75063201300480.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3-8b-os-plan-123/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbd46fbfd9a89b3d9c28236108ebbbc55924f7d9e68cc25913206a8c47583eb
+size 8145