初始化项目，由ModelHub XC社区提供模型

Model: laion/nemotron-terminal-system_administration__Qwen3-8B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: nemotron-system-administration__Qwen3-8B
+  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. -->
+
+# nemotron-system-administration__Qwen3-8B
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot/hf_hub/datasets--laion--nemotron-terminal-system_administration/snapshots/05ce499b399d666c5dcbddbebab30415cee2ed15_thinking_preprocessed dataset.
+
+## 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 96
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.9.1+cu130
+- Datasets 4.7.0
+- Tokenizers 0.22.2

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
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 11686.054329563682,
+    "achieved_tflops_per_gpu_theoretical": 291776.50466401974,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.12289686501026154,
+    "mfu_percent": 825.869563926762,
+    "mfu_percent_theoretical": 20620.247679436026,
+    "total_flos": 2.4619618330916946e+18,
+    "train_loss": 0.0,
+    "train_runtime": 6.5836,
+    "train_samples_per_second": 8267.793,
+    "train_steps_per_second": 86.123,
+    "valid_targets_mean": 9991.6,
+    "valid_targets_min": 6280
+}

chat_template.jinja

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

config.json

@@ -0,0 +1,68 @@
+{
+  "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": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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": "4.57.6"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e313edd99b76d7c526c71180c42c8f2682ecb39e4f402c45bb87cd8c3df9d83
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6129a8e2d669222dde7d16822d88e45662df9788c409dcdfc20c18cd5175690
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1f50144d0edf9db45fb7704c104d76813acd75f2b3aa6293315f421b22c4e8
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d2a1710c01586cb721adc6c7ddab311b34b2052d093741376384b4cb2dd324
+size 1580230264

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"
+  }
+}

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": "05ce499b399d666c5dcbddbebab30415cee2ed15_thinking_preprocessed",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "/e/data1/datasets/playground/ot/hf_hub/datasets--laion--nemotron-terminal-system_administration/snapshots/05ce499b399d666c5dcbddbebab30415cee2ed15_thinking_preprocessed",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/nemotron-terminal-system_administration__Qwen3-8B/blob/main/config.json",
+  "wandb_link": null,
+  "traces_location_s3": null
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,12 @@
+{
+    "achieved_tflops_per_gpu": 11686.054329563682,
+    "achieved_tflops_per_gpu_theoretical": 291776.50466401974,
+    "epoch": 7.0,
+    "mfu_percent": 825.869563926762,
+    "mfu_percent_theoretical": 20620.247679436026,
+    "total_flos": 2.4619618330916946e+18,
+    "train_loss": 0.0,
+    "train_runtime": 6.5836,
+    "train_samples_per_second": 8267.793,
+    "train_steps_per_second": 86.123
+}

trainer_log.jsonl

@@ -0,0 +1,119 @@
+{"current_steps": 5, "total_steps": 567, "loss": 0.8393, "lr": 2.8070175438596493e-06, "epoch": 0.06172839506172839, "percentage": 0.88, "elapsed_time": "0:02:13", "remaining_time": "4:10:54"}
+{"current_steps": 10, "total_steps": 567, "loss": 0.7853, "lr": 6.31578947368421e-06, "epoch": 0.12345679012345678, "percentage": 1.76, "elapsed_time": "0:04:25", "remaining_time": "4:06:23"}
+{"current_steps": 15, "total_steps": 567, "loss": 0.7006, "lr": 9.824561403508772e-06, "epoch": 0.18518518518518517, "percentage": 2.65, "elapsed_time": "0:06:28", "remaining_time": "3:58:32"}
+{"current_steps": 20, "total_steps": 567, "loss": 0.6693, "lr": 1.3333333333333333e-05, "epoch": 0.24691358024691357, "percentage": 3.53, "elapsed_time": "0:08:38", "remaining_time": "3:56:33"}
+{"current_steps": 25, "total_steps": 567, "loss": 0.6305, "lr": 1.6842105263157896e-05, "epoch": 0.30864197530864196, "percentage": 4.41, "elapsed_time": "0:10:44", "remaining_time": "3:52:58"}
+{"current_steps": 30, "total_steps": 567, "loss": 0.6038, "lr": 2.035087719298246e-05, "epoch": 0.37037037037037035, "percentage": 5.29, "elapsed_time": "0:12:49", "remaining_time": "3:49:29"}
+{"current_steps": 35, "total_steps": 567, "loss": 0.5804, "lr": 2.385964912280702e-05, "epoch": 0.43209876543209874, "percentage": 6.17, "elapsed_time": "0:14:55", "remaining_time": "3:46:56"}
+{"current_steps": 40, "total_steps": 567, "loss": 0.5557, "lr": 2.7368421052631583e-05, "epoch": 0.49382716049382713, "percentage": 7.05, "elapsed_time": "0:16:56", "remaining_time": "3:43:14"}
+{"current_steps": 45, "total_steps": 567, "loss": 0.5349, "lr": 3.087719298245614e-05, "epoch": 0.5555555555555556, "percentage": 7.94, "elapsed_time": "0:19:02", "remaining_time": "3:40:47"}
+{"current_steps": 50, "total_steps": 567, "loss": 0.5171, "lr": 3.43859649122807e-05, "epoch": 0.6172839506172839, "percentage": 8.82, "elapsed_time": "0:21:08", "remaining_time": "3:38:34"}
+{"current_steps": 55, "total_steps": 567, "loss": 0.5033, "lr": 3.789473684210526e-05, "epoch": 0.6790123456790124, "percentage": 9.7, "elapsed_time": "0:23:16", "remaining_time": "3:36:37"}
+{"current_steps": 60, "total_steps": 567, "loss": 0.4919, "lr": 3.999848220229662e-05, "epoch": 0.7407407407407407, "percentage": 10.58, "elapsed_time": "0:25:25", "remaining_time": "3:34:53"}
+{"current_steps": 65, "total_steps": 567, "loss": 0.479, "lr": 3.998140962368987e-05, "epoch": 0.8024691358024691, "percentage": 11.46, "elapsed_time": "0:27:31", "remaining_time": "3:32:32"}
+{"current_steps": 70, "total_steps": 567, "loss": 0.4669, "lr": 3.994538346771576e-05, "epoch": 0.8641975308641975, "percentage": 12.35, "elapsed_time": "0:29:46", "remaining_time": "3:31:23"}
+{"current_steps": 75, "total_steps": 567, "loss": 0.4607, "lr": 3.989043790736547e-05, "epoch": 0.9259259259259259, "percentage": 13.23, "elapsed_time": "0:31:50", "remaining_time": "3:28:55"}
+{"current_steps": 80, "total_steps": 567, "loss": 0.4539, "lr": 3.9816625061831206e-05, "epoch": 0.9876543209876543, "percentage": 14.11, "elapsed_time": "0:34:00", "remaining_time": "3:26:59"}
+{"current_steps": 85, "total_steps": 567, "loss": 0.4489, "lr": 3.972401494706805e-05, "epoch": 1.0493827160493827, "percentage": 14.99, "elapsed_time": "0:36:10", "remaining_time": "3:25:09"}
+{"current_steps": 90, "total_steps": 567, "loss": 0.4473, "lr": 3.9612695409379555e-05, "epoch": 1.1111111111111112, "percentage": 15.87, "elapsed_time": "0:38:22", "remaining_time": "3:23:25"}
+{"current_steps": 95, "total_steps": 567, "loss": 0.4372, "lr": 3.948277204209021e-05, "epoch": 1.1728395061728394, "percentage": 16.75, "elapsed_time": "0:40:30", "remaining_time": "3:21:16"}
+{"current_steps": 100, "total_steps": 567, "loss": 0.4398, "lr": 3.933436808538375e-05, "epoch": 1.2345679012345678, "percentage": 17.64, "elapsed_time": "0:42:36", "remaining_time": "3:19:00"}
+{"current_steps": 105, "total_steps": 567, "loss": 0.4271, "lr": 3.916762430940245e-05, "epoch": 1.2962962962962963, "percentage": 18.52, "elapsed_time": "0:44:45", "remaining_time": "3:16:54"}
+{"current_steps": 110, "total_steps": 567, "loss": 0.4294, "lr": 3.898269888071803e-05, "epoch": 1.3580246913580247, "percentage": 19.4, "elapsed_time": "0:46:47", "remaining_time": "3:14:21"}
+{"current_steps": 115, "total_steps": 567, "loss": 0.4238, "lr": 3.877976721230114e-05, "epoch": 1.4197530864197532, "percentage": 20.28, "elapsed_time": "0:48:50", "remaining_time": "3:11:56"}
+{"current_steps": 120, "total_steps": 567, "loss": 0.4247, "lr": 3.85590217971315e-05, "epoch": 1.4814814814814814, "percentage": 21.16, "elapsed_time": "0:57:22", "remaining_time": "3:33:41"}
+{"current_steps": 125, "total_steps": 567, "loss": 0.4182, "lr": 3.832067202560668e-05, "epoch": 1.5432098765432098, "percentage": 22.05, "elapsed_time": "0:59:25", "remaining_time": "3:30:06"}
+{"current_steps": 130, "total_steps": 567, "loss": 0.4223, "lr": 3.806494398692258e-05, "epoch": 1.6049382716049383, "percentage": 22.93, "elapsed_time": "1:01:25", "remaining_time": "3:26:28"}
+{"current_steps": 135, "total_steps": 567, "loss": 0.4225, "lr": 3.77920802546142e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "1:03:27", "remaining_time": "3:23:03"}
+{"current_steps": 140, "total_steps": 567, "loss": 0.4182, "lr": 3.750233965645985e-05, "epoch": 1.7283950617283952, "percentage": 24.69, "elapsed_time": "1:05:36", "remaining_time": "3:20:04"}
+{"current_steps": 145, "total_steps": 567, "loss": 0.4163, "lr": 3.719599702896745e-05, "epoch": 1.7901234567901234, "percentage": 25.57, "elapsed_time": "1:07:41", "remaining_time": "3:16:59"}
+{"current_steps": 150, "total_steps": 567, "loss": 0.4135, "lr": 3.687334295667533e-05, "epoch": 1.8518518518518519, "percentage": 26.46, "elapsed_time": "1:09:49", "remaining_time": "3:14:06"}
+{"current_steps": 155, "total_steps": 567, "loss": 0.4082, "lr": 3.653468349651527e-05, "epoch": 1.9135802469135803, "percentage": 27.34, "elapsed_time": "1:11:56", "remaining_time": "3:11:14"}
+{"current_steps": 160, "total_steps": 567, "loss": 0.4116, "lr": 3.6180339887498953e-05, "epoch": 1.9753086419753085, "percentage": 28.22, "elapsed_time": "1:14:00", "remaining_time": "3:08:15"}
+{"current_steps": 165, "total_steps": 567, "loss": 0.4073, "lr": 3.581064824600327e-05, "epoch": 2.037037037037037, "percentage": 29.1, "elapsed_time": "1:16:06", "remaining_time": "3:05:24"}
+{"current_steps": 170, "total_steps": 567, "loss": 0.4006, "lr": 3.542595924694362e-05, "epoch": 2.0987654320987654, "percentage": 29.98, "elapsed_time": "1:18:12", "remaining_time": "3:02:38"}
+{"current_steps": 175, "total_steps": 567, "loss": 0.4057, "lr": 3.502663779113747e-05, "epoch": 2.1604938271604937, "percentage": 30.86, "elapsed_time": "1:20:15", "remaining_time": "2:59:45"}
+{"current_steps": 180, "total_steps": 567, "loss": 0.4005, "lr": 3.4613062659173865e-05, "epoch": 2.2222222222222223, "percentage": 31.75, "elapsed_time": "1:22:17", "remaining_time": "2:56:54"}
+{"current_steps": 185, "total_steps": 567, "loss": 0.3986, "lr": 3.418562615211707e-05, "epoch": 2.2839506172839505, "percentage": 32.63, "elapsed_time": "1:24:11", "remaining_time": "2:53:51"}
+{"current_steps": 190, "total_steps": 567, "loss": 0.4055, "lr": 3.374473371938526e-05, "epoch": 2.3456790123456788, "percentage": 33.51, "elapsed_time": "1:26:14", "remaining_time": "2:51:07"}
+{"current_steps": 195, "total_steps": 567, "loss": 0.4011, "lr": 3.329080357415716e-05, "epoch": 2.4074074074074074, "percentage": 34.39, "elapsed_time": "1:28:24", "remaining_time": "2:48:39"}
+{"current_steps": 200, "total_steps": 567, "loss": 0.4, "lr": 3.282426629667157e-05, "epoch": 2.4691358024691357, "percentage": 35.27, "elapsed_time": "1:30:31", "remaining_time": "2:46:06"}
+{"current_steps": 205, "total_steps": 567, "loss": 0.3963, "lr": 3.234556442579586e-05, "epoch": 2.5308641975308643, "percentage": 36.16, "elapsed_time": "1:32:36", "remaining_time": "2:43:31"}
+{"current_steps": 210, "total_steps": 567, "loss": 0.3911, "lr": 3.18551520392511e-05, "epoch": 2.5925925925925926, "percentage": 37.04, "elapsed_time": "1:34:39", "remaining_time": "2:40:54"}
+{"current_steps": 215, "total_steps": 567, "loss": 0.3967, "lr": 3.1353494322891806e-05, "epoch": 2.6543209876543212, "percentage": 37.92, "elapsed_time": "1:36:40", "remaining_time": "2:38:16"}
+{"current_steps": 220, "total_steps": 567, "loss": 0.3924, "lr": 3.084106712944899e-05, "epoch": 2.7160493827160495, "percentage": 38.8, "elapsed_time": "1:38:54", "remaining_time": "2:36:00"}
+{"current_steps": 225, "total_steps": 567, "loss": 0.3959, "lr": 3.0318356527155024e-05, "epoch": 2.7777777777777777, "percentage": 39.68, "elapsed_time": "1:41:02", "remaining_time": "2:33:34"}
+{"current_steps": 230, "total_steps": 567, "loss": 0.3958, "lr": 2.9785858338678474e-05, "epoch": 2.8395061728395063, "percentage": 40.56, "elapsed_time": "1:43:00", "remaining_time": "2:30:56"}
+{"current_steps": 235, "total_steps": 567, "loss": 0.3952, "lr": 2.924407767080627e-05, "epoch": 2.9012345679012346, "percentage": 41.45, "elapsed_time": "1:45:08", "remaining_time": "2:28:31"}
+{"current_steps": 240, "total_steps": 567, "loss": 0.3927, "lr": 2.8693528435319304e-05, "epoch": 2.962962962962963, "percentage": 42.33, "elapsed_time": "1:47:13", "remaining_time": "2:26:05"}
+{"current_steps": 245, "total_steps": 567, "loss": 0.3877, "lr": 2.813473286151601e-05, "epoch": 3.0246913580246915, "percentage": 43.21, "elapsed_time": "1:49:20", "remaining_time": "2:23:42"}
+{"current_steps": 250, "total_steps": 567, "loss": 0.3882, "lr": 2.756822100084621e-05, "epoch": 3.0864197530864197, "percentage": 44.09, "elapsed_time": "1:51:25", "remaining_time": "2:21:17"}
+{"current_steps": 255, "total_steps": 567, "loss": 0.3876, "lr": 2.6994530224125225e-05, "epoch": 3.148148148148148, "percentage": 44.97, "elapsed_time": "1:53:41", "remaining_time": "2:19:06"}
+{"current_steps": 260, "total_steps": 567, "loss": 0.3827, "lr": 2.6414204711805106e-05, "epoch": 3.2098765432098766, "percentage": 45.86, "elapsed_time": "1:55:44", "remaining_time": "2:16:39"}
+{"current_steps": 265, "total_steps": 567, "loss": 0.3896, "lr": 2.5827794937786497e-05, "epoch": 3.271604938271605, "percentage": 46.74, "elapsed_time": "1:57:42", "remaining_time": "2:14:08"}
+{"current_steps": 270, "total_steps": 567, "loss": 0.3879, "lr": 2.523585714726081e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "1:59:45", "remaining_time": "2:11:44"}
+{"current_steps": 275, "total_steps": 567, "loss": 0.3823, "lr": 2.4638952829077964e-05, "epoch": 3.3950617283950617, "percentage": 48.5, "elapsed_time": "2:01:51", "remaining_time": "2:09:23"}
+{"current_steps": 280, "total_steps": 567, "loss": 0.3813, "lr": 2.4037648183140205e-05, "epoch": 3.45679012345679, "percentage": 49.38, "elapsed_time": "2:03:54", "remaining_time": "2:06:59"}
+{"current_steps": 285, "total_steps": 567, "loss": 0.3789, "lr": 2.3432513583327198e-05, "epoch": 3.5185185185185186, "percentage": 50.26, "elapsed_time": "2:05:55", "remaining_time": "2:04:36"}
+{"current_steps": 290, "total_steps": 567, "loss": 0.3824, "lr": 2.282412303646183e-05, "epoch": 3.580246913580247, "percentage": 51.15, "elapsed_time": "2:08:07", "remaining_time": "2:02:22"}
+{"current_steps": 295, "total_steps": 567, "loss": 0.3827, "lr": 2.2213053637830016e-05, "epoch": 3.6419753086419755, "percentage": 52.03, "elapsed_time": "2:10:19", "remaining_time": "2:00:10"}
+{"current_steps": 300, "total_steps": 567, "loss": 0.3791, "lr": 2.1599885023770833e-05, "epoch": 3.7037037037037037, "percentage": 52.91, "elapsed_time": "2:12:32", "remaining_time": "1:57:57"}
+{"current_steps": 305, "total_steps": 567, "loss": 0.3835, "lr": 2.098519882185634e-05, "epoch": 3.765432098765432, "percentage": 53.79, "elapsed_time": "2:14:43", "remaining_time": "1:55:43"}
+{"current_steps": 310, "total_steps": 567, "loss": 0.3793, "lr": 2.03695780991826e-05, "epoch": 3.8271604938271606, "percentage": 54.67, "elapsed_time": "2:16:45", "remaining_time": "1:53:22"}
+{"current_steps": 315, "total_steps": 567, "loss": 0.3817, "lr": 1.9753606809295234e-05, "epoch": 3.888888888888889, "percentage": 55.56, "elapsed_time": "2:18:48", "remaining_time": "1:51:02"}
+{"current_steps": 320, "total_steps": 567, "loss": 0.3867, "lr": 1.9137869238274095e-05, "epoch": 3.950617283950617, "percentage": 56.44, "elapsed_time": "2:20:50", "remaining_time": "1:48:42"}
+{"current_steps": 325, "total_steps": 567, "loss": 0.385, "lr": 1.8522949450502522e-05, "epoch": 4.012345679012346, "percentage": 57.32, "elapsed_time": "2:22:51", "remaining_time": "1:46:22"}
+{"current_steps": 330, "total_steps": 567, "loss": 0.3755, "lr": 1.7909430734646936e-05, "epoch": 4.074074074074074, "percentage": 58.2, "elapsed_time": "2:24:48", "remaining_time": "1:43:59"}
+{"current_steps": 335, "total_steps": 567, "loss": 0.3783, "lr": 1.7297895050372147e-05, "epoch": 4.135802469135802, "percentage": 59.08, "elapsed_time": "2:26:53", "remaining_time": "1:41:43"}
+{"current_steps": 340, "total_steps": 567, "loss": 0.3786, "lr": 1.66889224763174e-05, "epoch": 4.197530864197531, "percentage": 59.96, "elapsed_time": "2:28:56", "remaining_time": "1:39:26"}
+{"current_steps": 345, "total_steps": 567, "loss": 0.3769, "lr": 1.6083090659856665e-05, "epoch": 4.2592592592592595, "percentage": 60.85, "elapsed_time": "2:31:07", "remaining_time": "1:37:14"}
+{"current_steps": 350, "total_steps": 567, "loss": 0.3765, "lr": 1.5480974269165053e-05, "epoch": 4.320987654320987, "percentage": 61.73, "elapsed_time": "2:33:14", "remaining_time": "1:35:00"}
+{"current_steps": 355, "total_steps": 567, "loss": 0.3756, "lr": 1.4883144448111288e-05, "epoch": 4.382716049382716, "percentage": 62.61, "elapsed_time": "2:35:19", "remaining_time": "1:32:45"}
+{"current_steps": 360, "total_steps": 567, "loss": 0.3743, "lr": 1.4290168274493161e-05, "epoch": 4.444444444444445, "percentage": 63.49, "elapsed_time": "2:37:25", "remaining_time": "1:30:31"}
+{"current_steps": 365, "total_steps": 567, "loss": 0.3785, "lr": 1.3702608222129845e-05, "epoch": 4.506172839506172, "percentage": 64.37, "elapsed_time": "2:39:28", "remaining_time": "1:28:15"}
+{"current_steps": 370, "total_steps": 567, "loss": 0.3762, "lr": 1.3121021627321438e-05, "epoch": 4.567901234567901, "percentage": 65.26, "elapsed_time": "2:41:32", "remaining_time": "1:26:00"}
+{"current_steps": 375, "total_steps": 567, "loss": 0.3718, "lr": 1.254596016018172e-05, "epoch": 4.62962962962963, "percentage": 66.14, "elapsed_time": "2:43:38", "remaining_time": "1:23:47"}
+{"current_steps": 380, "total_steps": 567, "loss": 0.3741, "lr": 1.1977969301345627e-05, "epoch": 4.6913580246913575, "percentage": 67.02, "elapsed_time": "2:45:45", "remaining_time": "1:21:34"}
+{"current_steps": 385, "total_steps": 567, "loss": 0.3756, "lr": 1.1417587824547822e-05, "epoch": 4.753086419753086, "percentage": 67.9, "elapsed_time": "2:47:50", "remaining_time": "1:19:20"}
+{"current_steps": 390, "total_steps": 567, "loss": 0.3701, "lr": 1.086534728556319e-05, "epoch": 4.814814814814815, "percentage": 68.78, "elapsed_time": "2:49:50", "remaining_time": "1:17:04"}
+{"current_steps": 395, "total_steps": 567, "loss": 0.3723, "lr": 1.032177151799397e-05, "epoch": 4.8765432098765435, "percentage": 69.66, "elapsed_time": "2:51:51", "remaining_time": "1:14:50"}
+{"current_steps": 400, "total_steps": 567, "loss": 0.3801, "lr": 9.787376136381866e-06, "epoch": 4.938271604938271, "percentage": 70.55, "elapsed_time": "2:53:53", "remaining_time": "1:12:36"}
+{"current_steps": 405, "total_steps": 567, "loss": 0.3742, "lr": 9.262668047116399e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "2:55:56", "remaining_time": "1:10:22"}
+{"current_steps": 410, "total_steps": 567, "loss": 0.3748, "lr": 8.748144967603538e-06, "epoch": 5.061728395061729, "percentage": 72.31, "elapsed_time": "2:58:00", "remaining_time": "1:08:10"}
+{"current_steps": 415, "total_steps": 567, "loss": 0.3701, "lr": 8.24429495415054e-06, "epoch": 5.1234567901234565, "percentage": 73.19, "elapsed_time": "3:00:05", "remaining_time": "1:05:57"}
+{"current_steps": 420, "total_steps": 567, "loss": 0.3648, "lr": 7.751595939015005e-06, "epoch": 5.185185185185185, "percentage": 74.07, "elapsed_time": "3:02:03", "remaining_time": "1:03:43"}
+{"current_steps": 425, "total_steps": 567, "loss": 0.3704, "lr": 7.270515277057178e-06, "epoch": 5.246913580246914, "percentage": 74.96, "elapsed_time": "3:04:12", "remaining_time": "1:01:32"}
+{"current_steps": 430, "total_steps": 567, "loss": 0.3728, "lr": 6.801509302425553e-06, "epoch": 5.308641975308642, "percentage": 75.84, "elapsed_time": "3:06:22", "remaining_time": "0:59:22"}
+{"current_steps": 435, "total_steps": 567, "loss": 0.3697, "lr": 6.3450228956962915e-06, "epoch": 5.37037037037037, "percentage": 76.72, "elapsed_time": "3:08:23", "remaining_time": "0:57:10"}
+{"current_steps": 440, "total_steps": 567, "loss": 0.3716, "lr": 5.90148906187706e-06, "epoch": 5.432098765432099, "percentage": 77.6, "elapsed_time": "3:10:25", "remaining_time": "0:54:57"}
+{"current_steps": 445, "total_steps": 567, "loss": 0.3706, "lr": 5.471328519675521e-06, "epoch": 5.493827160493828, "percentage": 78.48, "elapsed_time": "3:12:26", "remaining_time": "0:52:45"}
+{"current_steps": 450, "total_steps": 567, "loss": 0.374, "lr": 5.054949302422178e-06, "epoch": 5.555555555555555, "percentage": 79.37, "elapsed_time": "3:14:25", "remaining_time": "0:50:32"}
+{"current_steps": 455, "total_steps": 567, "loss": 0.37, "lr": 4.65274637102606e-06, "epoch": 5.617283950617284, "percentage": 80.25, "elapsed_time": "3:16:25", "remaining_time": "0:48:21"}
+{"current_steps": 460, "total_steps": 567, "loss": 0.3692, "lr": 4.265101239330336e-06, "epoch": 5.679012345679013, "percentage": 81.13, "elapsed_time": "3:18:30", "remaining_time": "0:46:10"}
+{"current_steps": 465, "total_steps": 567, "loss": 0.3731, "lr": 3.892381612223348e-06, "epoch": 5.7407407407407405, "percentage": 82.01, "elapsed_time": "3:20:37", "remaining_time": "0:44:00"}
+{"current_steps": 470, "total_steps": 567, "loss": 0.3697, "lr": 3.534941036848258e-06, "epoch": 5.802469135802469, "percentage": 82.89, "elapsed_time": "3:22:41", "remaining_time": "0:41:50"}
+{"current_steps": 475, "total_steps": 567, "loss": 0.3717, "lr": 3.193118567242148e-06, "epoch": 5.864197530864198, "percentage": 83.77, "elapsed_time": "3:24:48", "remaining_time": "0:39:40"}
+{"current_steps": 480, "total_steps": 567, "loss": 0.3728, "lr": 2.8672384427227484e-06, "epoch": 5.925925925925926, "percentage": 84.66, "elapsed_time": "3:26:51", "remaining_time": "0:37:29"}
+{"current_steps": 485, "total_steps": 567, "loss": 0.3705, "lr": 2.5576097803277833e-06, "epoch": 5.987654320987654, "percentage": 85.54, "elapsed_time": "3:28:54", "remaining_time": "0:35:19"}
+{"current_steps": 490, "total_steps": 567, "loss": 0.3731, "lr": 2.264526281598762e-06, "epoch": 6.049382716049383, "percentage": 86.42, "elapsed_time": "3:30:56", "remaining_time": "0:33:08"}
+{"current_steps": 495, "total_steps": 567, "loss": 0.3719, "lr": 1.988265953987254e-06, "epoch": 6.111111111111111, "percentage": 87.3, "elapsed_time": "3:32:59", "remaining_time": "0:30:58"}
+{"current_steps": 500, "total_steps": 567, "loss": 0.3697, "lr": 1.7290908471479805e-06, "epoch": 6.172839506172839, "percentage": 88.18, "elapsed_time": "3:35:05", "remaining_time": "0:28:49"}
+{"current_steps": 505, "total_steps": 567, "loss": 0.3665, "lr": 1.487246804368876e-06, "epoch": 6.234567901234568, "percentage": 89.07, "elapsed_time": "3:37:09", "remaining_time": "0:26:39"}
+{"current_steps": 510, "total_steps": 567, "loss": 0.3707, "lr": 1.2629632293737903e-06, "epoch": 6.296296296296296, "percentage": 89.95, "elapsed_time": "3:39:10", "remaining_time": "0:24:29"}
+{"current_steps": 515, "total_steps": 567, "loss": 0.3745, "lr": 1.0564528687191954e-06, "epoch": 6.3580246913580245, "percentage": 90.83, "elapsed_time": "3:41:17", "remaining_time": "0:22:20"}
+{"current_steps": 520, "total_steps": 567, "loss": 0.3682, "lr": 8.679116099911855e-07, "epoch": 6.419753086419753, "percentage": 91.71, "elapsed_time": "3:43:23", "remaining_time": "0:20:11"}
+{"current_steps": 525, "total_steps": 567, "loss": 0.3647, "lr": 6.975182959942195e-07, "epoch": 6.481481481481482, "percentage": 92.59, "elapsed_time": "3:45:26", "remaining_time": "0:18:02"}
+{"current_steps": 530, "total_steps": 567, "loss": 0.371, "lr": 5.454345551079044e-07, "epoch": 6.54320987654321, "percentage": 93.47, "elapsed_time": "3:47:32", "remaining_time": "0:15:53"}
+{"current_steps": 535, "total_steps": 567, "loss": 0.3693, "lr": 4.118046479726823e-07, "epoch": 6.604938271604938, "percentage": 94.36, "elapsed_time": "3:49:28", "remaining_time": "0:13:43"}
+{"current_steps": 540, "total_steps": 567, "loss": 0.3699, "lr": 2.9675533064986937e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "3:51:36", "remaining_time": "0:11:34"}
+{"current_steps": 545, "total_steps": 567, "loss": 0.3682, "lr": 2.0039573438586091e-07, "epoch": 6.728395061728395, "percentage": 96.12, "elapsed_time": "3:53:46", "remaining_time": "0:09:26"}
+{"current_steps": 550, "total_steps": 567, "loss": 0.3704, "lr": 1.2281726209452782e-07, "epoch": 6.790123456790123, "percentage": 97.0, "elapsed_time": "3:55:52", "remaining_time": "0:07:17"}
+{"current_steps": 555, "total_steps": 567, "loss": 0.3645, "lr": 6.409350165601957e-08, "epoch": 6.851851851851852, "percentage": 97.88, "elapsed_time": "3:57:51", "remaining_time": "0:05:08"}
+{"current_steps": 560, "total_steps": 567, "loss": 0.3741, "lr": 2.4280156114202537e-08, "epoch": 6.91358024691358, "percentage": 98.77, "elapsed_time": "3:59:54", "remaining_time": "0:02:59"}
+{"current_steps": 565, "total_steps": 567, "loss": 0.3617, "lr": 3.414990838945809e-09, "epoch": 6.9753086419753085, "percentage": 99.65, "elapsed_time": "4:01:58", "remaining_time": "0:00:51"}
+{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:02:56", "remaining_time": "0:00:00"}
+{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509ed34c4da12bd514fb08fbfadfc310a54c1e12f3a05674df415f391701acc4
+size 8721