saketh1201/Qwen3-4B-Inventory-SFT
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: saketh1201/Qwen3-4B-Inventory-SFT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 12:05:07 +08:00
commit 3800042b5c
21 changed files with 2076 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.gitattributes vendored Normal file
View File

@@ -0,0 +1,38 @@
*.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
sft_data_rewards.png filter=lfs diff=lfs merge=lfs -text
sft_training_dashboard.png filter=lfs diff=lfs merge=lfs -text

21
README.md Normal file
View File

@@ -0,0 +1,21 @@
---
base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** saketh1201
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

86
chat_template.jinja Normal file
View File

@@ -0,0 +1,86 @@
{%- 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' }}
{%- endif %}

52
checkpoint-64/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "Qwen3ForCausalLM",
"parent_library": "transformers.models.qwen3.modeling_qwen3",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 32,
"lora_bias": false,
"lora_dropout": 0.0,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"k_proj",
"v_proj",
"gate_proj",
"o_proj",
"down_proj",
"q_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-64/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
size 11423114

233
checkpoint-64/tokenizer_config.json Normal file
View File

@@ -0,0 +1,233 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": false,
"model_max_length": 262144,
"pad_token": "<|PAD_TOKEN|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151667": {
"content": "<think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151668": {
"content": "</think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151669": {
"content": "<|PAD_TOKEN|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
}
}

118
checkpoint-64/trainer_state.json Normal file
View File

@@ -0,0 +1,118 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 64,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15625,
"grad_norm": 1.1824947595596313,
"learning_rate": 8e-05,
"loss": 2.1224836349487304,
"step": 5
},
{
"epoch": 0.3125,
"grad_norm": 0.45979633927345276,
"learning_rate": 9.952402219937816e-05,
"loss": 1.7379152297973632,
"step": 10
},
{
"epoch": 0.46875,
"grad_norm": 0.5583250522613525,
"learning_rate": 9.760588329553571e-05,
"loss": 1.5223669052124023,
"step": 15
},
{
"epoch": 0.625,
"grad_norm": 0.4054713845252991,
"learning_rate": 9.42728012826605e-05,
"loss": 1.2529266357421875,
"step": 20
},
{
"epoch": 0.78125,
"grad_norm": 0.41235220432281494,
"learning_rate": 8.962384209755452e-05,
"loss": 1.0075555801391602,
"step": 25
},
{
"epoch": 0.9375,
"grad_norm": 0.4131007790565491,
"learning_rate": 8.379718220723773e-05,
"loss": 0.7767543792724609,
"step": 30
},
{
"epoch": 1.09375,
"grad_norm": 0.28115367889404297,
"learning_rate": 7.696600172495997e-05,
"loss": 0.670633602142334,
"step": 35
},
{
"epoch": 1.25,
"grad_norm": 0.25491470098495483,
"learning_rate": 6.933333714707094e-05,
"loss": 0.6005853176116943,
"step": 40
},
{
"epoch": 1.40625,
"grad_norm": 0.2761740982532501,
"learning_rate": 6.112604669781572e-05,
"loss": 0.5778088092803955,
"step": 45
},
{
"epoch": 1.5625,
"grad_norm": 0.24875779449939728,
"learning_rate": 5.258806764421048e-05,
"loss": 0.538189172744751,
"step": 50
},
{
"epoch": 1.71875,
"grad_norm": 0.25878462195396423,
"learning_rate": 4.397316598723385e-05,
"loss": 0.5227806568145752,
"step": 55
},
{
"epoch": 1.875,
"grad_norm": 0.32230958342552185,
"learning_rate": 3.553739402317162e-05,
"loss": 0.5064546585083007,
"step": 60
}
],
"logging_steps": 5,
"max_steps": 96,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.659128844566528e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

52
checkpoint-96/adapter_config.json Normal file
View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "Qwen3ForCausalLM",
"parent_library": "transformers.models.qwen3.modeling_qwen3",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 32,
"lora_bias": false,
"lora_dropout": 0.0,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"k_proj",
"v_proj",
"gate_proj",
"o_proj",
"down_proj",
"q_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-96/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
size 11423114

233
checkpoint-96/tokenizer_config.json Normal file
View File

@@ -0,0 +1,233 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": false,
"model_max_length": 262144,
"pad_token": "<|PAD_TOKEN|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151667": {
"content": "<think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151668": {
"content": "</think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151669": {
"content": "<|PAD_TOKEN|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
}
}

167
checkpoint-96/trainer_state.json Normal file
View File

@@ -0,0 +1,167 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 96,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15625,
"grad_norm": 1.1824947595596313,
"learning_rate": 8e-05,
"loss": 2.1224836349487304,
"step": 5
},
{
"epoch": 0.3125,
"grad_norm": 0.45979633927345276,
"learning_rate": 9.952402219937816e-05,
"loss": 1.7379152297973632,
"step": 10
},
{
"epoch": 0.46875,
"grad_norm": 0.5583250522613525,
"learning_rate": 9.760588329553571e-05,
"loss": 1.5223669052124023,
"step": 15
},
{
"epoch": 0.625,
"grad_norm": 0.4054713845252991,
"learning_rate": 9.42728012826605e-05,
"loss": 1.2529266357421875,
"step": 20
},
{
"epoch": 0.78125,
"grad_norm": 0.41235220432281494,
"learning_rate": 8.962384209755452e-05,
"loss": 1.0075555801391602,
"step": 25
},
{
"epoch": 0.9375,
"grad_norm": 0.4131007790565491,
"learning_rate": 8.379718220723773e-05,
"loss": 0.7767543792724609,
"step": 30
},
{
"epoch": 1.09375,
"grad_norm": 0.28115367889404297,
"learning_rate": 7.696600172495997e-05,
"loss": 0.670633602142334,
"step": 35
},
{
"epoch": 1.25,
"grad_norm": 0.25491470098495483,
"learning_rate": 6.933333714707094e-05,
"loss": 0.6005853176116943,
"step": 40
},
{
"epoch": 1.40625,
"grad_norm": 0.2761740982532501,
"learning_rate": 6.112604669781572e-05,
"loss": 0.5778088092803955,
"step": 45
},
{
"epoch": 1.5625,
"grad_norm": 0.24875779449939728,
"learning_rate": 5.258806764421048e-05,
"loss": 0.538189172744751,
"step": 50
},
{
"epoch": 1.71875,
"grad_norm": 0.25878462195396423,
"learning_rate": 4.397316598723385e-05,
"loss": 0.5227806568145752,
"step": 55
},
{
"epoch": 1.875,
"grad_norm": 0.32230958342552185,
"learning_rate": 3.553739402317162e-05,
"loss": 0.5064546585083007,
"step": 60
},
{
"epoch": 2.03125,
"grad_norm": 0.3282443583011627,
"learning_rate": 2.7531479951641924e-05,
"loss": 0.5330670356750489,
"step": 65
},
{
"epoch": 2.1875,
"grad_norm": 0.2622469663619995,
"learning_rate": 2.0193375726538737e-05,
"loss": 0.4886016368865967,
"step": 70
},
{
"epoch": 2.34375,
"grad_norm": 0.27460813522338867,
"learning_rate": 1.3741184642831189e-05,
"loss": 0.4667336463928223,
"step": 75
},
{
"epoch": 2.5,
"grad_norm": 0.2819143831729889,
"learning_rate": 8.366678865639688e-06,
"loss": 0.4716463088989258,
"step": 80
},
{
"epoch": 2.65625,
"grad_norm": 0.260720431804657,
"learning_rate": 4.229599573731685e-06,
"loss": 0.46319150924682617,
"step": 85
},
{
"epoch": 2.8125,
"grad_norm": 0.29859086871147156,
"learning_rate": 1.4529091286973995e-06,
"loss": 0.47528905868530275,
"step": 90
},
{
"epoch": 2.96875,
"grad_norm": 0.42338818311691284,
"learning_rate": 1.191363849376237e-07,
"loss": 0.4699601173400879,
"step": 95
}
],
"logging_steps": 5,
"max_steps": 96,
"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": 3.988693266849792e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

72
config.json Normal file
View File

@@ -0,0 +1,72 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"torch_dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"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": 262144,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151669,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 5000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"unsloth_fixed": true,
"unsloth_version": "2026.4.8",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

256
data/data/sft_data.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3232a39eaa020df7b15da6790f627a90020a79d9b8578a358f5f8eaf1078507
size 4967215360

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d97e7f55f9ec344604bee85412dac0ded833dccc1d8a374fd9e0bc7819f5c23
size 3077766632

406
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,406 @@
{
"metadata": {
"total_parameters": 4022468096,
"total_size": 8044936192
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors"
}
}

3
sft_data_rewards.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1fa6f2ea4de530a4f6faa24e490bf8bc4b84c05eec7ea71edf64bcb22fa5ff5b
size 161219

3
sft_training_dashboard.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ce8c02074858c1968a4675b94773132b10982317c3894ce79f00d83d8760fe7
size 147979

88
sft_training_log.json Normal file
View File

@@ -0,0 +1,88 @@
{
"steps": [
5,
10,
15,
20,
25,
30,
35,
40,
45,
50,
55,
60,
65,
70,
75,
80,
85,
90,
95
],
"losses": [
2.1224836349487304,
1.7379152297973632,
1.5223669052124023,
1.2529266357421875,
1.0075555801391602,
0.7767543792724609,
0.670633602142334,
0.6005853176116943,
0.5778088092803955,
0.538189172744751,
0.5227806568145752,
0.5064546585083007,
0.5330670356750489,
0.4886016368865967,
0.4667336463928223,
0.4716463088989258,
0.46319150924682617,
0.47528905868530275,
0.4699601173400879
],
"lr_steps": [
5,
10,
15,
20,
25,
30,
35,
40,
45,
50,
55,
60,
65,
70,
75,
80,
85,
90,
95
],
"lrs": [
8e-05,
9.952402219937816e-05,
9.760588329553571e-05,
9.42728012826605e-05,
8.962384209755452e-05,
8.379718220723773e-05,
7.696600172495997e-05,
6.933333714707094e-05,
6.112604669781572e-05,
5.258806764421048e-05,
4.397316598723385e-05,
3.553739402317162e-05,
2.7531479951641924e-05,
2.0193375726538737e-05,
1.3741184642831189e-05,
8.366678865639688e-06,
4.229599573731685e-06,
1.4529091286973995e-06,
1.191363849376237e-07
],
"eval_steps": [],
"eval_losses": []
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
size 11423114

233
tokenizer_config.json Normal file
View File

@@ -0,0 +1,233 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": false,
"model_max_length": 262144,
"pad_token": "<|PAD_TOKEN|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151667": {
"content": "<think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151668": {
"content": "</think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151669": {
"content": "<|PAD_TOKEN|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
}
}