lldois/v48_v29_clean_fused_lr45e7_ep040
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: lldois/v48_v29_clean_fused_lr45e7_ep040
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-03 15:11:19 +08:00
commit 44005dff9b
17 changed files with 2747 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -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

58
README.md Normal file
View File

@@ -0,0 +1,58 @@
---
library_name: transformers
license: other
base_model: lldois/v29_v19_user_world_guard_lr8e7_ep018
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: v48_v29_clean_fused_lr45e7_ep040
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. -->
# v48_v29_clean_fused_lr45e7_ep040
This model is a fine-tuned version of [lldois/v29_v19_user_world_guard_lr8e7_ep018](https://huggingface.co/lldois/v29_v19_user_world_guard_lr8e7_ep018) on the exp_v48_clean_fused 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: 4.5e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607198
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 0.4
### Training results
### Framework versions
- Transformers 5.6.0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 0.40634920634920635,
"total_flos": 1.5185329017526272e+16,
"train_loss": 2.147665500640869,
"train_runtime": 258.8642,
"train_samples_per_second": 0.487,
"train_steps_per_second": 0.124
}

89
chat_template.jinja Normal file
View File

@@ -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 %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.6.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 176253
}

121
experiment_recipe.json Normal file
View File

@@ -0,0 +1,121 @@
{
"created_at": "2026-07-16 01:45:38",
"name": "v48_v29_clean_fused_lr45e7_ep040",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v48_clean_fused",
"dataset_manifest": {
"name": "v48_clean_fused",
"path": "/home/ll/llm4rec/experiments/data/v48_clean_fused.jsonl",
"records": 11600,
"bytes": 45339493,
"sha256": "d080d8786abbd5f20116c97bfee6d8d073bcecb38143880985452fe0fe503af2",
"requested_components": {
"general_cn_direct": 800,
"general_cn_think": 400,
"general_other_direct": 800,
"general_other_think": 400,
"r0_ground_direct": 1000,
"r0_caption_direct": 400,
"r0_caption_think": 250,
"r3_balanced_ad_direct": 600,
"r3_balanced_ad_think": 200,
"r3_balanced_live_direct": 400,
"r3_balanced_live_think": 500,
"r3_balanced_goods_direct": 250,
"r3_balanced_goods_think": 500,
"r3_balanced_video_direct": 550,
"r3_balanced_video_think": 600,
"old_rec_live_direct": 250,
"old_rec_live_think": 100,
"old_rec_ad_direct": 250,
"old_rec_ad_think": 100,
"old_rec_goods_direct": 250,
"old_rec_goods_think": 100,
"old_rec_video_direct": 250,
"old_rec_video_think": 150,
"old_user_array_direct": 450,
"old_user_logic_direct": 400,
"old_user_logic_think": 150,
"old_item_goods_direct": 300,
"old_item_goods_think": 75,
"old_item_live_direct": 300,
"old_item_live_think": 75,
"old_item_ad_direct": 300,
"old_item_ad_think": 75,
"old_item_video_direct": 300,
"old_item_video_think": 75
},
"groups": {
"old_user_clean": 1000,
"r0_clean": 1650,
"general_clean": 2400,
"r3_clean": 3600,
"old_rec_clean": 1450,
"old_item_clean": 1500
},
"variants": {
"old_user_logic_direct": 400,
"caption_to_sid_collision_free": 1000,
"strict_single_turn_direct": 1600,
"strict_ad_direct": 600,
"old_rec_video_cot": 150,
"old_rec_live_direct": 250,
"sid_to_caption_grounded_cot": 250,
"old_rec_video_direct": 250,
"old_rec_goods_direct": 250,
"strict_goods_cot": 500,
"old_item_ad_direct": 300,
"old_user_logic_cot": 150,
"strict_goods_direct": 250,
"strict_single_turn_cot": 800,
"sid_to_caption_direct": 400,
"old_item_goods_direct": 300,
"strict_video_cot": 600,
"old_rec_ad_direct": 250,
"strict_live_direct": 400,
"old_item_video_direct": 300,
"strict_live_cot": 500,
"old_item_live_cot": 75,
"old_item_live_direct": 300,
"old_rec_ad_cot": 100,
"old_user_array_direct": 450,
"old_rec_goods_cot": 100,
"old_rec_live_cot": 100,
"strict_ad_cot": 200,
"strict_video_direct": 550,
"old_item_goods_cot": 75,
"old_item_ad_cot": 75,
"old_item_video_cot": 75
},
"routes": {
"no_think": 7850,
"think": 3750
},
"domains": {
"ad": 1654,
"goods": 2148,
"video": 2764,
"live": 1634
},
"canonical_duplicates": 0,
"output_chars_p50": 190,
"output_chars_p90": 1219,
"seed": 202607255
},
"learning_rate": "4.5e-7",
"epochs": 0.4,
"stages": null,
"note": "Fused high-confidence candidate combining clean general, collision-free R0, domain-aware strict R3, and deduplicated original-task guards.",
"cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
"checkpoint_policy": "save_strategy=no; only the final model is retained.",
"script": "/home/ll/llm4rec/experiments/run_experiments.py",
"script_sha256": "78d5f1619c271f19b4204ff4fa210ff4bbbadd81cdc0221e5f40cee201fc9877",
"data_builder": "/home/ll/llm4rec/experiments/source_data.py",
"data_builder_sha256": "a689f0bf36e31f612c3800f971501655b403e38420f4aad9116a3110206a1d5c",
"data_cleaner": "/home/ll/llm4rec/experiments/clean_data.py",
"data_cleaner_sha256": "c1831a3d85c86c740ba80e095252574495b06d79d6341ed190ac2e3fe67133bf",
"configs": [
"/home/ll/llm4rec/experiments/configs/v48_v29_clean_fused_lr45e7_ep040.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_experiments.py --single v48_v29_clean_fused_lr45e7_ep040 --gpu <gpu>"
}

12
generation_config.json Normal file
View File

@@ -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": "5.6.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a709f22f79252afcab9743fc9baaa837abd320e337c86ec90e6f202aa36371a8
size 1602902832

3
runs/Jul16_01-40-00_ubuntu-System-Product-Name/events.out.tfevents.1784137200.ubuntu-System-Product-Name.1409680.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8240b160f9c015e84bc0a8e295e9e1d23b15d301646c6a6d928f4e62972d1cd
size 6919

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
size 16016554

16
tokenizer_config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": true,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

2256
train.log Normal file
View File

File diff suppressed because one or more lines are too long

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 0.40634920634920635,
"total_flos": 1.5185329017526272e+16,
"train_loss": 2.147665500640869,
"train_runtime": 258.8642,
"train_samples_per_second": 0.487,
"train_steps_per_second": 0.124
}

4
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,4 @@
{"current_steps": 10, "total_steps": 32, "loss": 2.188013458251953, "lr": 3.800175567920295e-07, "epoch": 0.12698412698412698, "percentage": 31.25, "elapsed_time": "0:01:19", "remaining_time": "0:02:54"}
{"current_steps": 20, "total_steps": 32, "loss": 2.155006980895996, "lr": 1.6860318024178784e-07, "epoch": 0.25396825396825395, "percentage": 62.5, "elapsed_time": "0:02:41", "remaining_time": "0:01:37"}
{"current_steps": 30, "total_steps": 32, "loss": 2.011971282958984, "lr": 1.0318667309989016e-08, "epoch": 0.38095238095238093, "percentage": 93.75, "elapsed_time": "0:04:02", "remaining_time": "0:00:16"}
{"current_steps": 32, "total_steps": 32, "epoch": 0.40634920634920635, "percentage": 100.0, "elapsed_time": "0:04:18", "remaining_time": "0:00:00"}

64
trainer_state.json Normal file
View File

@@ -0,0 +1,64 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.40634920634920635,
"eval_steps": 500,
"global_step": 32,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12698412698412698,
"grad_norm": 11.0625,
"learning_rate": 3.800175567920295e-07,
"loss": 2.188013458251953,
"step": 10
},
{
"epoch": 0.25396825396825395,
"grad_norm": 11.1875,
"learning_rate": 1.6860318024178784e-07,
"loss": 2.155006980895996,
"step": 20
},
{
"epoch": 0.38095238095238093,
"grad_norm": 13.4375,
"learning_rate": 1.0318667309989016e-08,
"loss": 2.011971282958984,
"step": 30
},
{
"epoch": 0.40634920634920635,
"step": 32,
"total_flos": 1.5185329017526272e+16,
"train_loss": 2.147665500640869,
"train_runtime": 258.8642,
"train_samples_per_second": 0.487,
"train_steps_per_second": 0.124
}
],
"logging_steps": 10,
"max_steps": 32,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.5185329017526272e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14559310eedc27baafb7461d5f3294928980915898cc77f1e10f80f1e13ef019
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 40 KiB