varshak1/open_reward_agent_sft_lf
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: varshak1/open_reward_agent_sft_lf
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 07:50:16 +08:00
commit ce5246e3fd
14 changed files with 528 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

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: open_reward_agent_sft_lf
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. -->
# open_reward_agent_sft_lf
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the open_reward_agent_sft_lf 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: 8e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- 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: 0.05
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 5.2.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 2.640143661303595e+18,
"train_loss": 0.9932206619076612,
"train_runtime": 1797.9362,
"train_samples_per_second": 7.286,
"train_steps_per_second": 0.114
}

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 %}

71
config.json Normal file
View File

@@ -0,0 +1,71 @@
{
"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": 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_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.2.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

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": "5.2.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6627998b45798f599014942c9bf5bf8977efdc0468ef27b94fe3597f50625f1f
size 16381517208

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

30
tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_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|>"
],
"is_local": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 2.640143661303595e+18,
"train_loss": 0.9932206619076612,
"train_runtime": 1797.9362,
"train_samples_per_second": 7.286,
"train_steps_per_second": 0.114
}

21
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,21 @@
{"current_steps": 10, "total_steps": 205, "loss": 1.6103919982910155, "lr": 6.545454545454546e-06, "epoch": 0.04884004884004884, "percentage": 4.88, "elapsed_time": "0:01:30", "remaining_time": "0:29:33"}
{"current_steps": 20, "total_steps": 205, "loss": 1.1710912704467773, "lr": 7.9664804049057e-06, "epoch": 0.09768009768009768, "percentage": 9.76, "elapsed_time": "0:02:55", "remaining_time": "0:27:04"}
{"current_steps": 30, "total_steps": 205, "loss": 1.0446645736694335, "lr": 7.831269296751948e-06, "epoch": 0.14652014652014653, "percentage": 14.63, "elapsed_time": "0:04:19", "remaining_time": "0:25:14"}
{"current_steps": 40, "total_steps": 205, "loss": 0.9899624824523926, "lr": 7.595806964341581e-06, "epoch": 0.19536019536019536, "percentage": 19.51, "elapsed_time": "0:05:44", "remaining_time": "0:23:39"}
{"current_steps": 50, "total_steps": 205, "loss": 0.9951982498168945, "lr": 7.266254652228843e-06, "epoch": 0.2442002442002442, "percentage": 24.39, "elapsed_time": "0:07:11", "remaining_time": "0:22:17"}
{"current_steps": 60, "total_steps": 205, "loss": 0.9782312393188477, "lr": 6.851235618187317e-06, "epoch": 0.29304029304029305, "percentage": 29.27, "elapsed_time": "0:08:34", "remaining_time": "0:20:42"}
{"current_steps": 70, "total_steps": 205, "loss": 0.9667717933654785, "lr": 6.36160949202369e-06, "epoch": 0.3418803418803419, "percentage": 34.15, "elapsed_time": "0:09:58", "remaining_time": "0:19:13"}
{"current_steps": 80, "total_steps": 205, "loss": 0.9572884559631347, "lr": 5.810188116178156e-06, "epoch": 0.3907203907203907, "percentage": 39.02, "elapsed_time": "0:11:20", "remaining_time": "0:17:43"}
{"current_steps": 90, "total_steps": 205, "loss": 0.9558270454406739, "lr": 5.211400303591802e-06, "epoch": 0.43956043956043955, "percentage": 43.9, "elapsed_time": "0:12:45", "remaining_time": "0:16:17"}
{"current_steps": 100, "total_steps": 205, "loss": 0.9527605056762696, "lr": 4.580914284981961e-06, "epoch": 0.4884004884004884, "percentage": 48.78, "elapsed_time": "0:14:08", "remaining_time": "0:14:51"}
{"current_steps": 110, "total_steps": 205, "loss": 0.9419396400451661, "lr": 3.935227724789994e-06, "epoch": 0.5372405372405372, "percentage": 53.66, "elapsed_time": "0:15:33", "remaining_time": "0:13:26"}
{"current_steps": 120, "total_steps": 205, "loss": 0.9319709777832031, "lr": 3.2912360336831093e-06, "epoch": 0.5860805860805861, "percentage": 58.54, "elapsed_time": "0:16:57", "remaining_time": "0:12:00"}
{"current_steps": 130, "total_steps": 205, "loss": 0.9522204399108887, "lr": 2.665790273396718e-06, "epoch": 0.6349206349206349, "percentage": 63.41, "elapsed_time": "0:18:20", "remaining_time": "0:10:34"}
{"current_steps": 140, "total_steps": 205, "loss": 0.9412946701049805, "lr": 2.0752562220367795e-06, "epoch": 0.6837606837606838, "percentage": 68.29, "elapsed_time": "0:19:47", "remaining_time": "0:09:11"}
{"current_steps": 150, "total_steps": 205, "loss": 0.9191699981689453, "lr": 1.5350861375962904e-06, "epoch": 0.7326007326007326, "percentage": 73.17, "elapsed_time": "0:21:11", "remaining_time": "0:07:46"}
{"current_steps": 160, "total_steps": 205, "loss": 0.9190822601318359, "lr": 1.0594144251711994e-06, "epoch": 0.7814407814407814, "percentage": 78.05, "elapsed_time": "0:22:37", "remaining_time": "0:06:21"}
{"current_steps": 170, "total_steps": 205, "loss": 0.9286371231079101, "lr": 6.606877878829161e-07, "epoch": 0.8302808302808303, "percentage": 82.93, "elapsed_time": "0:24:01", "remaining_time": "0:04:56"}
{"current_steps": 180, "total_steps": 205, "loss": 0.9289794921875, "lr": 3.4933953919383984e-07, "epoch": 0.8791208791208791, "percentage": 87.8, "elapsed_time": "0:25:24", "remaining_time": "0:03:31"}
{"current_steps": 190, "total_steps": 205, "loss": 0.919953727722168, "lr": 1.3351659874955546e-07, "epoch": 0.927960927960928, "percentage": 92.68, "elapsed_time": "0:26:51", "remaining_time": "0:02:07"}
{"current_steps": 200, "total_steps": 205, "loss": 0.9213088989257813, "lr": 1.8866315333544213e-08, "epoch": 0.9768009768009768, "percentage": 97.56, "elapsed_time": "0:28:14", "remaining_time": "0:00:42"}
{"current_steps": 205, "total_steps": 205, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:29:56", "remaining_time": "0:00:00"}

183
trainer_state.json Normal file
View File

@@ -0,0 +1,183 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 205,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04884004884004884,
"grad_norm": 2.951613426208496,
"learning_rate": 6.545454545454546e-06,
"loss": 1.6103919982910155,
"step": 10
},
{
"epoch": 0.09768009768009768,
"grad_norm": 1.4161419868469238,
"learning_rate": 7.9664804049057e-06,
"loss": 1.1710912704467773,
"step": 20
},
{
"epoch": 0.14652014652014653,
"grad_norm": 1.1890255212783813,
"learning_rate": 7.831269296751948e-06,
"loss": 1.0446645736694335,
"step": 30
},
{
"epoch": 0.19536019536019536,
"grad_norm": 1.1855751276016235,
"learning_rate": 7.595806964341581e-06,
"loss": 0.9899624824523926,
"step": 40
},
{
"epoch": 0.2442002442002442,
"grad_norm": 1.4533610343933105,
"learning_rate": 7.266254652228843e-06,
"loss": 0.9951982498168945,
"step": 50
},
{
"epoch": 0.29304029304029305,
"grad_norm": 1.264499545097351,
"learning_rate": 6.851235618187317e-06,
"loss": 0.9782312393188477,
"step": 60
},
{
"epoch": 0.3418803418803419,
"grad_norm": 1.3089553117752075,
"learning_rate": 6.36160949202369e-06,
"loss": 0.9667717933654785,
"step": 70
},
{
"epoch": 0.3907203907203907,
"grad_norm": 1.0916252136230469,
"learning_rate": 5.810188116178156e-06,
"loss": 0.9572884559631347,
"step": 80
},
{
"epoch": 0.43956043956043955,
"grad_norm": 1.2539805173873901,
"learning_rate": 5.211400303591802e-06,
"loss": 0.9558270454406739,
"step": 90
},
{
"epoch": 0.4884004884004884,
"grad_norm": 1.1267527341842651,
"learning_rate": 4.580914284981961e-06,
"loss": 0.9527605056762696,
"step": 100
},
{
"epoch": 0.5372405372405372,
"grad_norm": 1.0940070152282715,
"learning_rate": 3.935227724789994e-06,
"loss": 0.9419396400451661,
"step": 110
},
{
"epoch": 0.5860805860805861,
"grad_norm": 1.7783108949661255,
"learning_rate": 3.2912360336831093e-06,
"loss": 0.9319709777832031,
"step": 120
},
{
"epoch": 0.6349206349206349,
"grad_norm": 1.1148947477340698,
"learning_rate": 2.665790273396718e-06,
"loss": 0.9522204399108887,
"step": 130
},
{
"epoch": 0.6837606837606838,
"grad_norm": 1.0567108392715454,
"learning_rate": 2.0752562220367795e-06,
"loss": 0.9412946701049805,
"step": 140
},
{
"epoch": 0.7326007326007326,
"grad_norm": 1.0418899059295654,
"learning_rate": 1.5350861375962904e-06,
"loss": 0.9191699981689453,
"step": 150
},
{
"epoch": 0.7814407814407814,
"grad_norm": 0.9806021451950073,
"learning_rate": 1.0594144251711994e-06,
"loss": 0.9190822601318359,
"step": 160
},
{
"epoch": 0.8302808302808303,
"grad_norm": 1.0123064517974854,
"learning_rate": 6.606877878829161e-07,
"loss": 0.9286371231079101,
"step": 170
},
{
"epoch": 0.8791208791208791,
"grad_norm": 1.079588770866394,
"learning_rate": 3.4933953919383984e-07,
"loss": 0.9289794921875,
"step": 180
},
{
"epoch": 0.927960927960928,
"grad_norm": 1.2275781631469727,
"learning_rate": 1.3351659874955546e-07,
"loss": 0.919953727722168,
"step": 190
},
{
"epoch": 0.9768009768009768,
"grad_norm": 1.0596216917037964,
"learning_rate": 1.8866315333544213e-08,
"loss": 0.9213088989257813,
"step": 200
},
{
"epoch": 1.0,
"step": 205,
"total_flos": 2.640143661303595e+18,
"train_loss": 0.9932206619076612,
"train_runtime": 1797.9362,
"train_samples_per_second": 7.286,
"train_steps_per_second": 0.114
}
],
"logging_steps": 10,
"max_steps": 205,
"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": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.640143661303595e+18,
"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:df97d1b346179757db27ce8b703af272dc95cec4c6ac81113071fb45d7156285
size 6776

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 32 KiB