17Lab/qwen7b-hermes-fc-full-sft-s42
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: 17Lab/qwen7b-hermes-fc-full-sft-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-30 09:20:16 +08:00
commit 55c5362824
14 changed files with 414 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

67
README.md Normal file
View File

@@ -0,0 +1,67 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-7B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: qwen7b_bfcl_mini_full_sft_s42
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. -->
# qwen7b_bfcl_mini_full_sft_s42
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the bfcl_mini_sft dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2251
## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.1746 | 1.96 | 25 | 0.2569 |
| 0.0856 | 3.0 | 39 | 0.2251 |
### Framework versions
- Transformers 5.6.0
- Pytorch 2.7.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2

12
all_results.json Normal file
View File

@@ -0,0 +1,12 @@
{
"epoch": 3.0,
"eval_loss": 0.22509032487869263,
"eval_runtime": 0.8749,
"eval_samples_per_second": 48.004,
"eval_steps_per_second": 6.858,
"total_flos": 1274990395392.0,
"train_loss": 0.3065599493491344,
"train_runtime": 587.7054,
"train_samples_per_second": 4.012,
"train_steps_per_second": 0.066
}

54
chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# 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' }}
{%- else %}
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.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 %}

62
config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"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": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.6.0",
"use_cache": false,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}

7
eval_results.json Normal file
View File

@@ -0,0 +1,7 @@
{
"epoch": 3.0,
"eval_loss": 0.22509032487869263,
"eval_runtime": 0.8749,
"eval_samples_per_second": 48.004,
"eval_steps_per_second": 6.858
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"do_sample": false,
"eos_token_id": [
151645,
151643
],
"max_new_tokens": 2048,
"pad_token_id": 151643,
"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 sha256:0b46c73af91374d795eb05d9d4ca84a691b2b3a4a505882b9fa3f7b2fb68511d
size 15231272152

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
size 11421892

31
tokenizer_config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"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,
"local_files_only": 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": 3.0,
"total_flos": 1274990395392.0,
"train_loss": 0.3065599493491344,
"train_runtime": 587.7054,
"train_samples_per_second": 4.012,
"train_steps_per_second": 0.066
}

10
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,10 @@
{"current_steps": 5, "total_steps": 39, "loss": 0.8891424179077149, "lr": 1.9856159103477085e-05, "epoch": 0.4, "percentage": 12.82, "elapsed_time": "0:00:23", "remaining_time": "0:02:38"}
{"current_steps": 10, "total_steps": 39, "loss": 0.5139811515808106, "lr": 1.8285096492438424e-05, "epoch": 0.8, "percentage": 25.64, "elapsed_time": "0:00:38", "remaining_time": "0:01:52"}
{"current_steps": 15, "total_steps": 39, "loss": 0.3687877893447876, "lr": 1.5243072835572319e-05, "epoch": 1.16, "percentage": 38.46, "elapsed_time": "0:00:51", "remaining_time": "0:01:23"}
{"current_steps": 20, "total_steps": 39, "loss": 0.21150989532470704, "lr": 1.1270178197468788e-05, "epoch": 1.56, "percentage": 51.28, "elapsed_time": "0:01:06", "remaining_time": "0:01:03"}
{"current_steps": 25, "total_steps": 39, "loss": 0.17464923858642578, "lr": 7.071772287234497e-06, "epoch": 1.96, "percentage": 64.1, "elapsed_time": "0:01:21", "remaining_time": "0:00:45"}
{"current_steps": 25, "total_steps": 39, "eval_loss": 0.25689050555229187, "epoch": 1.96, "percentage": 64.1, "elapsed_time": "0:01:22", "remaining_time": "0:00:46"}
{"current_steps": 30, "total_steps": 39, "loss": 0.09203737378120422, "lr": 3.3932527660991877e-06, "epoch": 2.32, "percentage": 76.92, "elapsed_time": "0:05:18", "remaining_time": "0:01:35"}
{"current_steps": 35, "total_steps": 39, "loss": 0.0855832576751709, "lr": 8.87715096118642e-07, "epoch": 2.7199999999999998, "percentage": 89.74, "elapsed_time": "0:05:32", "remaining_time": "0:00:38"}
{"current_steps": 39, "total_steps": 39, "eval_loss": 0.22509032487869263, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:44", "remaining_time": "0:00:00"}
{"current_steps": 39, "total_steps": 39, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:27", "remaining_time": "0:00:00"}

108
trainer_state.json Normal file
View File

@@ -0,0 +1,108 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 25,
"global_step": 39,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4,
"grad_norm": 14.682328659827894,
"learning_rate": 1.9856159103477085e-05,
"loss": 0.8891424179077149,
"step": 5
},
{
"epoch": 0.8,
"grad_norm": 11.714302479472073,
"learning_rate": 1.8285096492438424e-05,
"loss": 0.5139811515808106,
"step": 10
},
{
"epoch": 1.16,
"grad_norm": 10.208381605756056,
"learning_rate": 1.5243072835572319e-05,
"loss": 0.3687877893447876,
"step": 15
},
{
"epoch": 1.56,
"grad_norm": 10.262843920575644,
"learning_rate": 1.1270178197468788e-05,
"loss": 0.21150989532470704,
"step": 20
},
{
"epoch": 1.96,
"grad_norm": 6.68105063937876,
"learning_rate": 7.071772287234497e-06,
"loss": 0.17464923858642578,
"step": 25
},
{
"epoch": 1.96,
"eval_loss": 0.25689050555229187,
"eval_runtime": 0.9005,
"eval_samples_per_second": 46.642,
"eval_steps_per_second": 6.663,
"step": 25
},
{
"epoch": 2.32,
"grad_norm": 5.69195152871731,
"learning_rate": 3.3932527660991877e-06,
"loss": 0.09203737378120422,
"step": 30
},
{
"epoch": 2.7199999999999998,
"grad_norm": 4.8584537804368715,
"learning_rate": 8.87715096118642e-07,
"loss": 0.0855832576751709,
"step": 35
},
{
"epoch": 3.0,
"eval_loss": 0.22509032487869263,
"eval_runtime": 0.8925,
"eval_samples_per_second": 47.061,
"eval_steps_per_second": 6.723,
"step": 39
},
{
"epoch": 3.0,
"step": 39,
"total_flos": 1274990395392.0,
"train_loss": 0.3065599493491344,
"train_runtime": 587.7054,
"train_samples_per_second": 4.012,
"train_steps_per_second": 0.066
}
],
"logging_steps": 5,
"max_steps": 39,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1274990395392.0,
"train_batch_size": 4,
"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 sha256:6c9d4d8b3e2a1ba2b5a51263d22c647c20bc87114204ffb764d1eac7e28268bf
size 7377