---
library_name: peft
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
tags:
- axolotl
- generated_from_trainer
datasets:
- kanhatakeyama/ramdom-to-fixed-multiturn-Calm3
- Aratako/Magpie-Tanuki-Qwen2.5-72B-Answered
- Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted
- Aratako/magpie-reasoning-llama-nemotron-70b-100k-filtered
- Aratako/Open-Platypus-Japanese-masked-formatted
- kanhatakeyama/wizardlm8x22b-logical-math-coding-sft_additional-ja
- Aratako/magpie-ultra-v0.1-formatted
- Aratako/orca-agentinstruct-1M-v1-selected
- Aratako/Synthetic-JP-EN-Coding-Dataset-801k-50k
model-index:
- name: DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0
  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. -->

[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.8.0.dev0`
```yaml
# 学習のベースモデルに関する設定
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

# 学習後のモデルのHFへのアップロードに関する設定
hub_model_id: kazuyamaa/DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0
hub_strategy: "end"
push_dataset_to_hub:
hf_use_auth_token: true

# Liger Kernelの設定（学習の軽量・高速化）
plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_cross_entropy: false
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

# 量子化に関する設定
load_in_8bit: false
load_in_4bit: true

# SFTに利用するchat templateの設定
chat_template: gemma

# 学習データセットの前処理に関する設定
datasets:
  - path: kanhatakeyama/ramdom-to-fixed-multiturn-Calm3
    split: 20240806filtered[0:10000]
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: Aratako/Magpie-Tanuki-Qwen2.5-72B-Answered
    split: train[0:10000]
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted
    split: train[0:10000]
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
  - path: Aratako/magpie-reasoning-llama-nemotron-70b-100k-filtered
    split: train[0:10000]
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
  - path: Aratako/Open-Platypus-Japanese-masked-formatted
    split: train[0:10000]
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
  - path: kanhatakeyama/wizardlm8x22b-logical-math-coding-sft_additional-ja
    split: train[0:10000]
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: Aratako/magpie-ultra-v0.1-formatted
    split: train[0:10000]
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
  - path: Aratako/orca-agentinstruct-1M-v1-selected
    split: train[0:10000]
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: Aratako/Synthetic-JP-EN-Coding-Dataset-801k-50k
    split: train[0:10000]
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content

# データセット、モデルの出力先に関する設定
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/data/sft-data
output_dir: /workspace/data/models/DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0

# valid datasetのサイズ
val_set_size: 0.05

# LoRAに関する設定（フルファインチューニングしたい場合は全て空欄にする）
adapter: qlora
lora_model_dir:
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

# wandbに関する設定
wandb_project: axolotl
wandb_entity: kazukitakayamas051-securities-companies
wandb_watch:
wandb_name: sft-lora-1
wandb_log_model:

# 学習に関する様々な設定
sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1
learning_rate: 3e-4

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false


gradient_checkpointing: false
early_stopping_patience:
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

save_strategy: steps
save_steps: 50
save_total_limit: 2

warmup_steps: 10
eval_steps: 50
eval_batch_size: 1
eval_table_size:
eval_max_new_tokens:
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
  pad_token: <pad>
```

</details><br>

# DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0

This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) on the kanhatakeyama/ramdom-to-fixed-multiturn-Calm3, the Aratako/Magpie-Tanuki-Qwen2.5-72B-Answered, the Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted, the Aratako/magpie-reasoning-llama-nemotron-70b-100k-filtered, the Aratako/Open-Platypus-Japanese-masked-formatted, the kanhatakeyama/wizardlm8x22b-logical-math-coding-sft_additional-ja, the Aratako/magpie-ultra-v0.1-formatted, the Aratako/orca-agentinstruct-1M-v1-selected and the Aratako/Synthetic-JP-EN-Coding-Dataset-801k-50k datasets.
It achieves the following results on the evaluation set:
- Loss: 0.6711

## 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: 0.0003
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- total_eval_batch_size: 2
- optimizer: Use paged_adamw_8bit 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: 10
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1079        | 0.0015 | 1    | 1.0631          |
| 0.8387        | 0.0763 | 50   | 0.7640          |
| 0.7109        | 0.1526 | 100  | 0.7312          |
| 0.7324        | 0.2289 | 150  | 0.7155          |
| 0.8239        | 0.3051 | 200  | 0.7045          |
| 0.7019        | 0.3814 | 250  | 0.6967          |
| 0.8834        | 0.4577 | 300  | 0.6910          |
| 0.7097        | 0.5340 | 350  | 0.6857          |
| 0.6659        | 0.6103 | 400  | 0.6821          |
| 0.6755        | 0.6866 | 450  | 0.6785          |
| 0.6465        | 0.7628 | 500  | 0.6755          |
| 0.6697        | 0.8391 | 550  | 0.6735          |
| 0.8425        | 0.9154 | 600  | 0.6720          |
| 0.6461        | 0.9917 | 650  | 0.6711          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.1