# 学習のベースモデルに関する設定
base_model: Kendamarron/Qwen2.5-4x0.5B-cpt
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: Kendamarron/Qwen2.5-4x0.5B-sft-v1
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: false

# SFTに利用するchat templateの設定
chat_template: qwen_25

# 学習データセットの前処理に関する設定
datasets:
  - path: Kendamarron/jimba-instruction-all
    split: train
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
  - path: Kendamarron/OpenMathInstruct-2-ja-CoT-only_thought
    split: train
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: Aratako/Synthetic-JP-EN-Coding-Dataset-801k
    split: train[0:10000]
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: llm-jp/magpie-sft-v1.0
    split: train[0:30000]
    type: chat_template
    field_messages: conversations
    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/Qwen2.5-4x0.5B-SFT

# valid datasetのサイズ
val_set_size: 0.005

# wandbに関する設定
wandb_project: Qwen2.5-4x0.5B
wandb_entity: kendamarron
wandb_watch:
wandb_name: sft-v1
wandb_log_model:

# 学習に関する様々な設定
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1
learning_rate: 2e-5

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

saves_per_epoch: 1

warmup_steps: 60
eval_steps: 100
eval_batch_size: 1
eval_table_size:
eval_max_new_tokens:
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"

Qwen2.5-4x0.5B-sft-v1

This model is a fine-tuned version of Kendamarron/Qwen2.5-4x0.5B-cpt on the Kendamarron/jimba-instruction-all, the Kendamarron/OpenMathInstruct-2-ja-CoT-only_thought, the Aratako/Synthetic-JP-EN-Coding-Dataset-801k and the llm-jp/magpie-sft-v1.0 datasets. It achieves the following results on the evaluation set:

Loss: 1.0085

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_BNB 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: 60
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.3068	0.0033	1	1.3071
1.1087	0.3309	100	1.0806
1.1393	0.6617	200	1.0488
1.0569	0.9926	300	1.0286
0.9902	1.3209	400	1.0215
0.9933	1.6518	500	1.0133
0.9706	1.9826	600	1.0085

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0

Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja

Qwen2.5-1.75B-A1.1B-Instruct-ja

Details

Qwen2.5-4x0.5B-sft-v1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Kendamarron/
Qwen2.5-1.75B-A1.1B-Instruct-ja