Kendamarron/LongWriter-llm-jp-3-3.7b-instruct

llm-jp/llm-jp-3-3.7b-instructを長文出力ができるようにSFTしたモデルです。

Dataset

• Kendamarron/Japanese-LongWriter-3k

Detail

https://zenn.dev/kendama/articles/32aa9ec4bed409

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 8
• 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_ratio: 0.1
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7184	1.2626	500	0.7673

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3

LLaMA-Factory yaml

### model
model_name_or_path: llm-jp/llm-jp-3-3.7b-instruct

### method
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json
enable_liger_kernel: true

### dataset
dataset: longwriter
template: alpaca_ja
cutoff_len: 32768
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/llm_jp/full/sft
logging_steps: 1
save_steps: 500
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 1
learning_rate: 1.0e-5
optim: adamw_bnb_8bit
num_train_epochs: 2.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

### eval
val_size: 0.01
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500

### logging
report_to: wandb