Hugging Face's logo

lu-vae
/
qwen1.5-7b-fft

Text Generation
Transformers
PyTorch
qwen2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
qwen1.5-7b-fft / README.md
lu-vae's picture
lu-vae
Upload README.md with huggingface_hub
6856cca verified
preview code
|
raw
history blame contribute delete
3.03 kB
metadata
license: other
base_model: Qwen/Qwen1.5-7B
tags:
  - generated_from_trainer
model-index:
  - name: qwen1.5-7b-fft
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: Qwen/Qwen1.5-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: /data/data/final_set_cleaned/train/
    type: sharegpt
    conversation: chatml
  - path: /data/data/map_coig_cqia.jsonl
    type: sharegpt
    conversation: chatml
  - path: /data/data/ruozhiba.jsonl
    type: sharegpt
    conversation: chatml
  - path: /data/data/sharegpt4.jsonl
    type: sharegpt
    conversation: chatml
  - path: /data/data/OpenHermes-Zh.jsonl
    type: sharegpt
    conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: FFT
wandb_entity:
wandb_watch:
wandb_name: 
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-5

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.05
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 4
save_total_limit: 8
debug:
deepspeed: deepspeed/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
default_system_message: "You are a helpful assistant."
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

qwen1.5-7b-fft

This model is a fine-tuned version of Qwen/Qwen1.5-7B on the None 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: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 6
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 48
  • total_eval_batch_size: 6
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 48
  • num_epochs: 2

Training results

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.15.0
  • Tokenizers 0.19.1