Axolotl finetune mistral (miladyos)

axolotl-train.Jenkinsfile

pipeline {
    agent any

    stages {
        stage('Run Training Session') {
            agent {
                docker {
                    image 'winglian/axolotl:main-py3.10-cu118-2.0.1'
                    args '--privileged --gpus all --shm-size 10g --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --mount type=volume,src=axolotl,target=/workspace/axolotl -v ${HOME}/.cache/huggingface:/root/.cache/huggingface'
                }
            }
            steps {
                sh 'ls -lh'
                sh 'pwd'
                writeFile file: 'qlora.yml', text: '''
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false
eval_sample_packing: false

datasets:
  - path: linpang/alpaca_html
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
eval_steps: 0.05
eval_table_size:
eval_table_max_new_tokens: 128
save_steps:
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"
                '''
                writeFile file: 'zero2.json', text: '''
{
  "zero_optimization": {
    "stage": 2,
    "offload_optimizer": {
      "device": "cpu"
    },
    "contiguous_gradients": true,
    "overlap_comm": true
  },
  "bf16": {
    "enabled": "auto"
  },
  "fp16": {
    "enabled": "auto",
    "auto_cast": false,
    "loss_scale": 0,
    "initial_scale_power": 32,
    "loss_scale_window": 1000,
    "hysteresis": 2,
    "min_loss_scale": 1
  },
  "gradient_accumulation_steps": "auto",
  "train_batch_size": "auto",
  "train_micro_batch_size_per_gpu": "auto",
  "wall_clock_breakdown": false
}
                '''
                sh 'ACCELERATE_USE_DEEPSPEED=true accelerate launch -m axolotl.cli.train qlora.yml --deepspeed zero2.json'
            }
        }
    }

    post {
        always {
            echo 'Cleaning up...'
        }
    }
}