See axolotl config

axolotl version: 0.5.0

# /home/az/Bureau/FINE_TUNING_VASTAI_CLM+SFT_SUR_BASE_MODEL/01_DOCKER_finetune/axolotl_config.yaml

base_model: Qwen/Qwen2.5-14B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false

# Dataset CLM pur
datasets:
  - path: philipperen55/dataset40CLM
    data_files: dataset40CLM.jsonl
    type: completion
    field: text

dataset_prepared_path: /workspace/prepared_data
val_set_size: 0.0
output_dir: /workspace/output

# Séquence et packing
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

# LoRA
adapter: lora
lora_r: 64
lora_alpha: 128
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj

# Training
gradient_accumulation_steps: 2
micro_batch_size: 8
num_epochs: 2
learning_rate: 5e-6
lr_scheduler: cosine
warmup_ratio: 0.05
optimizer: adamw_torch

# Précision
bf16: true
fp16: false
tf32: true

# Optimisations
flash_attention: false
gradient_checkpointing: true

# Logging et sauvegardes
logging_steps: 10
save_steps: 314
save_total_limit: 6

# WandB
wandb_project: Qwen2.5-14B-CLM-style

# Hub
hub_model_id: philipperen55/Qwen2.5-14B-style-CLM
push_to_hub: true

Qwen2.5-14B-style-CLM

This model is a fine-tuned version of Qwen/Qwen2.5-14B 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: 5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 25
• num_epochs: 2

Training results

Framework versions

• PEFT 0.13.2
• Transformers 4.46.1
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3