axolotl版本: 0.8.0.dev0

base_model: Qwen/Qwen2.5-7B-Instruct-1M  
load_in_8bit: false  
load_in_4bit: true  
strict: false  

datasets:  
  - path: diabolic6045/Sanskrit-llama  
    type: alpaca  
dataset_prepared_path:  
val_set_size: 0  
output_dir: ./outputs/qlora-out  

adapter: qlora  
lora_model_dir:  

sequence_len: 1024  
sample_packing: true  
eval_sample_packing: false  
pad_to_sequence_len: true  

lora_r: 32  
lora_alpha: 16  
lora_dropout: 0.05  
lora_target_modules:  
lora_target_linear: true  
lora_fan_in_fan_out:  

hub_model_id: Sanskrit-qwen-8B  

wandb_project: संस्कृतम्-llama  
wandb_entity:   
wandb_watch: all  
wandb_name: संस्कृतम्-llama  
wandb_log_model:   

gradient_accumulation_steps: 1  
micro_batch_size: 1  
num_epochs: 1  
optimizer: paged_adamw_8bit  
lr_scheduler: cosine  
cosine_min_lr_ratio: 0.2  
learning_rate: 2e-5  

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

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

#gpu_memory_limit: 20GiB  
#lora_on_cpu: true          

warmup_steps: 10  
evals_per_epoch: 4  
saves_per_epoch: 1  
debug:  
deepspeed: deepspeed_configs/zero1.json  
weight_decay: 0.0  
special_tokens:  
   pad_token: <|end_of_text|>