43 lines
1014 B
YAML
43 lines
1014 B
YAML
cutoff_len: 1024
|
|
dataset: alpaca_slovak_cleaned
|
|
dataset_dir: data
|
|
ddp_timeout: 180000000
|
|
do_train: true
|
|
double_quantization: true
|
|
enable_thinking: false
|
|
eval_steps: 1000
|
|
eval_strategy: steps
|
|
finetuning_type: lora
|
|
flash_attn: auto
|
|
fp16: true
|
|
gradient_accumulation_steps: 8
|
|
include_num_input_tokens_seen: true
|
|
learning_rate: 0.0002
|
|
logging_steps: 5
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_rank: 16
|
|
lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
|
|
lr_scheduler_type: cosine
|
|
max_grad_norm: 1.0
|
|
max_samples: 50000
|
|
model_name_or_path: slovak-nlp/mistral-sk-7b
|
|
num_train_epochs: 1.0
|
|
optim: adamw_8bit
|
|
output_dir: /home/schwarc/diplomovka/mistral_sk_alpaca/llamafactory-full-lora
|
|
packing: false
|
|
per_device_eval_batch_size: 1
|
|
per_device_train_batch_size: 1
|
|
plot_loss: true
|
|
preprocessing_num_workers: 16
|
|
quantization_bit: 4
|
|
quantization_method: bnb
|
|
report_to: none
|
|
save_steps: 1000
|
|
save_total_limit: 2
|
|
stage: sft
|
|
template: alpaca
|
|
trust_remote_code: true
|
|
use_unsloth: true
|
|
val_size: 0.025
|
|
warmup_steps: 150 |