60 lines
1.3 KiB
YAML
60 lines
1.3 KiB
YAML
# Jeden trening tohto modelu: 4 H200, DDP, Unsloth a bf16.
|
|
model_name_or_path: "slovak-nlp/mistral-sk-7b"
|
|
model_revision: "089497ae0d72018e9591895c54f774bf0b4a83a4"
|
|
stage: sft
|
|
do_train: true
|
|
do_eval: true
|
|
finetuning_type: lora
|
|
template: alpaca
|
|
use_unsloth: true
|
|
use_unsloth_gc: true
|
|
bf16: true
|
|
infer_dtype: bfloat16
|
|
flash_attn: sdpa
|
|
|
|
dataset_dir: data/aya_slovak_4096
|
|
dataset: aya_train
|
|
eval_dataset: aya_eval
|
|
cutoff_len: 4096
|
|
packing: false
|
|
train_on_prompt: false
|
|
preprocessing_num_workers: 8
|
|
dataloader_num_workers: 2
|
|
overwrite_cache: false
|
|
|
|
lora_rank: 16
|
|
lora_alpha: 32
|
|
lora_dropout: 0.0
|
|
lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
|
|
|
|
per_device_train_batch_size: 8
|
|
per_device_eval_batch_size: 8
|
|
gradient_accumulation_steps: 1
|
|
learning_rate: 0.0001
|
|
num_train_epochs: 1.0
|
|
lr_scheduler_type: cosine
|
|
warmup_ratio: 0.08
|
|
optim: adamw_torch
|
|
weight_decay: 0.0
|
|
max_grad_norm: 0.5
|
|
gradient_checkpointing: true
|
|
ddp_find_unused_parameters: false
|
|
|
|
output_dir: runs/mistral/adapter
|
|
overwrite_output_dir: false
|
|
logging_steps: 10
|
|
eval_strategy: steps
|
|
eval_steps: 1000
|
|
save_strategy: steps
|
|
save_steps: 1000
|
|
save_total_limit: 2
|
|
save_only_model: false
|
|
load_best_model_at_end: true
|
|
metric_for_best_model: loss
|
|
greater_is_better: false
|
|
predict_with_generate: false
|
|
plot_loss: true
|
|
report_to: none
|
|
seed: 42
|
|
data_seed: 42
|