adapter: qlora
base_model: mistralai/Mistral-7B-v0.3
bf16: false
dataset_prepared_path: null
datasets:
- path: Igorrr0/mrowczaki2
  type: alpaca
debug: null
deepspeed: null
early_stopping_patience: null
evals_per_epoch: 2
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
is_llama_derived_model: false
learning_rate: 0.0004
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
micro_batch_size: 1
mlflow_experiment_name: mrowki-example
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: paged_adamw_32bit
output_dir: ./qlora-out-mrowki2
pad_to_sequence_len: false
resume_from_checkpoint: null
sample_packing: false
saves_per_epoch: 2
sequence_len: 512
special_tokens: null
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
val_set_size: 0.1
wandb_entity: null
wandb_log_model: null
wandb_name: null
wandb_project: null
wandb_watch: null
warmup_steps: 5
weight_decay: 0.001
xformers_attention: null

work in progress. i do not advise you to use it right now.

Igorrr0/gemma-2b-polish-ants

Igorrr0/
gemma-2b-polish-ants