base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

datasets:
  - path: vitalune/business-assistant-ai-tools
    type:
      field_instruction: prompt
      field_output: response
prompt_template: mistral

dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/mistral-ovarra-custom
sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00002

bf16: auto
tf32: false
gradient_checkpointing: true
flash_attention: true

logging_steps: 1
warmup_steps: 10
evals_per_epoch: 2
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"