base_model: CohereForAI/c4ai-command-r7b-12-2024
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true

# huggingface repo
chat_template: cohere
datasets:
  - path: cgato/SlimOrcaDedupCleaned
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

val_set_size: 0.0
output_dir: ./outputs/out

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:


gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: true

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch:
saves_per_epoch: 1
weight_decay: 0.0
special_tokens: