base_model: /workspace/mistral-11b-base
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Open-Orca/SlimOrca
    type: sharegpt
    conversation: mistral

dataset_prepared_path:
val_set_size: 0.005
output_dir: ./out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: mistral-11b-noresidual
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

train_on_inputs: true
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
flash_attention: true

logging_steps: 1
warmup_steps: 10
eval_steps: 100
save_steps: 100
weight_decay: 0.0
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"