base_model: mistral-community/Mixtral-8x22B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

unfrozen_parameters:
  - ^lm_head.weight$
  - ^model.embed_tokens.weight$
  - model.layers.4[4-9]+.block_sparse_moe.gate
  - model.layers.4[4-9]+.block_sparse_moe.experts
  - model.layers.5[0-5]+.block_sparse_moe.gate
  - model.layers.5[0-5]+.block_sparse_moe.experts

model_config:
  output_router_logits: true

datasets:
  - path: yahma/alpaca-cleaned
    type: alpaca
output_dir: ./outputs/out

sequence_len: 8000
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

save_total_limit: 1
save_steps:
debug:
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_all.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"