tinyllama.yml

base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0

model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

max_steps: 200
datasets:
  - path: microsoft/orca-math-word-problems-200k
    type:
      system_prompt: ""
      field_system: system
      field_instruction: question
      field_output: answer
      format: "<|user|>\n{instruction}</s>\n<|assistant|>\n"
      no_input_format: "<|user|>\n{instruction}</s>\n<|assistant|>\n"

wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 10
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

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

warmup_steps: 10
evals_per_epoch:
eval_table_size:
saves_per_epoch: 5
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens: