base_model: huggyllama/llama-7b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
datasets:
  - path: openaccess-ai-collective/jeopardy
    type: jeopardy
dataset_prepared_path:
val_set_size: 0.02
adapter:
lora_model_dir:
sequence_len: 512
max_packed_sequence_len:
lora_r:
lora_alpha:
lora_dropout:
lora_target_modules:
lora_fan_in_fan_out: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./jeopardy-bot-7b
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.00003
train_on_inputs: false
group_by_length: false
bf16: true
tf32: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 5
xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"