base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
model_type: GPTNeoXForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code:
load_in_8bit: false
datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
dataset_prepared_path:
val_set_size: 0.02
adapter:
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
lora_fan_in_fan_out: false
wandb_project: redpajama-alpaca-3b
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./redpajama-alpaca-3b
batch_size: 4
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0000002
train_on_inputs: false
group_by_length: false
bf16: auto
tf32: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 5
xformers_attention:
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0001
fsdp:
fsdp_config:
tokens:
  pad_token: "<|padding|>"
  bos_token: "<|endoftext|>"
  eos_token: "<|endoftext|>"
  unk_token: "<|endoftext|>"