73 lines
1.3 KiB
YAML
73 lines
1.3 KiB
YAML
base_model: TheBloke/Llama-2-7B-GPTQ
|
|
gptq: true
|
|
gptq_disable_exllama: true
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
tokenizer_use_fast: true
|
|
tokenizer_legacy: true
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
push_dataset_to_hub:
|
|
hf_use_auth_token: true
|
|
datasets:
|
|
- path: mhenrichsen/alpaca_2k_test
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
adapter: lora
|
|
lora_model_dir:
|
|
sequence_len: 4096
|
|
sample_packing:
|
|
lora_r: 8
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_target_modules:
|
|
- k_proj
|
|
- o_proj
|
|
- q_proj
|
|
- v_proj
|
|
lora_target_linear:
|
|
lora_fan_in_fan_out:
|
|
wandb_project:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
output_dir: ./model-out
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 4
|
|
optimizer: adamw_torch
|
|
adam_beta2: 0.95
|
|
adam_eps: 0.00001
|
|
max_grad_norm: 1.0
|
|
torchdistx_path:
|
|
lr_scheduler: cosine
|
|
lr_quadratic_warmup: true
|
|
learning_rate: 0.000017
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: false
|
|
fp16: false
|
|
float16: true
|
|
tf32: true
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention:
|
|
sdp_attention:
|
|
flash_optimum:
|
|
warmup_steps: 100
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.1
|
|
special_tokens:
|
|
bos_token: "<s>"
|
|
eos_token: "</s>"
|
|
unk_token: "<unk>"
|