63 lines
1.3 KiB
YAML
63 lines
1.3 KiB
YAML
base_model: mosaicml/mpt-7b
|
|
# optionally might have model_type or tokenizer_type
|
|
tokenizer_type: AutoTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
trust_remote_code: true # required for mpt as their model class is not merged into transformers yet
|
|
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: mpt-alpaca-7b
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
output_dir: ./outputs/mpt-alpaca-7b
|
|
gradient_accumulation_steps: 1
|
|
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|>"
|