40a6362c92
* support for mamba * more mamba fixes * use fork for mamba kwargs fix * grad checkpointing doesn't work * fix extras for mamaba * mamba loss fix * use fp32 and remove verbose logging * mamba fixes * fix collator for mamba * set model_type on training_args * don't save safetensors for mamba * update mamba config to disable safetensor checkpooints, install for tests * no evals for mamba tests * handle save_pretrained * handle unused safetensors arg
62 lines
1018 B
YAML
62 lines
1018 B
YAML
base_model: state-spaces/mamba-2.8b
|
|
model_type: MambaLMHeadModel
|
|
tokenizer_type: AutoTokenizer
|
|
tokenizer_config: EleutherAI/gpt-neox-20b
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: mhenrichsen/alpaca_2k_test
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.0
|
|
output_dir: ./out
|
|
|
|
sequence_len: 2048
|
|
sample_packing: false
|
|
pad_to_sequence_len: false
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 2
|
|
optimizer: paged_adamw_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 5e-5
|
|
|
|
train_on_inputs: false
|
|
group_by_length: true
|
|
|
|
bf16: true
|
|
fp16: false
|
|
tf32: true
|
|
|
|
gradient_checkpointing: false
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention:
|
|
|
|
warmup_steps: 10
|
|
eval_steps:
|
|
eval_table_size:
|
|
eval_table_max_new_tokens: 128
|
|
save_steps: 0.25
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
tokens:
|
|
save_safetensors: False
|