553c80f79a
* [Feat] streaming multipack * WIP make continued pretraining work w multipack * fix up hadrcoding, lint * fix dict check * update test for updated pretraining multipack code * fix hardcoded data collator fix for multipack pretraining * fix the collator to be the max length for multipack pretraining * don't bother with latest tag for test * cleanup docker build/test --------- Co-authored-by: jinwonkim93@github.com <jinwonkim> Co-authored-by: Wing Lian <wing.lian@gmail.com>
59 lines
938 B
YAML
59 lines
938 B
YAML
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
|
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_llama_derived_model: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
max_steps: 200
|
|
pretraining_dataset:
|
|
path: c4
|
|
name: en
|
|
dataset_prepared_path:
|
|
val_set_size: 0.0
|
|
output_dir: ./model-out
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 4
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch:
|
|
eval_table_size:
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|