22810c97b7
* use warmup_ratio as a better default than warmup steps since it's data dependent * replace remainder of warmup_steps
46 lines
876 B
YAML
46 lines
876 B
YAML
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
|
# optionally might have model_type or tokenizer_type
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
max_steps: 200
|
|
pretraining_dataset:
|
|
- path: allenai/c4
|
|
name: en
|
|
type: pretrain
|
|
dataset_prepared_path:
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/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
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch:
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|