e4063d60a7
* bump transformers and set roundup_power2_divisions for more VRAM improvements * support for low bit optimizers from torch ao * fix check for alternate optimizers and use nous models on hf for llama3 * add missing check for ao_adamw_fp8 * fix check when using custom optimizers w adamw
72 lines
1.2 KiB
YAML
72 lines
1.2 KiB
YAML
base_model: NousResearch/Meta-Llama-3-8B
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: mhenrichsen/alpaca_2k_test
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
output_dir: ./outputs/lora-out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
eval_sample_packing: false
|
|
pad_to_sequence_len: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
lora_modules_to_save:
|
|
- embed_tokens
|
|
- lm_head
|
|
|
|
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: auto
|
|
fp16:
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
s2_attention:
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
eval_table_size:
|
|
eval_max_new_tokens: 128
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
pad_token: <|end_of_text|>
|