1d70f24b50
* Add s2_attn to hijack flash code * Refactor code to account for s2_attn * Add test for models utils * Add ``s2_attention`` option to llama configs * Add ``s2_attention`` option to README config * Format code to appease linter * chore: lint * Remove xpos and llama-landmark [bad merge] * add e2e smoke tests for shifted sparse attention * remove stray patch from merge * update yml with link to paper for s2_attention/longlora * fix assertion check for full fine tune * increase sequence len for tests and PR feedback updates * reduce context len to 16k for tests * reduce context len to 16k for tests * reduce batch size for larger context len and udpate test to check message * fix test for message --------- Co-authored-by: joecummings <jrcummings@devvm050.nha0.facebook.com> Co-authored-by: Wing Lian <wing.lian@gmail.com>
69 lines
1.2 KiB
YAML
69 lines
1.2 KiB
YAML
base_model: openlm-research/open_llama_3b_v2
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
strict: false
|
|
push_dataset_to_hub:
|
|
datasets:
|
|
- path: teknium/GPT4-LLM-Cleaned
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.02
|
|
adapter: lora
|
|
lora_model_dir:
|
|
sequence_len: 1024
|
|
sample_packing: true
|
|
lora_r: 8
|
|
lora_alpha: 16
|
|
lora_dropout: 0.0
|
|
lora_target_modules:
|
|
- gate_proj
|
|
- down_proj
|
|
- up_proj
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
lora_fan_in_fan_out:
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
output_dir: ./lora-out
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 2
|
|
num_epochs: 4
|
|
optimizer: adamw_bnb_8bit
|
|
torchdistx_path:
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: false
|
|
fp16: true
|
|
tf32: false
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
gptq_groupsize:
|
|
s2_attention:
|
|
gptq_model_v1:
|
|
warmup_steps: 20
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.1
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
bos_token: "<s>"
|
|
eos_token: "</s>"
|
|
unk_token: "<unk>"
|