a1da39cd48
* Feat: Update to handle wandb env better * chore: rename wandb_run_id to wandb_name * feat: add new recommendation and update config * fix: indent and pop disabled env if project passed * feat: test env set for wandb and recommendation * feat: update to use wandb_name and allow id * chore: add info to readme
73 lines
1.2 KiB
YAML
73 lines
1.2 KiB
YAML
base_model: NousResearch/Llama-2-7b-hf
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_llama_derived_model: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: mhenrichsen/alpaca_2k_test
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.05
|
|
output_dir: ./out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
adapter:
|
|
lora_model_dir:
|
|
lora_r:
|
|
lora_alpha:
|
|
lora_dropout:
|
|
lora_target_linear:
|
|
lora_fan_in_fan_out:
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
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
|
|
flash_attn_cross_entropy: false
|
|
flash_attn_rms_norm: true
|
|
flash_attn_fuse_qkv: false
|
|
flash_attn_fuse_mlp: true
|
|
|
|
warmup_steps: 100
|
|
eval_steps: 0.05
|
|
eval_table_size:
|
|
save_steps:
|
|
debug:
|
|
deepspeed: #deepspeed/zero2.json # multi-gpu only
|
|
weight_decay: 0.1
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
bos_token: "<s>"
|
|
eos_token: "</s>"
|
|
unk_token: "<unk>"
|