732851f105
* restore to current phi modeling code from phi-2 * enable gradient checkpointing * don't cast everything to float32 all the time * gradient checkpointing for phi2 ParallelBlock module too * fix enabling flash attn for phi2 * add comment about import * fix phi2 example * fix model type check for tokenizer * revert float32 -> bf16 casting changes * support fused dense flash attn * fix the repo for flash-attn * add package name for subdir pkg * fix the data collator when not using sample packing * install packaging for pytests in ci * also fix setup to not install flash attn fused dense subdir if not extras * split out the fused-dense-lib in extra requires * don't train w group_by_length for phi * update integration test to use phi2 * set max steps and save steps for phi e2e tests * try to workaround ssave issue in ci * skip phi2 e2e test for now
74 lines
1.2 KiB
YAML
74 lines
1.2 KiB
YAML
base_model: microsoft/phi-2
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
trust_remote_code: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: garage-bAInd/Open-Platypus
|
|
type: alpaca
|
|
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
output_dir: ./phi-sft-out
|
|
|
|
sequence_len: 2048
|
|
sample_packing: false # currently unsupported
|
|
pad_to_sequence_len:
|
|
|
|
adapter:
|
|
lora_model_dir:
|
|
lora_r: 16
|
|
lora_alpha: 32
|
|
lora_dropout: 0.1
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
lora_modules_to_save:
|
|
- embd
|
|
- lm_head
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 4
|
|
optimizer: paged_adamw_8bit
|
|
adam_beta2: 0.95
|
|
adam_epsilon: 0.00001
|
|
max_grad_norm: 1.0
|
|
lr_scheduler: cosine
|
|
learning_rate: 1e-5
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 100
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.1
|
|
fsdp:
|
|
fsdp_config:
|
|
resize_token_embeddings_to_32x: true
|
|
special_tokens:
|
|
pad_token: "<|endoftext|>"
|