9f824ef76a
* simplify the example configs to be more minimal and less daunting * drop empty s2_attention from example yamls
63 lines
1.2 KiB
YAML
63 lines
1.2 KiB
YAML
base_model: microsoft/Phi-3-mini-4k-instruct
|
|
# optionally might have model_type or tokenizer_type
|
|
trust_remote_code: true
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
chat_template: phi_3
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: garage-bAInd/Open-Platypus
|
|
type: alpaca:phi
|
|
|
|
dataset_prepared_path:
|
|
val_set_size: 0.01
|
|
output_dir: ./out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 64
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 2
|
|
num_epochs: 1
|
|
optimizer: adamw_torch_fused
|
|
adam_beta2: 0.95
|
|
adam_epsilon: 0.00001
|
|
max_grad_norm: 1.0
|
|
lr_scheduler: cosine
|
|
learning_rate: 5.0e-6
|
|
|
|
bf16: auto
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: True
|
|
early_stopping_patience: 3
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
eval_steps: 1000
|
|
save_steps: 5000
|
|
eval_batch_size: 2
|
|
eval_sample_packing: false
|
|
eval_table_size: 2
|
|
eval_max_new_tokens: 32
|
|
eval_causal_lm_metrics: ["perplexity"]
|
|
do_causal_lm_eval: true
|
|
|
|
warmup_ratio: 0.2
|
|
debug: true
|
|
weight_decay: 0.1
|
|
resize_token_embeddings_to_32x: true
|