20 lines
423 B
YAML
20 lines
423 B
YAML
|
model_name: "EleutherAI/pythia-6.9b-deduped"
|
||
|
|
log_with: "wandb"
|
||
|
|
learning_rate: 1e-5
|
||
|
|
lr_scheduler_type: cosine
|
||
|
|
num_warmup_steps: 100
|
||
|
|
weight_decay: 0.05
|
||
|
|
load_in_8bit: True
|
||
|
|
use_peft: True
|
||
|
|
lora_r: 8
|
||
|
|
lora_alpha: 16
|
||
|
|
lora_dropout: 0.05
|
||
|
|
bf16: False
|
||
|
|
streaming: False
|
||
|
|
gradient_checkpointing: False
|
||
|
|
gradient_accumulation_steps: 8
|
||
|
|
per_device_train_batch_size: 2
|
||
|
|
per_device_eval_batch_size: 2
|
||
|
|
train_completions: True
|
||
|
|
num_train_epochs: 2
|