use super::*;
use crate::device::test_pool::get_test_device;
fn default_config() -> AdamConfig {
AdamConfig::new(0.001).weight_decay(0.01)
}
#[tokio::test]
async fn test_adamw_gpu_basic() {
let device = get_test_device().await;
let size = 1000;
let params = Tensor::from_vec_on(vec![1.0; size], vec![size], device.clone())
.await
.unwrap();
let gradients = Tensor::from_vec_on(vec![0.1; size], vec![size], device.clone())
.await
.unwrap();
let m = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let v = Tensor::from_vec_on(vec![0.0; size], vec![size], device)
.await
.unwrap();
let (new_params, new_m, new_v) = params
.adamw(&gradients, &m, &v, &default_config(), 1)
.unwrap();
assert_eq!(new_params.shape(), &[size]);
assert_eq!(new_m.shape(), &[size]);
assert_eq!(new_v.shape(), &[size]);
let p_data = new_params.to_vec().unwrap();
let m_data = new_m.to_vec().unwrap();
let v_data = new_v.to_vec().unwrap();
assert!(p_data.iter().all(|&x| x < 1.0));
assert!(m_data.iter().any(|&x| x.abs() > 1e-6));
assert!(v_data.iter().all(|&x| x > 0.0));
}
#[tokio::test]
async fn test_adamw_gpu_convergence() {
let device = get_test_device().await;
let size = 100;
let mut params = Tensor::from_vec_on(vec![5.0; size], vec![size], device.clone())
.await
.unwrap();
let mut m = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let mut v = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let gradients = Tensor::from_vec_on(vec![1.0; size], vec![size], device)
.await
.unwrap();
let config = AdamConfig::new(0.1).weight_decay(0.01);
for step in 1..=10 {
let (p, m_new, v_new) = params.adamw(&gradients, &m, &v, &config, step).unwrap();
params = p;
m = m_new;
v = v_new;
}
let final_params = params.to_vec().unwrap();
assert!(final_params.iter().all(|&x| x < 4.0));
}
#[tokio::test]
async fn test_adamw_gpu_weight_decay_stronger() {
let device = get_test_device().await;
let size = 100;
let params = Tensor::from_vec_on(vec![10.0; size], vec![size], device.clone())
.await
.unwrap();
let gradients = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let m = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let v = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let (new_params_wd, _, _) = params
.clone()
.adamw(
&gradients,
&m,
&v,
&AdamConfig::new(0.1).weight_decay(0.1),
1,
)
.unwrap();
let (new_params_no_wd, _, _) = params
.adamw(&gradients, &m, &v, &AdamConfig::new(0.1), 1)
.unwrap();
let wd_data = new_params_wd.to_vec().unwrap();
let no_wd_data = new_params_no_wd.to_vec().unwrap();
assert!(wd_data[0] < no_wd_data[0]);
assert!(wd_data[0] < 10.0);
}
#[tokio::test]
async fn test_adamw_gpu_shape_validation() {
let device = get_test_device().await;
let params = Tensor::from_vec_on(vec![1.0; 100], vec![100], device.clone())
.await
.unwrap();
let gradients = Tensor::from_vec_on(vec![0.1; 50], vec![50], device.clone())
.await
.unwrap();
let m = Tensor::from_vec_on(vec![0.0; 100], vec![100], device.clone())
.await
.unwrap();
let v = Tensor::from_vec_on(vec![0.0; 100], vec![100], device)
.await
.unwrap();
let result = params.adamw(&gradients, &m, &v, &default_config(), 1);
assert!(result.is_err());
}
#[tokio::test]
async fn test_adamw_gpu_multidimensional() {
let device = get_test_device().await;
let params = Tensor::from_vec_on(vec![1.0; 100], vec![10, 10], device.clone())
.await
.unwrap();
let gradients = Tensor::from_vec_on(vec![0.1; 100], vec![10, 10], device.clone())
.await
.unwrap();
let m = Tensor::from_vec_on(vec![0.0; 100], vec![10, 10], device.clone())
.await
.unwrap();
let v = Tensor::from_vec_on(vec![0.0; 100], vec![10, 10], device)
.await
.unwrap();
let (new_params, new_m, new_v) = params
.adamw(&gradients, &m, &v, &default_config(), 1)
.unwrap();
assert_eq!(new_params.shape(), &[10, 10]);
assert_eq!(new_m.shape(), &[10, 10]);
assert_eq!(new_v.shape(), &[10, 10]);
}
#[tokio::test]
async fn test_adamw_vs_adam_difference() {
let device = get_test_device().await;
let size = 100;
let params = Tensor::from_vec_on(vec![10.0; size], vec![size], device.clone())
.await
.unwrap();
let gradients = Tensor::from_vec_on(vec![0.1; size], vec![size], device.clone())
.await
.unwrap();
let m = Tensor::from_vec_on(vec![0.0; size], vec![size], device.clone())
.await
.unwrap();
let v = Tensor::from_vec_on(vec![0.0; size], vec![size], device)
.await
.unwrap();
let (adamw_params, _, _) = params
.clone()
.adamw(
&gradients,
&m,
&v,
&AdamConfig::new(0.01).weight_decay(0.1),
1,
)
.unwrap();
let adamw_data = adamw_params.to_vec().unwrap();
assert!(adamw_data.iter().all(|&x| x < 10.0));
assert!(adamw_data.iter().all(|&x| x.is_finite()));
}