Download code/tests/test_reference.py from jisue/robottt-pi05-base-comparison: direct link, hf CLI and curl.
- Browser
- Download file 1.91 kB
-
https://huggingface.co/jisue/robottt-pi05-base-comparison/resolve/main/code/tests/test_reference.py
- Command line
-
hf download hf://jisue/robottt-pi05-base-comparison/code/tests/test_reference.py
-
curl -L -o test_reference.py https://huggingface.co/jisue/robottt-pi05-base-comparison/resolve/main/code/tests/test_reference.py
1.91 kB
| """Parity of the state bridge against the unchanged OpenTau scan.""" | |
| import copy,unittest | |
| import torch | |
| try: | |
| from robottt_pi05.reference_core_adapter import ReferenceLayer | |
| except ModuleNotFoundError as error: | |
| if error.name!='einops':raise | |
| ReferenceLayer=None | |
| from robottt_pi05.optimization import learning_rate | |
| class ReferenceParityTests(unittest.TestCase): | |
| def test_sequential_bridge_equals_native_scan_and_gradients(self): | |
| torch.manual_seed(9);wrapped=ReferenceLayer(width=16).double();native=copy.deepcopy(wrapped) | |
| x=torch.randn(1,3*26,16,dtype=torch.float64) | |
| state=wrapped.initial_state(1);outputs=[] | |
| for t in range(3): | |
| y,state=wrapped.step(x[:,t*26:(t+1)*26],state,differentiable=True);outputs.append(y) | |
| sequence=torch.cat(outputs,1) | |
| y,fast=native.core(x,mini_batch_size=26) | |
| expected=native.gate(x,y) | |
| torch.testing.assert_close(sequence,expected,rtol=1e-12,atol=1e-12) | |
| for a,b in zip(state.weights,(fast.w1,fast.b1,fast.w2,fast.b2)):torch.testing.assert_close(a,b,rtol=1e-12,atol=1e-12) | |
| sequence.square().mean().backward();expected.square().mean().backward() | |
| for (an,ap),(bn,bp) in zip(wrapped.named_parameters(),native.named_parameters()): | |
| self.assertEqual(an,bn);self.assertIsNotNone(ap.grad) | |
| torch.testing.assert_close(ap.grad,bp.grad,rtol=1e-9,atol=1e-11) | |
| self.assertEqual(state.updates.tolist(),[3]) | |
| def test_explicit_schedule(self): | |
| self.assertAlmostEqual(learning_rate(0,'opentau_3000'),1e-4/101) | |
| self.assertAlmostEqual(learning_rate(3000,'opentau_3000'),1e-5) | |
| self.assertGreater(learning_rate(99,'opentau_3000'),learning_rate(0,'opentau_3000')) | |
| self.assertEqual(learning_rate(10000,'opentau_3000'),learning_rate(3000,'opentau_3000')) | |