[LLM] Rewrite GSM8K reward function to follow standard GRPO conventions #4457
vmoensnightly_build.yml
on: pull_request
Matrix: build-wheel-unix
Matrix: build-wheel-windows
Matrix: test-wheel-unix
Matrix: test-wheel-windows
Matrix: upload-wheel-unix
Matrix: upload-wheel-windows
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
torchrl-linux-3.10_cpu.whl
|
8.39 MB |
sha256:e76b7c5a2c23c8d48da4ad2aa6ce7550c04e75302444ab99861e80a91e5adfe4
|
|
|
torchrl-linux-3.11_cpu.whl
|
8.42 MB |
sha256:05e828b258d18ae2d7e8f3a0d93597e43302aa277ed4af83d6e7b2b50b67abef
|
|
|
torchrl-linux-3.12_cpu.whl
|
8.4 MB |
sha256:4d58d50f41c553e09100378c952e604da868024f6bcb862e703e3651a3e49903
|
|
|
torchrl-linux-3.13_cpu.whl
|
8.4 MB |
sha256:aea6c01a1c9bc02370720dc2540cab2e499eb3ee873ba301a4527834c0b94ca2
|
|
|
torchrl-linux-3.14_cpu.whl
|
8.39 MB |
sha256:ae6fdda85fe122b2b0ca5b9d8fb7ee241df9e80bd37cb7e37194e078d8a21d56
|
|
|
torchrl-macos-3.10_cpu.whl
|
2.2 MB |
sha256:9c03538b299e4fce6b0e29b581e08e81383b8e6eeb2591245601802da81ae838
|
|
|
torchrl-macos-3.11_cpu.whl
|
2.2 MB |
sha256:f087daf9afb2000da5265996253c36088c59cacb35e6e38c62f2f43234ddd4bc
|
|
|
torchrl-macos-3.12_cpu.whl
|
2.19 MB |
sha256:f89e6a5a263b9a7acd430367fe154ff4747f87e0f133b69139830cf8417a03d5
|
|
|
torchrl-macos-3.13_cpu.whl
|
2.19 MB |
sha256:724298f4a4a6878c9891a056cea9e8bfc8db5778d0741e0448a18f3101490ffd
|
|
|
torchrl-macos-3.14_cpu.whl
|
2.19 MB |
sha256:6e2b1e4c09d0fdcc55cb81621f835654f433adf83d5bb52398be81fdb951eb60
|
|
|
torchrl-win-3.10.whl
|
1.95 MB |
sha256:956c1dc7bba10795bb14c525fb6721bce23b7a6aeca48e08183d85f573bf0927
|
|
|
torchrl-win-3.11.whl
|
1.95 MB |
sha256:b2e40206988cab76dd7e8754c13e2053ab00ce12c0e22645e7528356db7754fe
|
|
|
torchrl-win-3.12.whl
|
1.96 MB |
sha256:2fcb35cff606cf224c524edb41118bf52ed704ec5e8f5642bbd65c4a7f83f8ca
|
|
|
torchrl-win-3.13.whl
|
1.96 MB |
sha256:3ba3a4b0e7186fb6079bb81166cf54b52b312d3f5a6eda301e891486c046bb2f
|
|
|
torchrl-win-3.14.whl
|
1.96 MB |
sha256:c96c2c8df694d42ce213f8c433b498bcb084a8b3bc5fccb6c1599863765a66d6
|
|