Skip to content

CI

CI #3600

Triggered via schedule November 30, 2024 09:31
Status Failure
Total duration 18h 4m 49s
Artifacts 99

ci.yaml

on: schedule
metadata
0s
metadata
bump-manifest
34s
bump-manifest
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
amd64  /  ...  /  build-base
4m 25s
amd64 / build-base / build-base
arm64  /  ...  /  build-base
4m 35s
arm64 / build-base / build-base
amd64  /  ...  /  build-jax
25m 40s
amd64 / build-jax / build-jax
arm64  /  ...  /  build-jax
34m 19s
arm64 / build-jax / build-jax
amd64  /  ...  /  build-upstream-pax
7m 2s
amd64 / build-upstream-pax / build-upstream-pax
Matrix: amd64 / test-jax / run-unit-test
Matrix: amd64 / test-nsys-jax / run-unit-test
amd64  /  ...  /  build-upstream-t5x
6m 30s
amd64 / build-upstream-t5x / build-upstream-t5x
amd64  /  ...  /  launch-slurm-runner
47m 50s
amd64 / test-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
56m 35s
amd64 / test-nsys-jax / runner / launch-slurm-runner
amd64  /  ...  /  build-gemma
6m 13s
amd64 / build-gemma / build-gemma
amd64  /  ...  /  build-levanter
4m 38s
amd64 / build-levanter / build-levanter
amd64  /  ...  /  build-maxtext
8m 25s
amd64 / build-maxtext / build-maxtext
amd64  /  ...  /  build-triton
11m 27s
amd64 / build-triton / build-triton
amd64  /  ...  /  build-equinox
3m 41s
amd64 / build-equinox / build-equinox
arm64  /  ...  /  build-upstream-pax
21m 46s
arm64 / build-upstream-pax / build-upstream-pax
Matrix: arm64 / test-jax / run-unit-test
Waiting for pending jobs
Matrix: arm64 / test-nsys-jax / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  build-upstream-t5x
42m 47s
arm64 / build-upstream-t5x / build-upstream-t5x
arm64  /  ...  /  launch-slurm-runner
arm64 / test-jax / runner / launch-slurm-runner
arm64  /  ...  /  launch-slurm-runner
arm64 / test-nsys-jax / runner / launch-slurm-runner
arm64  /  ...  /  build
arm64 / build-gemma / build
arm64  /  ...  /  build-levanter
6m 7s
arm64 / build-levanter / build-levanter
arm64  /  ...  /  build-maxtext
1h 39m
arm64 / build-maxtext / build-maxtext
arm64  /  ...  /  build
arm64 / build-triton / build
arm64  /  ...  /  build-equinox
4m 37s
arm64 / build-equinox / build-equinox
amd64  /  ...  /  build-rosetta
6m 43s
amd64 / build-rosetta-pax / build-rosetta
Matrix: amd64 / test-te / run-unit-test
amd64  /  ...  /  launch-slurm-runner
3h 7m
amd64 / test-te / runner / launch-slurm-runner
Matrix: amd64 / test-upstream-pax / pax-multi-node
Matrix: amd64 / test-upstream-pax / single-process-evaluation
Matrix: amd64 / test-upstream-pax / single-process-multi-device
Matrix: amd64 / test-te-multigpu / te-multi-gpu
amd64  /  ...  /  build-rosetta
17m 3s
amd64 / build-rosetta-t5x / build-rosetta
Matrix: amd64 / test-upstream-t5x / t5x-multi-gpu
Matrix: amd64 / test-upstream-t5x / t5x-multi-node
Matrix: amd64 / test-gemma / run-unit-test
amd64  /  ...  /  launch-slurm-runner
1h 11m
amd64 / test-gemma / runner / launch-slurm-runner
Matrix: amd64 / test-levanter / run-unit-test
amd64  /  ...  /  launch-slurm-runner
1h 11m
amd64 / test-levanter / runner / launch-slurm-runner
Matrix: amd64 / test-maxtext / maxtext-multinode
Matrix: amd64 / test-maxtext / single-process-multi-device
Matrix: amd64 / test-triton / run-unit-test
amd64  /  ...  /  launch-slurm-runner
1h 15m
amd64 / test-triton / runner / launch-slurm-runner
arm64  /  ...  /  build-rosetta
arm64 / build-rosetta-pax / build-rosetta
Matrix: arm64 / test-te / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  launch-slurm-runner
arm64 / test-te / runner / launch-slurm-runner
Matrix: arm64 / test-upstream-pax / pax-multi-node
Waiting for pending jobs
Matrix: arm64 / test-upstream-pax / single-process-evaluation
Waiting for pending jobs
Matrix: arm64 / test-upstream-pax / single-process-multi-device
Waiting for pending jobs
Matrix: arm64 / test-te-multigpu / te-multi-gpu
Waiting for pending jobs
arm64  /  ...  /  build-rosetta
arm64 / build-rosetta-t5x / build-rosetta
Matrix: arm64 / test-upstream-t5x / t5x-multi-gpu
Waiting for pending jobs
Matrix: arm64 / test-upstream-t5x / t5x-multi-node
Waiting for pending jobs
Matrix: arm64 / test-gemma / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  launch-slurm-runner
arm64 / test-gemma / runner / launch-slurm-runner
Matrix: arm64 / test-levanter / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  launch-slurm-runner
arm64 / test-levanter / runner / launch-slurm-runner
Matrix: arm64 / test-maxtext / maxtext-multinode
Waiting for pending jobs
Matrix: arm64 / test-maxtext / single-process-multi-device
Waiting for pending jobs
Matrix: arm64 / test-triton / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  launch-slurm-runner
arm64 / test-triton / runner / launch-slurm-runner
Matrix: amd64 / test-rosetta-pax / rosetta-pax-multi-node-te
Matrix: amd64 / test-rosetta-pax / rosetta-pax-multi-node
Matrix: amd64 / test-rosetta-pax / rosetta-pax-single-node-dropout-te
Matrix: amd64 / test-rosetta-pax / single-process-evaluation-te
Matrix: amd64 / test-rosetta-pax / single-process-multi-device-te
amd64  /  ...  /  test-upstream-pax-summary
0s
amd64 / test-upstream-pax / test-upstream-pax-summary
amd64  /  ...  /  test-upstream-pax-metrics
0s
amd64 / test-upstream-pax / test-upstream-pax-metrics
amd64  /  ...  /  sitrep
5s
amd64 / test-te-multigpu / sitrep
amd64  /  collect-docker-tags
0s
amd64 / collect-docker-tags
Matrix: amd64 / test-rosetta-t5x / multi-gpu-multi-node
Matrix: amd64 / test-rosetta-t5x / single-process-multi-device
Matrix: amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node
Matrix: amd64 / test-rosetta-t5x / vit-single-process-multi-device
amd64  /  ...  /  test-upstream-t5x-summary
0s
amd64 / test-upstream-t5x / test-upstream-t5x-summary
amd64  /  ...  /  test-upstream-t5x-metrics
0s
amd64 / test-upstream-t5x / test-upstream-t5x-metrics
amd64  /  ...  /  test-maxtext-summary
0s
amd64 / test-maxtext / test-maxtext-summary
amd64  /  ...  /  test-maxtext-metrics
0s
amd64 / test-maxtext / test-maxtext-metrics
Matrix: arm64 / test-rosetta-pax / rosetta-pax-multi-node-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / rosetta-pax-multi-node
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / rosetta-pax-single-node-dropout-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / single-process-evaluation-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / single-process-multi-device-te
Waiting for pending jobs
arm64  /  ...  /  test-upstream-pax-summary
arm64 / test-upstream-pax / test-upstream-pax-summary
arm64  /  ...  /  test-upstream-pax-metrics
arm64 / test-upstream-pax / test-upstream-pax-metrics
arm64  /  ...  /  sitrep
arm64 / test-te-multigpu / sitrep
arm64  /  collect-docker-tags
0s
arm64 / collect-docker-tags
Matrix: arm64 / test-rosetta-t5x / multi-gpu-multi-node
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / single-process-multi-device
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / vit-multi-gpu-multi-node
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / vit-single-process-multi-device
Waiting for pending jobs
arm64  /  ...  /  test-upstream-t5x-summary
arm64 / test-upstream-t5x / test-upstream-t5x-summary
arm64  /  ...  /  test-upstream-t5x-metrics
arm64 / test-upstream-t5x / test-upstream-t5x-metrics
arm64  /  ...  /  test-maxtext-summary
arm64 / test-maxtext / test-maxtext-summary
arm64  /  ...  /  test-maxtext-metrics
arm64 / test-maxtext / test-maxtext-metrics
amd64  /  ...  /  test-pax-rosetta-summary
0s
amd64 / test-rosetta-pax / test-pax-rosetta-summary
amd64  /  ...  /  test-pax-rosetta-metrics
0s
amd64 / test-rosetta-pax / test-pax-rosetta-metrics
amd64  /  ...  /  sitrep
15s
amd64 / test-upstream-pax / test-upstream-pax-sitrep / sitrep
amd64  /  ...  /  test-t5x-rosetta-summary
0s
amd64 / test-rosetta-t5x / test-t5x-rosetta-summary
amd64  /  ...  /  test-t5x-rosetta-metrics
0s
amd64 / test-rosetta-t5x / test-t5x-rosetta-metrics
amd64  /  ...  /  sitrep
12s
amd64 / test-upstream-t5x / test-upstream-t5x-sitrep / sitrep
amd64  /  ...  /  sitrep
12s
amd64 / test-maxtext / test-maxtext-sitrep / sitrep
arm64  /  ...  /  test-pax-rosetta-summary
arm64 / test-rosetta-pax / test-pax-rosetta-summary
arm64  /  ...  /  test-pax-rosetta-metrics
arm64 / test-rosetta-pax / test-pax-rosetta-metrics
arm64  /  ...  /  sitrep
arm64 / test-upstream-pax / test-upstream-pax-sitrep / sitrep
arm64  /  ...  /  test-t5x-rosetta-summary
arm64 / test-rosetta-t5x / test-t5x-rosetta-summary
arm64  /  ...  /  test-t5x-rosetta-metrics
arm64 / test-rosetta-t5x / test-t5x-rosetta-metrics
arm64  /  ...  /  sitrep
arm64 / test-upstream-t5x / test-upstream-t5x-sitrep / sitrep
arm64  /  ...  /  sitrep
arm64 / test-maxtext / test-maxtext-sitrep / sitrep
amd64  /  ...  /  sitrep
13s
amd64 / test-rosetta-pax / test-pax-rosetta-sitrep / sitrep
amd64  /  ...  /  test-upstream-pax-outcome
0s
amd64 / test-upstream-pax / test-upstream-pax-outcome
amd64  /  ...  /  sitrep
16s
amd64 / test-rosetta-t5x / test-t5x-rosetta-sitrep / sitrep
amd64  /  ...  /  test-upstream-t5x-outcome
0s
amd64 / test-upstream-t5x / test-upstream-t5x-outcome
amd64  /  ...  /  test-maxtext-outcome
0s
amd64 / test-maxtext / test-maxtext-outcome
arm64  /  ...  /  sitrep
arm64 / test-rosetta-pax / test-pax-rosetta-sitrep / sitrep
arm64  /  ...  /  test-upstream-pax-outcome
arm64 / test-upstream-pax / test-upstream-pax-outcome
arm64  /  ...  /  sitrep
arm64 / test-rosetta-t5x / test-t5x-rosetta-sitrep / sitrep
arm64  /  ...  /  test-upstream-t5x-outcome
arm64 / test-upstream-t5x / test-upstream-t5x-outcome
arm64  /  ...  /  test-maxtext-outcome
arm64 / test-maxtext / test-maxtext-outcome
amd64  /  ...  /  test-pax-rosetta-outcome
0s
amd64 / test-rosetta-pax / test-pax-rosetta-outcome
amd64  /  ...  /  test-t5x-rosetta-outcome
amd64 / test-rosetta-t5x / test-t5x-rosetta-outcome
arm64  /  ...  /  test-pax-rosetta-outcome
arm64 / test-rosetta-pax / test-pax-rosetta-outcome
arm64  /  ...  /  test-t5x-rosetta-outcome
arm64 / test-rosetta-t5x / test-t5x-rosetta-outcome
make-publish-configs
3s
make-publish-configs
merge-new-manifest
8s
merge-new-manifest
Matrix: publish-containers
finalize  /  workflow-badge
6s
finalize / workflow-badge
finalize  /  report
21s
finalize / report
finalize  /  upload-badge
6s
finalize / upload-badge
finalize  /  publish-badge
7s
finalize / publish-badge
Fit to window
Zoom out
Zoom in

Annotations

33 errors and 2 warnings
arm64 / build-upstream-pax / build-upstream-pax
buildx failed with: ERROR: failed to solve: process "/bin/sh -c pip-finalize.sh" did not complete successfully: exit code: 1
amd64 / test-jax / jax-A100-unit-test
Process completed with exit code 1.
arm64 / build-upstream-t5x / build-upstream-t5x
buildx failed with: ERROR: failed to solve: process "/bin/sh -c pip-finalize.sh" did not complete successfully: exit code: 1
amd64 / test-levanter / levanter-V100-unit-test
Process completed with exit code 1.
amd64 / test-levanter / levanter-A100-unit-test
Process completed with exit code 1.
arm64 / build-maxtext / build-maxtext
buildx failed with: ERROR: failed to solve: process "/bin/sh -c pip-finalize.sh" did not complete successfully: exit code: 1
amd64 / test-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
The job running on runner jumpbox-vc69x-6pk8c has exceeded the maximum execution time of 360 minutes.
amd64 / test-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
The operation was canceled.
amd64 / test-rosetta-t5x / multi-gpu-multi-node (2N8G-te-1, 8, 2, --gin.train/utils.DatasetConfig.pack=False --gin.train_eva...
The job running on runner jumpbox-vc69x-2btv4 has exceeded the maximum execution time of 360 minutes.
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 2)
The job running on runner jumpbox-vc69x-srxbs has exceeded the maximum execution time of 360 minutes.
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 2)
The operation was canceled.
amd64 / test-rosetta-pax / rosetta-pax-multi-node (4, 2, 1, 2)
The job running on runner jumpbox-vc69x-l2b5j has exceeded the maximum execution time of 360 minutes.
amd64 / test-rosetta-pax / rosetta-pax-multi-node (4, 2, 1, 2)
The operation was canceled.
amd64 / test-rosetta-pax / rosetta-pax-multi-node-te (16DP1FSDP1TP1PP_TE, 1, 16, 1, 1, 4)
The job running on runner jumpbox-vc69x-g6x9w has exceeded the maximum execution time of 360 minutes.
amd64 / test-maxtext / maxtext-multinode (1, 4, 2, 2)
The job running on runner jumpbox-vc69x-dzr76 has exceeded the maximum execution time of 360 minutes.
amd64 / test-maxtext / maxtext-multinode (1, 4, 2, 2)
The operation was canceled.
amd64 / test-maxtext / test-maxtext-outcome
Process completed with exit code 1.
amd64 / test-upstream-pax / pax-multi-node (16DP1FSDP1TP1PP, 1, 16, 1, 1, 4)
The job running on runner jumpbox-vc69x-s8bff has exceeded the maximum execution time of 360 minutes.
amd64 / test-rosetta-pax / test-pax-rosetta-outcome
Process completed with exit code 1.
amd64 / test-upstream-t5x / t5x-multi-node (8G2N_fmha, 8, 2, --enable-fmha 1)
The job running on runner jumpbox-vc69x-kb8t8 has exceeded the maximum execution time of 360 minutes.
amd64 / test-upstream-t5x / test-upstream-t5x-outcome
Process completed with exit code 1.
amd64 / test-rosetta-t5x / multi-gpu-multi-node (2N2G_te-0, 2, 2, --enable-te 0)
The job running on runner jumpbox-vc69x-5zsv2 has exceeded the maximum execution time of 360 minutes.
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (8, 2)
The job running on runner jumpbox-vc69x-fd8zl has exceeded the maximum execution time of 360 minutes.
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (8, 2)
The operation was canceled.
amd64 / test-rosetta-t5x / test-t5x-rosetta-outcome
Process completed with exit code 1.
amd64 / test-upstream-pax / pax-multi-node (2DP1FSDP2TP4PP, 4, 2, 1, 2, 4)
The job running on runner jumpbox-vc69x-pdzpp has exceeded the maximum execution time of 360 minutes.
amd64 / test-upstream-pax / test-upstream-pax-outcome
Process completed with exit code 1.
merge-new-manifest
Unexpected input(s) 'owner_and_repo', valid inputs are ['route', 'mediaType']
merge-new-manifest
Unexpected input(s) 'owner_and_repo', 'head', 'base', 'body', 'title', 'draft', valid inputs are ['route', 'mediaType']

Artifacts

Produced during runtime
Name Size
artifact-base-build-amd64
567 Bytes
artifact-base-build-arm64
567 Bytes
artifact-equinox-build-amd64
571 Bytes
artifact-equinox-build-arm64
569 Bytes
artifact-final-report
5.09 KB
artifact-gemma-build-amd64
560 Bytes
artifact-jax-build-amd64
553 Bytes
artifact-jax-build-arm64
553 Bytes
artifact-levanter-build-amd64
572 Bytes
artifact-levanter-build-arm64
574 Bytes
artifact-maxtext-build-amd64
567 Bytes
artifact-maxtext-build-arm64
515 Bytes
artifact-maxtext-test
654 Bytes
artifact-pax-build-amd64
567 Bytes
artifact-pax-build-arm64
514 Bytes
artifact-rosetta-build-pax-amd64
582 Bytes
artifact-rosetta-build-t5x-amd64
583 Bytes
artifact-rosetta-pax-mgmn-test
737 Bytes
artifact-rosetta-t5x-mgmn-test
658 Bytes
artifact-t5x-build-amd64
569 Bytes
artifact-t5x-build-arm64
515 Bytes
artifact-triton-build-amd64
564 Bytes
artifact-upstream-pax-mgmn-test
688 Bytes
artifact-upstream-t5x-mgmn-test
634 Bytes
artifact-workflow-metadata
278 Bytes
bumped-manifest
80.1 KB
final-base
249 Bytes
final-equinox
258 Bytes
final-gemma
252 Bytes
final-jax
246 Bytes
final-levanter
261 Bytes
final-maxtext
258 Bytes
final-pax
246 Bytes
final-t5x
246 Bytes
final-triton
255 Bytes
final-upstream-pax
273 Bytes
final-upstream-t5x
273 Bytes
gemma-unit-test-A100
5.23 KB
gemma-unit-test-V100
3.96 KB
jax-unit-test-A100
21.3 KB
jax-unit-test-V100
26.4 KB
levanter-unit-test-A100
13.1 KB
levanter-unit-test-V100
15.3 KB
mealkit-equinox
270 Bytes
mealkit-gemma
263 Bytes
mealkit-jax
256 Bytes
mealkit-levanter
273 Bytes
mealkit-maxtext
269 Bytes
mealkit-pax
258 Bytes
mealkit-t5x
258 Bytes
mealkit-triton
266 Bytes
mealkit-upstream-pax
283 Bytes
mealkit-upstream-t5x
283 Bytes
nsys-jax-unit-test-A100
29.3 MB
nsys-jax-unit-test-V100
16 MB
rosetta-pax-12095330964-1DP1FSDP1TP1PP_TE
92.4 KB
rosetta-pax-12095330964-1DP2FSDP4TP1PP_single_process_TE
112 KB
rosetta-pax-12095330964-1DP8FSDP1TP1PP_TE
384 KB
rosetta-pax-12095330964-2DP1FSDP1TP4PP
247 KB
rosetta-pax-12095330964-4DP1FSDP2TP1PP
403 KB
rosetta-pax-12095330964-4DP1FSDP2TP1PP_TE
380 KB
rosetta-pax-12095330964-5B_fused_attn_0
418 KB
rosetta-pax-12095330964-5B_fused_attn_1
431 KB
rosetta-pax-12095330964-8DP1FSDP1TP1PP
406 KB
rosetta-pax-12095330964-8DP1FSDP1TP1PP_TE
379 KB
rosetta-pax-12095330964-8DP1FSDP1TP1PP_eval_TE
90 KB
rosetta-pax-12095330964-8DP1FSDP1TP1PP_single_process_TE
112 KB
rosetta-pax-12095330964-8DP_TE_dropout
384 KB
rosetta-pax-12095330964-LLaMA_eval_TE
255 KB
rosetta-t5x-12095330964-1P1G_te-0
35.3 KB
rosetta-t5x-12095330964-1P8G_te-1
35.3 KB
rosetta-t5x-vit-12095330964-VIT1G1N
21.6 KB
rosetta-t5x-vit-12095330964-VIT1P8G
21.8 KB
rosetta-t5x-vit-12095330964-VIT8G1N
33.2 KB
te-2GPU
5.37 KB
te-4GPU
5.39 KB
te-8GPU
5.44 KB
te-multigpu-test
528 Bytes
te-unit-test-A100
840 KB
te-unit-test-V100
679 KB
triton-unit-test-A100
5.81 KB
triton-unit-test-V100
5.83 KB
upstream-maxtext-12095330964-1DP1FSDP1TP1PP
14.8 KB
upstream-maxtext-12095330964-1DP1FSDP8TP1PP
21.2 KB
upstream-maxtext-12095330964-1DP2FSDP4TP1PP_single_process
15.2 KB
upstream-maxtext-12095330964-1DP4FSDP2TP1PP
20.9 KB
upstream-maxtext-12095330964-1DP8FSDP1TP1PP
20.9 KB
upstream-maxtext-12095330964-2DP2FSDP2TP1PP
21.2 KB
upstream-pax-12095330964-1DP1FSDP1TP1PP
147 KB
upstream-pax-12095330964-1DP2FSDP4TP1PP_single_process
147 KB
upstream-pax-12095330964-1DP8FSDP1TP1PP
449 KB
upstream-pax-12095330964-2DP1FSDP1TP4PP
325 KB
upstream-pax-12095330964-4DP1FSDP2TP1PP
454 KB
upstream-pax-12095330964-8DP1FSDP1TP1PP
448 KB
upstream-pax-12095330964-8DP1FSDP1TP1PP_eval
120 KB
upstream-pax-12095330964-8DP1FSDP1TP1PP_single_process
147 KB
upstream-pax-12095330964-LLaMA_eval
260 KB
upstream-t5x-12095330964-1P2G_fmha
34.1 KB
upstream-t5x-12095330964-1P8G
33.6 KB