Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-kimid-v1-cosine-v4-mkmlizer
Waiting for job on chaiml-kimid-v1-cosine-v4-mkmlizer to finish
chaiml-kimid-v1-cosine-v4-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v1-cosine-v4-mkmlizer: bash: no job control in this shell
chaiml-kimid-v1-cosine-v4-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-kimid-v1-cosine-v4-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v1-cosine-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ belonging to: ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ║ ║
chaiml-kimid-v1-cosine-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v1-cosine-v4-mkmlizer: Downloaded to shared memory in 38.311s
chaiml-kimid-v1-cosine-v4-mkmlizer: Checking if ChaiML/kimid-v1_cosine already exists in ChaiML
chaiml-kimid-v1-cosine-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpx656yc4x, device:0
chaiml-kimid-v1-cosine-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v1-cosine-v4-mkmlizer:
Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s]
Loading 0: 1%| | 3.00/363 [00:02<04:04, 1.48it/s]
Loading 0: 1%| | 3.00/363 [00:02<04:04, 1.48it/s]
Loading 0: 1%| | 4.00/363 [00:04<06:56, 1.16s/it]
Loading 0: 1%| | 4.00/363 [00:04<06:56, 1.16s/it]
Loading 0: 1%|▏ | 5.00/363 [00:06<08:31, 1.43s/it]
Loading 0: 1%|▏ | 5.00/363 [00:06<08:31, 1.43s/it]
Loading 0: 3%|▎ | 12.0/363 [00:08<03:40, 1.59it/s]
Loading 0: 3%|▎ | 12.0/363 [00:08<03:40, 1.59it/s]
Loading 0: 4%|▎ | 13.0/363 [00:10<04:38, 1.26it/s]
Loading 0: 4%|▎ | 13.0/363 [00:10<04:38, 1.26it/s]
Loading 0: 4%|▍ | 14.0/363 [00:12<05:45, 1.01it/s]
Loading 0: 4%|▍ | 14.0/363 [00:12<05:45, 1.01it/s]
Loading 0: 6%|▌ | 21.0/363 [00:15<03:27, 1.65it/s]
Loading 0: 6%|▌ | 21.0/363 [00:15<03:27, 1.65it/s]
Loading 0: 6%|▌ | 22.0/363 [00:17<04:15, 1.33it/s]
Loading 0: 6%|▌ | 22.0/363 [00:17<04:15, 1.33it/s]
Loading 0: 6%|▋ | 23.0/363 [00:19<05:13, 1.09it/s]
Loading 0: 6%|▋ | 23.0/363 [00:19<05:13, 1.09it/s]
Loading 0: 9%|▊ | 31.0/363 [00:20<02:29, 2.22it/s]
Loading 0: 9%|▊ | 31.0/363 [00:20<02:29, 2.22it/s]
Loading 0: 9%|▉ | 34.0/363 [00:22<02:51, 1.91it/s]
Loading 0: 9%|▉ | 34.0/363 [00:22<02:51, 1.91it/s]
Loading 0: 10%|▉ | 35.0/363 [00:24<03:38, 1.50it/s]
Loading 0: 10%|▉ | 35.0/363 [00:24<03:38, 1.50it/s]
Loading 0: 10%|▉ | 36.0/363 [00:26<04:34, 1.19it/s]
Loading 0: 10%|▉ | 36.0/363 [00:26<04:34, 1.19it/s]
Loading 0: 11%|█ | 39.0/363 [00:28<04:07, 1.31it/s]
Loading 0: 11%|█ | 39.0/363 [00:28<04:07, 1.31it/s]
Loading 0: 11%|█ | 40.0/363 [00:30<05:01, 1.07it/s]
Loading 0: 11%|█ | 40.0/363 [00:30<05:01, 1.07it/s]
Loading 0: 11%|█▏ | 41.0/363 [00:32<05:58, 1.11s/it]
Loading 0: 11%|█▏ | 41.0/363 [00:32<05:58, 1.11s/it]
Loading 0: 13%|█▎ | 48.0/363 [00:34<03:21, 1.56it/s]
Loading 0: 13%|█▎ | 48.0/363 [00:34<03:21, 1.56it/s]
Loading 0: 13%|█▎ | 49.0/363 [00:36<04:05, 1.28it/s]
Loading 0: 13%|█▎ | 49.0/363 [00:36<04:05, 1.28it/s]
Loading 0: 14%|█▍ | 50.0/363 [00:38<04:58, 1.05it/s]
Loading 0: 14%|█▍ | 50.0/363 [00:38<04:58, 1.05it/s]
Loading 0: 16%|█▌ | 57.0/363 [00:41<03:06, 1.64it/s]
Loading 0: 16%|█▌ | 57.0/363 [00:41<03:06, 1.64it/s]
Loading 0: 16%|█▌ | 58.0/363 [00:43<03:47, 1.34it/s]
Loading 0: 16%|█▌ | 58.0/363 [00:43<03:47, 1.34it/s]
Loading 0: 16%|█▋ | 59.0/363 [00:45<04:37, 1.10it/s]
Loading 0: 16%|█▋ | 59.0/363 [00:45<04:37, 1.10it/s]
Loading 0: 18%|█▊ | 65.0/363 [00:47<03:15, 1.53it/s]
Loading 0: 18%|█▊ | 65.0/363 [00:47<03:15, 1.53it/s]
Loading 0: 20%|█▉ | 71.0/363 [00:50<02:46, 1.75it/s]
Loading 0: 20%|█▉ | 71.0/363 [00:50<02:46, 1.75it/s]
Loading 0: 20%|█▉ | 72.0/363 [00:52<03:21, 1.44it/s]
Loading 0: 20%|█▉ | 72.0/363 [00:52<03:21, 1.44it/s]
Loading 0: 20%|██ | 73.0/363 [00:54<04:05, 1.18it/s]
Loading 0: 20%|██ | 73.0/363 [00:54<04:05, 1.18it/s]
Loading 0: 22%|██▏ | 79.0/363 [00:56<03:00, 1.57it/s]
Loading 0: 22%|██▏ | 79.0/363 [00:56<03:00, 1.57it/s]
Loading 0: 22%|██▏ | 80.0/363 [00:58<03:40, 1.28it/s]
Loading 0: 22%|██▏ | 80.0/363 [00:58<03:40, 1.28it/s]
Loading 0: 24%|██▎ | 86.0/363 [01:01<02:49, 1.64it/s]
Loading 0: 24%|██▎ | 86.0/363 [01:01<02:49, 1.64it/s]
Loading 0: 24%|██▍ | 87.0/363 [01:03<03:27, 1.33it/s]
Loading 0: 24%|██▍ | 87.0/363 [01:03<03:27, 1.33it/s]
Loading 0: 25%|██▍ | 90.0/363 [01:05<03:14, 1.40it/s]
Loading 0: 25%|██▍ | 90.0/363 [01:05<03:14, 1.40it/s]
Loading 0: 25%|██▌ | 91.0/363 [01:07<03:53, 1.16it/s]
Loading 0: 25%|██▌ | 91.0/363 [01:07<03:53, 1.16it/s]
Loading 0: 25%|██▌ | 92.0/363 [01:09<04:39, 1.03s/it]
Loading 0: 25%|██▌ | 92.0/363 [01:09<04:39, 1.03s/it]
Loading 0: 27%|██▋ | 99.0/363 [01:11<02:46, 1.58it/s]
Loading 0: 27%|██▋ | 99.0/363 [01:11<02:46, 1.58it/s]
Loading 0: 28%|██▊ | 100/363 [01:13<03:22, 1.30it/s]
Loading 0: 28%|██▊ | 100/363 [01:13<03:22, 1.30it/s]
Loading 0: 28%|██▊ | 101/363 [01:15<04:05, 1.07it/s]
Loading 0: 28%|██▊ | 101/363 [01:15<04:05, 1.07it/s]
Loading 0: 30%|██▉ | 108/363 [01:18<02:37, 1.62it/s]
Loading 0: 30%|██▉ | 108/363 [01:18<02:37, 1.62it/s]
Loading 0: 31%|███ | 111/363 [01:20<02:36, 1.61it/s]
Loading 0: 31%|███ | 111/363 [01:20<02:36, 1.61it/s]
Loading 0: 31%|███ | 112/363 [01:22<03:10, 1.31it/s]
Loading 0: 31%|███ | 112/363 [01:22<03:10, 1.31it/s]
Loading 0: 31%|███ | 113/363 [01:24<03:52, 1.08it/s]
Loading 0: 31%|███ | 113/363 [01:24<03:52, 1.08it/s]
Loading 0: 33%|███▎ | 120/363 [01:26<02:26, 1.65it/s]
Loading 0: 33%|███▎ | 120/363 [01:26<02:26, 1.65it/s]
Loading 0: 33%|███▎ | 121/363 [01:28<02:59, 1.35it/s]
Loading 0: 33%|███▎ | 121/363 [01:28<02:59, 1.35it/s]
Loading 0: 34%|███▎ | 122/363 [01:30<03:37, 1.11it/s]
Loading 0: 34%|███▎ | 122/363 [01:30<03:37, 1.11it/s]
Loading 0: 36%|███▌ | 129/363 [01:33<02:19, 1.68it/s]
Loading 0: 36%|███▌ | 129/363 [01:33<02:19, 1.68it/s]
Loading 0: 36%|███▌ | 130/363 [01:34<02:50, 1.37it/s]
Loading 0: 36%|███▌ | 130/363 [01:34<02:50, 1.37it/s]
Loading 0: 36%|███▌ | 131/363 [01:36<03:27, 1.12it/s]
Loading 0: 36%|███▌ | 131/363 [01:36<03:27, 1.12it/s]
Loading 0: 38%|███▊ | 138/363 [01:39<02:14, 1.67it/s]
Loading 0: 38%|███▊ | 138/363 [01:39<02:14, 1.67it/s]
Loading 0: 38%|███▊ | 139/363 [01:41<02:43, 1.37it/s]
Loading 0: 38%|███▊ | 139/363 [01:41<02:43, 1.37it/s]
Loading 0: 39%|███▊ | 140/363 [01:43<03:18, 1.12it/s]
Loading 0: 39%|███▊ | 140/363 [01:43<03:18, 1.12it/s]
Loading 0: 41%|████ | 148/363 [01:44<01:37, 2.22it/s]
Loading 0: 41%|████ | 148/363 [01:44<01:37, 2.22it/s]
Loading 0: 42%|████▏ | 151/363 [01:46<01:51, 1.90it/s]
Loading 0: 42%|████▏ | 151/363 [01:46<01:51, 1.90it/s]
Loading 0: 42%|████▏ | 152/363 [01:48<02:20, 1.50it/s]
Loading 0: 42%|████▏ | 152/363 [01:48<02:20, 1.50it/s]
Loading 0: 42%|████▏ | 153/363 [01:50<02:56, 1.19it/s]
Loading 0: 42%|████▏ | 153/363 [01:50<02:56, 1.19it/s]
Loading 0: 43%|████▎ | 156/363 [01:52<02:38, 1.31it/s]
Loading 0: 43%|████▎ | 156/363 [01:52<02:38, 1.31it/s]
Loading 0: 43%|████▎ | 157/363 [01:54<03:10, 1.08it/s]
Loading 0: 43%|████▎ | 157/363 [01:54<03:10, 1.08it/s]
Loading 0: 44%|████▎ | 158/363 [01:56<03:46, 1.11s/it]
Loading 0: 44%|████▎ | 158/363 [01:56<03:46, 1.11s/it]
Loading 0: 45%|████▌ | 165/363 [01:59<02:06, 1.56it/s]
Loading 0: 45%|████▌ | 165/363 [01:59<02:06, 1.56it/s]
Loading 0: 46%|████▌ | 166/363 [02:01<02:33, 1.28it/s]
Loading 0: 46%|████▌ | 166/363 [02:01<02:33, 1.28it/s]
Loading 0: 46%|████▌ | 167/363 [02:03<03:05, 1.05it/s]
Loading 0: 46%|████▌ | 167/363 [02:03<03:05, 1.05it/s]
Loading 0: 48%|████▊ | 174/363 [02:05<01:55, 1.64it/s]
Loading 0: 48%|████▊ | 174/363 [02:05<01:55, 1.64it/s]
Loading 0: 48%|████▊ | 175/363 [02:07<02:20, 1.34it/s]
Loading 0: 48%|████▊ | 175/363 [02:07<02:20, 1.34it/s]
Loading 0: 48%|████▊ | 176/363 [02:09<02:50, 1.10it/s]
Loading 0: 48%|████▊ | 176/363 [02:09<02:50, 1.10it/s]
Loading 0: 50%|█████ | 182/363 [02:12<01:58, 1.53it/s]
Loading 0: 50%|█████ | 182/363 [02:12<01:58, 1.53it/s]
Loading 0: 52%|█████▏ | 188/363 [02:14<01:39, 1.76it/s]
Loading 0: 52%|█████▏ | 188/363 [02:14<01:39, 1.76it/s]
Loading 0: 52%|█████▏ | 189/363 [02:16<02:01, 1.43it/s]
Loading 0: 52%|█████▏ | 189/363 [02:16<02:01, 1.43it/s]
Loading 0: 53%|█████▎ | 192/363 [02:18<01:56, 1.47it/s]
Loading 0: 53%|█████▎ | 192/363 [02:18<01:56, 1.47it/s]
Loading 0: 53%|█████▎ | 193/363 [02:20<02:19, 1.22it/s]
Loading 0: 53%|█████▎ | 193/363 [02:20<02:19, 1.22it/s]
Loading 0: 53%|█████▎ | 194/363 [02:22<02:48, 1.00it/s]
Loading 0: 53%|█████▎ | 194/363 [02:22<02:48, 1.00it/s]
Loading 0: 55%|█████▌ | 201/363 [02:25<01:40, 1.61it/s]
Loading 0: 55%|█████▌ | 201/363 [02:25<01:40, 1.61it/s]
Loading 0: 56%|█████▌ | 202/363 [02:26<02:02, 1.32it/s]
Loading 0: 56%|█████▌ | 202/363 [02:26<02:02, 1.32it/s]
Loading 0: 56%|█████▌ | 203/363 [02:28<02:27, 1.09it/s]
Loading 0: 56%|█████▌ | 203/363 [02:28<02:27, 1.09it/s]
Loading 0: 58%|█████▊ | 210/363 [02:31<01:32, 1.66it/s]
Loading 0: 58%|█████▊ | 210/363 [02:31<01:32, 1.66it/s]
Loading 0: 58%|█████▊ | 211/363 [02:33<01:52, 1.36it/s]
Loading 0: 58%|█████▊ | 211/363 [02:33<01:52, 1.36it/s]
Loading 0: 58%|█████▊ | 212/363 [02:35<02:15, 1.11it/s]
Loading 0: 58%|█████▊ | 212/363 [02:35<02:15, 1.11it/s]
Loading 0: 60%|██████ | 218/363 [02:37<01:34, 1.54it/s]
Loading 0: 60%|██████ | 218/363 [02:37<01:34, 1.54it/s]
Loading 0: 60%|██████ | 219/363 [02:39<01:55, 1.25it/s]
Loading 0: 60%|██████ | 219/363 [02:39<01:55, 1.25it/s]
Loading 0: 62%|██████▏ | 225/363 [02:42<01:26, 1.59it/s]
Loading 0: 62%|██████▏ | 225/363 [02:42<01:26, 1.59it/s]
Loading 0: 63%|██████▎ | 228/363 [02:44<01:24, 1.59it/s]
Loading 0: 63%|██████▎ | 228/363 [02:44<01:24, 1.59it/s]
Loading 0: 63%|██████▎ | 229/363 [02:46<01:42, 1.31it/s]
Loading 0: 63%|██████▎ | 229/363 [02:46<01:42, 1.31it/s]
Loading 0: 63%|██████▎ | 230/363 [02:48<02:03, 1.08it/s]
Loading 0: 63%|██████▎ | 230/363 [02:48<02:03, 1.08it/s]
Loading 0: 65%|██████▌ | 237/363 [02:50<01:16, 1.65it/s]
Loading 0: 65%|██████▌ | 237/363 [02:50<01:16, 1.65it/s]
Loading 0: 66%|██████▌ | 238/363 [02:52<01:32, 1.35it/s]
Loading 0: 66%|██████▌ | 238/363 [02:52<01:32, 1.35it/s]
Loading 0: 66%|██████▌ | 239/363 [02:54<01:52, 1.10it/s]
Loading 0: 66%|██████▌ | 239/363 [02:54<01:52, 1.10it/s]
Loading 0: 68%|██████▊ | 246/363 [02:57<01:09, 1.67it/s]
Loading 0: 68%|██████▊ | 246/363 [02:57<01:09, 1.67it/s]
Loading 0: 68%|██████▊ | 247/363 [02:59<01:24, 1.37it/s]
Loading 0: 68%|██████▊ | 247/363 [02:59<01:24, 1.37it/s]
Loading 0: 68%|██████▊ | 248/363 [03:01<01:42, 1.12it/s]
Loading 0: 68%|██████▊ | 248/363 [03:01<01:42, 1.12it/s]
Loading 0: 70%|███████ | 255/363 [03:03<01:04, 1.68it/s]
Loading 0: 70%|███████ | 255/363 [03:03<01:04, 1.68it/s]
Loading 0: 71%|███████ | 256/363 [03:05<01:17, 1.37it/s]
Loading 0: 71%|███████ | 256/363 [03:05<01:17, 1.37it/s]
Loading 0: 71%|███████ | 257/363 [03:07<01:34, 1.13it/s]
Loading 0: 71%|███████ | 257/363 [03:07<01:34, 1.13it/s]
Loading 0: 73%|███████▎ | 265/363 [03:08<00:44, 2.22it/s]
Loading 0: 73%|███████▎ | 265/363 [03:08<00:44, 2.22it/s]
Loading 0: 74%|███████▍ | 268/363 [03:11<00:49, 1.93it/s]
Loading 0: 74%|███████▍ | 268/363 [03:11<00:49, 1.93it/s]
Loading 0: 74%|███████▍ | 269/363 [03:12<01:01, 1.52it/s]
Loading 0: 74%|███████▍ | 269/363 [03:12<01:01, 1.52it/s]
Loading 0: 74%|███████▍ | 270/363 [03:14<01:17, 1.21it/s]
Loading 0: 74%|███████▍ | 270/363 [03:14<01:17, 1.21it/s]
Loading 0: 75%|███████▌ | 273/363 [03:29<03:29, 2.32s/it]
Loading 0: 75%|███████▌ | 273/363 [03:29<03:29, 2.32s/it]
Loading 0: 75%|███████▌ | 274/363 [03:31<03:21, 2.26s/it]
Loading 0: 75%|███████▌ | 274/363 [03:31<03:21, 2.26s/it]
Loading 0: 76%|███████▌ | 275/363 [03:33<03:15, 2.22s/it]
Loading 0: 76%|███████▌ | 275/363 [03:33<03:15, 2.22s/it]
Loading 0: 78%|███████▊ | 282/363 [03:36<01:24, 1.05s/it]
Loading 0: 78%|███████▊ | 282/363 [03:36<01:24, 1.05s/it]
Loading 0: 78%|███████▊ | 283/363 [03:38<01:30, 1.13s/it]
Loading 0: 78%|███████▊ | 283/363 [03:38<01:30, 1.13s/it]
Loading 0: 78%|███████▊ | 284/363 [03:40<01:38, 1.25s/it]
Loading 0: 78%|███████▊ | 284/363 [03:40<01:38, 1.25s/it]
Loading 0: 80%|████████ | 291/363 [03:42<00:52, 1.37it/s]
Loading 0: 80%|████████ | 291/363 [03:42<00:52, 1.37it/s]
Loading 0: 80%|████████ | 292/363 [03:44<01:00, 1.17it/s]
Loading 0: 80%|████████ | 292/363 [03:44<01:00, 1.17it/s]
Loading 0: 81%|████████ | 293/363 [03:46<01:10, 1.00s/it]
Loading 0: 81%|████████ | 293/363 [03:46<01:10, 1.00s/it]
Loading 0: 82%|████████▏ | 299/363 [03:49<00:44, 1.45it/s]
Loading 0: 82%|████████▏ | 299/363 [03:49<00:44, 1.45it/s]
Loading 0: 84%|████████▍ | 305/363 [03:51<00:33, 1.71it/s]
Loading 0: 84%|████████▍ | 305/363 [03:51<00:33, 1.71it/s]
Loading 0: 84%|████████▍ | 306/363 [03:53<00:40, 1.40it/s]
Loading 0: 84%|████████▍ | 306/363 [03:53<00:40, 1.40it/s]
Loading 0: 85%|████████▌ | 309/363 [03:55<00:37, 1.45it/s]
Loading 0: 85%|████████▌ | 309/363 [03:55<00:37, 1.45it/s]
Loading 0: 85%|████████▌ | 310/363 [03:57<00:44, 1.20it/s]
Loading 0: 85%|████████▌ | 310/363 [03:57<00:44, 1.20it/s]
Loading 0: 86%|████████▌ | 311/363 [03:59<00:51, 1.00it/s]
Loading 0: 86%|████████▌ | 311/363 [03:59<00:51, 1.00it/s]
Loading 0: 88%|████████▊ | 318/363 [04:02<00:27, 1.61it/s]
Loading 0: 88%|████████▊ | 318/363 [04:02<00:27, 1.61it/s]
Loading 0: 88%|████████▊ | 319/363 [04:03<00:33, 1.32it/s]
Loading 0: 88%|████████▊ | 319/363 [04:03<00:33, 1.32it/s]
Loading 0: 88%|████████▊ | 320/363 [04:05<00:39, 1.09it/s]
Loading 0: 88%|████████▊ | 320/363 [04:05<00:39, 1.09it/s]
Loading 0: 90%|█████████ | 327/363 [04:08<00:21, 1.67it/s]
Loading 0: 90%|█████████ | 327/363 [04:08<00:21, 1.67it/s]
Loading 0: 90%|█████████ | 328/363 [04:10<00:25, 1.37it/s]
Loading 0: 90%|█████████ | 328/363 [04:10<00:25, 1.37it/s]
Loading 0: 91%|█████████ | 329/363 [04:12<00:30, 1.12it/s]
Loading 0: 91%|█████████ | 329/363 [04:12<00:30, 1.12it/s]
Loading 0: 92%|█████████▏| 335/363 [04:14<00:18, 1.55it/s]
Loading 0: 92%|█████████▏| 335/363 [04:14<00:18, 1.55it/s]
Loading 0: 93%|█████████▎| 336/363 [04:16<00:21, 1.26it/s]
Loading 0: 93%|█████████▎| 336/363 [04:16<00:21, 1.26it/s]
Loading 0: 94%|█████████▍| 343/363 [04:19<00:11, 1.70it/s]
Loading 0: 94%|█████████▍| 343/363 [04:19<00:11, 1.70it/s]
Loading 0: 95%|█████████▌| 346/363 [04:21<00:10, 1.67it/s]
Loading 0: 95%|█████████▌| 346/363 [04:21<00:10, 1.67it/s]
Loading 0: 96%|█████████▌| 347/363 [04:23<00:11, 1.37it/s]
Loading 0: 96%|█████████▌| 347/363 [04:23<00:11, 1.37it/s]
Loading 0: 96%|█████████▌| 348/363 [04:25<00:13, 1.12it/s]
Loading 0: 96%|█████████▌| 348/363 [04:25<00:13, 1.12it/s]
Loading 0: 98%|█████████▊| 355/363 [04:27<00:04, 1.68it/s]
Loading 0: 98%|█████████▊| 355/363 [04:27<00:04, 1.68it/s]
Loading 0: 98%|█████████▊| 356/363 [04:29<00:05, 1.37it/s]
Loading 0: 98%|█████████▊| 356/363 [04:29<00:05, 1.37it/s]
Loading 0: 98%|█████████▊| 357/363 [04:31<00:05, 1.12it/s]
Loading 0: 98%|█████████▊| 357/363 [04:31<00:05, 1.12it/s]
Loading 0: 100%|██████████| 363/363 [04:32<00:00, 2.07it/s]
Loading 0: 100%|██████████| 363/363 [04:32<00:00, 2.07it/s]
Loading 0: 100%|██████████| 363/363 [04:32<00:00, 1.33it/s]
chaiml-kimid-v1-cosine-v4-mkmlizer: The tokenizer you are loading from '/tmp/tmpx656yc4x' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-kimid-v1-cosine-v4-mkmlizer: quantized model in 278.247s
chaiml-kimid-v1-cosine-v4-mkmlizer: Processed model ChaiML/kimid-v1_cosine in 316.558s
chaiml-kimid-v1-cosine-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v1-cosine-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v1-cosine-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia
chaiml-kimid-v1-cosine-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia/config.json
chaiml-kimid-v1-cosine-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia/special_tokens_map.json
chaiml-kimid-v1-cosine-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia/tokenizer_config.json
chaiml-kimid-v1-cosine-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia/tokenizer.json
chaiml-kimid-v1-cosine-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v1-cosine-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v1-cosine-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v1-cosine-v4-mkmlizer completed after 398.84s with status: succeeded
Stopping job with name chaiml-kimid-v1-cosine-v4-mkmlizer
Pipeline stage MKMLizer completed in 399.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v1-cosine-v4
Waiting for inference service chaiml-kimid-v1-cosine-v4 to be ready
Inference service chaiml-kimid-v1-cosine-v4 ready after 311.72365140914917s
Pipeline stage MKMLDeployer completed in 312.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.207603931427002s
Received healthy response to inference request in 2.286454200744629s
Received healthy response to inference request in 2.3295950889587402s
Received healthy response to inference request in 2.2608466148376465s
Received healthy response to inference request in 2.406236171722412s
5 requests
0 failed requests
5th percentile: 2.2182524681091307
10th percentile: 2.22890100479126
20th percentile: 2.2501980781555178
30th percentile: 2.265968132019043
40th percentile: 2.276211166381836
50th percentile: 2.286454200744629
60th percentile: 2.3037105560302735
70th percentile: 2.320966911315918
80th percentile: 2.3449233055114744
90th percentile: 2.3755797386169433
95th percentile: 2.390907955169678
99th percentile: 2.403170528411865
mean time: 2.298147201538086
Pipeline stage StressChecker completed in 12.79s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.60s
Shutdown handler de-registered
chaiml-kimid-v1-cosine_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v1-cosine-v4-profiler
Waiting for inference service chaiml-kimid-v1-cosine-v4-profiler to be ready
Inference service chaiml-kimid-v1-cosine-v4-profiler ready after 181.29817461967468s
Pipeline stage MKMLProfilerDeployer completed in 181.98s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-kimid-v1-cosine-v4-profiler-predictor-00001-deploym9flvd:/code/chaiverse_profiler_1764832102 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v1-cosine-v4-profiler-predictor-00001-deploym9flvd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1764832102 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 72 --summary /code/chaiverse_profiler_1764832102/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-kimid-v1-cosine-v4-profiler-predictor-00001-deploym9flvd:/code/chaiverse_profiler_1764832893 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v1-cosine-v4-profiler-predictor-00001-deploym9flvd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1764832893 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 72 --summary /code/chaiverse_profiler_1764832893/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-kimid-v1-cosine-v4-profiler-predictor-00001-deploym9flvd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1764832893/summary.json'
Pipeline stage MKMLProfilerRunner completed in 2374.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-kimid-v1-cosine-v4-profiler is running
Tearing down inference service chaiml-kimid-v1-cosine-v4-profiler
Service chaiml-kimid-v1-cosine-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.73s
Shutdown handler de-registered