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-mistral-24b-2048-77769-v1-mkmlizer
Waiting for job on chaiml-mistral-24b-2048-77769-v1-mkmlizer to finish
chaiml-mistral-24b-2048-77769-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-mistral-24b-2048-77769-v1-mkmlizer: bash: no job control in this shell
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-24b-2048-77769-v1-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-mistral-24b-2048-77769-v1-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ║ ║
chaiml-mistral-24b-2048-77769-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-24b-2048-77769-v1-mkmlizer: Downloaded to shared memory in 86.752s
chaiml-mistral-24b-2048-77769-v1-mkmlizer: Checking if ChaiML/mistral_24b_2048_funny_ds_v4_450_2k_base_merged already exists in ChaiML
chaiml-mistral-24b-2048-77769-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpo_dd1z2s, device:0
chaiml-mistral-24b-2048-77769-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-2048-77769-v1-mkmlizer:
Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s]
Loading 0: 1%| | 3.00/363 [00:02<04:26, 1.35it/s]
Loading 0: 1%| | 3.00/363 [00:02<04:26, 1.35it/s]
Loading 0: 1%| | 4.00/363 [00:04<07:11, 1.20s/it]
Loading 0: 1%| | 4.00/363 [00:04<07:11, 1.20s/it]
Loading 0: 1%|▏ | 5.00/363 [00:06<09:16, 1.55s/it]
Loading 0: 1%|▏ | 5.00/363 [00:06<09:16, 1.55s/it]
Loading 0: 3%|▎ | 11.0/363 [00:07<03:15, 1.80it/s]
Loading 0: 3%|▎ | 11.0/363 [00:07<03:15, 1.80it/s]
Loading 0: 4%|▎ | 13.0/363 [00:10<04:14, 1.37it/s]
Loading 0: 4%|▎ | 13.0/363 [00:10<04:14, 1.37it/s]
Loading 0: 4%|▍ | 14.0/363 [00:12<05:33, 1.05it/s]
Loading 0: 4%|▍ | 14.0/363 [00:12<05:33, 1.05it/s]
Loading 0: 4%|▍ | 15.0/363 [00:14<06:56, 1.20s/it]
Loading 0: 4%|▍ | 15.0/363 [00:14<06:56, 1.20s/it]
Loading 0: 6%|▌ | 21.0/363 [00:17<04:12, 1.35it/s]
Loading 0: 6%|▌ | 21.0/363 [00:17<04:12, 1.35it/s]
Loading 0: 6%|▌ | 22.0/363 [00:19<05:13, 1.09it/s]
Loading 0: 6%|▌ | 22.0/363 [00:19<05:13, 1.09it/s]
Loading 0: 6%|▋ | 23.0/363 [00:21<06:24, 1.13s/it]
Loading 0: 6%|▋ | 23.0/363 [00:21<06:24, 1.13s/it]
Loading 0: 8%|▊ | 30.0/363 [00:22<03:00, 1.85it/s]
Loading 0: 8%|▊ | 30.0/363 [00:22<03:00, 1.85it/s]
Loading 0: 9%|▉ | 34.0/363 [00:25<03:15, 1.68it/s]
Loading 0: 9%|▉ | 34.0/363 [00:25<03:15, 1.68it/s]
Loading 0: 10%|▉ | 35.0/363 [00:27<04:09, 1.31it/s]
Loading 0: 10%|▉ | 35.0/363 [00:27<04:09, 1.31it/s]
Loading 0: 10%|▉ | 36.0/363 [00:30<05:14, 1.04it/s]
Loading 0: 10%|▉ | 36.0/363 [00:30<05:14, 1.04it/s]
Loading 0: 11%|█ | 39.0/363 [00:32<04:44, 1.14it/s]
Loading 0: 11%|█ | 39.0/363 [00:32<04:44, 1.14it/s]
Loading 0: 11%|█ | 40.0/363 [00:34<05:44, 1.07s/it]
Loading 0: 11%|█ | 40.0/363 [00:34<05:44, 1.07s/it]
Loading 0: 11%|█▏ | 41.0/363 [00:36<06:52, 1.28s/it]
Loading 0: 11%|█▏ | 41.0/363 [00:36<06:52, 1.28s/it]
Loading 0: 13%|█▎ | 48.0/363 [00:38<02:59, 1.75it/s]
Loading 0: 13%|█▎ | 48.0/363 [00:38<02:59, 1.75it/s]
Loading 0: 14%|█▍ | 52.0/363 [00:40<03:11, 1.63it/s]
Loading 0: 14%|█▍ | 52.0/363 [00:40<03:11, 1.63it/s]
Loading 0: 15%|█▍ | 53.0/363 [00:43<04:03, 1.28it/s]
Loading 0: 15%|█▍ | 53.0/363 [00:43<04:03, 1.28it/s]
Loading 0: 15%|█▍ | 54.0/363 [00:45<05:04, 1.01it/s]
Loading 0: 15%|█▍ | 54.0/363 [00:45<05:04, 1.01it/s]
Loading 0: 16%|█▌ | 57.0/363 [00:47<04:33, 1.12it/s]
Loading 0: 16%|█▌ | 57.0/363 [00:47<04:33, 1.12it/s]
Loading 0: 16%|█▌ | 58.0/363 [00:49<05:30, 1.08s/it]
Loading 0: 16%|█▌ | 58.0/363 [00:49<05:30, 1.08s/it]
Loading 0: 16%|█▋ | 59.0/363 [00:51<06:33, 1.30s/it]
Loading 0: 16%|█▋ | 59.0/363 [00:51<06:33, 1.30s/it]
Loading 0: 18%|█▊ | 66.0/363 [00:53<02:49, 1.76it/s]
Loading 0: 18%|█▊ | 66.0/363 [00:53<02:49, 1.76it/s]
Loading 0: 19%|█▉ | 70.0/363 [00:55<03:00, 1.62it/s]
Loading 0: 19%|█▉ | 70.0/363 [00:55<03:00, 1.62it/s]
Loading 0: 20%|█▉ | 71.0/363 [00:58<03:49, 1.27it/s]
Loading 0: 20%|█▉ | 71.0/363 [00:58<03:49, 1.27it/s]
Loading 0: 20%|█▉ | 72.0/363 [01:00<04:47, 1.01it/s]
Loading 0: 20%|█▉ | 72.0/363 [01:00<04:47, 1.01it/s]
Loading 0: 21%|██ | 75.0/363 [01:02<04:17, 1.12it/s]
Loading 0: 21%|██ | 75.0/363 [01:02<04:17, 1.12it/s]
Loading 0: 21%|██ | 76.0/363 [01:04<05:10, 1.08s/it]
Loading 0: 21%|██ | 76.0/363 [01:04<05:10, 1.08s/it]
Loading 0: 21%|██ | 77.0/363 [01:07<06:10, 1.30s/it]
Loading 0: 21%|██ | 77.0/363 [01:07<06:10, 1.30s/it]
Loading 0: 23%|██▎ | 84.0/363 [01:08<02:39, 1.74it/s]
Loading 0: 23%|██▎ | 84.0/363 [01:08<02:39, 1.74it/s]
Loading 0: 24%|██▍ | 88.0/363 [01:10<02:49, 1.62it/s]
Loading 0: 24%|██▍ | 88.0/363 [01:10<02:49, 1.62it/s]
Loading 0: 25%|██▍ | 89.0/363 [01:13<03:35, 1.27it/s]
Loading 0: 25%|██▍ | 89.0/363 [01:13<03:35, 1.27it/s]
Loading 0: 25%|██▍ | 90.0/363 [01:15<04:30, 1.01it/s]
Loading 0: 25%|██▍ | 90.0/363 [01:15<04:30, 1.01it/s]
Loading 0: 27%|██▋ | 97.0/363 [01:16<02:16, 1.95it/s]
Loading 0: 27%|██▋ | 97.0/363 [01:16<02:16, 1.95it/s]
Loading 0: 28%|██▊ | 101/363 [01:19<02:26, 1.79it/s]
Loading 0: 28%|██▊ | 101/363 [01:19<02:26, 1.79it/s]
Loading 0: 28%|██▊ | 102/363 [01:21<03:08, 1.38it/s]
Loading 0: 28%|██▊ | 102/363 [01:21<03:08, 1.38it/s]
Loading 0: 28%|██▊ | 103/363 [01:23<04:00, 1.08it/s]
Loading 0: 28%|██▊ | 103/363 [01:23<04:00, 1.08it/s]
Loading 0: 29%|██▉ | 106/363 [01:25<03:44, 1.14it/s]
Loading 0: 29%|██▉ | 106/363 [01:25<03:44, 1.14it/s]
Loading 0: 29%|██▉ | 107/363 [01:28<04:32, 1.06s/it]
Loading 0: 29%|██▉ | 107/363 [01:28<04:32, 1.06s/it]
Loading 0: 30%|██▉ | 108/363 [01:30<05:25, 1.28s/it]
Loading 0: 30%|██▉ | 108/363 [01:30<05:25, 1.28s/it]
Loading 0: 31%|███ | 111/363 [01:32<04:24, 1.05s/it]
Loading 0: 31%|███ | 111/363 [01:32<04:24, 1.05s/it]
Loading 0: 31%|███ | 112/363 [01:34<05:11, 1.24s/it]
Loading 0: 31%|███ | 112/363 [01:34<05:11, 1.24s/it]
Loading 0: 31%|███ | 113/363 [01:37<06:00, 1.44s/it]
Loading 0: 31%|███ | 113/363 [01:37<06:00, 1.44s/it]
Loading 0: 33%|███▎ | 120/363 [01:38<02:25, 1.67it/s]
Loading 0: 33%|███▎ | 120/363 [01:38<02:25, 1.67it/s]
Loading 0: 34%|███▍ | 124/363 [01:41<02:32, 1.57it/s]
Loading 0: 34%|███▍ | 124/363 [01:41<02:32, 1.57it/s]
Loading 0: 34%|███▍ | 125/363 [01:43<03:12, 1.24it/s]
Loading 0: 34%|███▍ | 125/363 [01:43<03:12, 1.24it/s]
Loading 0: 35%|███▍ | 126/363 [01:45<04:00, 1.01s/it]
Loading 0: 35%|███▍ | 126/363 [01:45<04:00, 1.01s/it]
Loading 0: 36%|███▌ | 129/363 [01:47<03:32, 1.10it/s]
Loading 0: 36%|███▌ | 129/363 [01:47<03:32, 1.10it/s]
Loading 0: 36%|███▌ | 130/363 [01:49<04:16, 1.10s/it]
Loading 0: 36%|███▌ | 130/363 [01:49<04:16, 1.10s/it]
Loading 0: 36%|███▌ | 131/363 [01:52<05:04, 1.31s/it]
Loading 0: 36%|███▌ | 131/363 [01:52<05:04, 1.31s/it]
Loading 0: 38%|███▊ | 138/363 [01:53<02:09, 1.74it/s]
Loading 0: 38%|███▊ | 138/363 [01:53<02:09, 1.74it/s]
Loading 0: 39%|███▉ | 142/363 [01:56<02:18, 1.60it/s]
Loading 0: 39%|███▉ | 142/363 [01:56<02:18, 1.60it/s]
Loading 0: 39%|███▉ | 143/363 [01:58<02:54, 1.26it/s]
Loading 0: 39%|███▉ | 143/363 [01:58<02:54, 1.26it/s]
Loading 0: 40%|███▉ | 144/363 [02:00<03:38, 1.00it/s]
Loading 0: 40%|███▉ | 144/363 [02:00<03:38, 1.00it/s]
Loading 0: 40%|████ | 147/363 [02:02<03:14, 1.11it/s]
Loading 0: 40%|████ | 147/363 [02:02<03:14, 1.11it/s]
Loading 0: 41%|████ | 148/363 [02:05<04:04, 1.14s/it]
Loading 0: 41%|████ | 148/363 [02:05<04:04, 1.14s/it]
Loading 0: 41%|████ | 149/363 [02:07<04:47, 1.34s/it]
Loading 0: 41%|████ | 149/363 [02:07<04:47, 1.34s/it]
Loading 0: 43%|████▎ | 156/363 [02:08<02:01, 1.71it/s]
Loading 0: 43%|████▎ | 156/363 [02:08<02:01, 1.71it/s]
Loading 0: 44%|████▍ | 160/363 [02:11<02:06, 1.60it/s]
Loading 0: 44%|████▍ | 160/363 [02:11<02:06, 1.60it/s]
Loading 0: 44%|████▍ | 161/363 [02:13<02:40, 1.26it/s]
Loading 0: 44%|████▍ | 161/363 [02:13<02:40, 1.26it/s]
Loading 0: 45%|████▍ | 162/363 [02:16<03:20, 1.00it/s]
Loading 0: 45%|████▍ | 162/363 [02:16<03:20, 1.00it/s]
Loading 0: 45%|████▌ | 165/363 [02:18<02:58, 1.11it/s]
Loading 0: 45%|████▌ | 165/363 [02:18<02:58, 1.11it/s]
Loading 0: 46%|████▌ | 166/363 [02:20<03:34, 1.09s/it]
Loading 0: 46%|████▌ | 166/363 [02:20<03:34, 1.09s/it]
Loading 0: 46%|████▌ | 167/363 [02:22<04:14, 1.30s/it]
Loading 0: 46%|████▌ | 167/363 [02:22<04:14, 1.30s/it]
Loading 0: 48%|████▊ | 174/363 [02:23<01:48, 1.75it/s]
Loading 0: 48%|████▊ | 174/363 [02:23<01:48, 1.75it/s]
Loading 0: 49%|████▉ | 178/363 [02:27<02:00, 1.54it/s]
Loading 0: 49%|████▉ | 178/363 [02:27<02:00, 1.54it/s]
Loading 0: 49%|████▉ | 179/363 [02:29<02:30, 1.23it/s]
Loading 0: 49%|████▉ | 179/363 [02:29<02:30, 1.23it/s]
Loading 0: 50%|████▉ | 180/363 [02:31<03:05, 1.02s/it]
Loading 0: 50%|████▉ | 180/363 [02:31<03:05, 1.02s/it]
Loading 0: 50%|█████ | 183/363 [02:33<02:44, 1.10it/s]
Loading 0: 50%|█████ | 183/363 [02:33<02:44, 1.10it/s]
Loading 0: 51%|█████ | 184/363 [02:35<03:16, 1.10s/it]
Loading 0: 51%|█████ | 184/363 [02:35<03:16, 1.10s/it]
Loading 0: 51%|█████ | 185/363 [02:38<03:52, 1.31s/it]
Loading 0: 51%|█████ | 185/363 [02:38<03:52, 1.31s/it]
Loading 0: 53%|█████▎ | 192/363 [02:39<01:37, 1.75it/s]
Loading 0: 53%|█████▎ | 192/363 [02:39<01:37, 1.75it/s]
Loading 0: 54%|█████▍ | 196/363 [02:42<01:42, 1.63it/s]
Loading 0: 54%|█████▍ | 196/363 [02:42<01:42, 1.63it/s]
Loading 0: 54%|█████▍ | 197/363 [02:44<02:10, 1.28it/s]
Loading 0: 54%|█████▍ | 197/363 [02:44<02:10, 1.28it/s]
Loading 0: 55%|█████▍ | 198/363 [02:46<02:43, 1.01it/s]
Loading 0: 55%|█████▍ | 198/363 [02:46<02:43, 1.01it/s]
Loading 0: 55%|█████▌ | 201/363 [02:48<02:24, 1.12it/s]
Loading 0: 55%|█████▌ | 201/363 [02:48<02:24, 1.12it/s]
Loading 0: 56%|█████▌ | 202/363 [02:50<02:54, 1.08s/it]
Loading 0: 56%|█████▌ | 202/363 [02:50<02:54, 1.08s/it]
Loading 0: 56%|█████▌ | 203/363 [02:53<03:26, 1.29s/it]
Loading 0: 56%|█████▌ | 203/363 [02:53<03:26, 1.29s/it]
Loading 0: 58%|█████▊ | 210/363 [02:54<01:27, 1.76it/s]
Loading 0: 58%|█████▊ | 210/363 [02:54<01:27, 1.76it/s]
Loading 0: 59%|█████▉ | 214/363 [02:57<01:31, 1.62it/s]
Loading 0: 59%|█████▉ | 214/363 [02:57<01:31, 1.62it/s]
Loading 0: 59%|█████▉ | 215/363 [02:59<01:56, 1.27it/s]
Loading 0: 59%|█████▉ | 215/363 [02:59<01:56, 1.27it/s]
Loading 0: 60%|█████▉ | 216/363 [03:01<02:25, 1.01it/s]
Loading 0: 60%|█████▉ | 216/363 [03:01<02:25, 1.01it/s]
Loading 0: 60%|██████ | 219/363 [03:03<02:08, 1.12it/s]
Loading 0: 60%|██████ | 219/363 [03:03<02:08, 1.12it/s]
Loading 0: 61%|██████ | 220/363 [03:05<02:34, 1.08s/it]
Loading 0: 61%|██████ | 220/363 [03:05<02:34, 1.08s/it]
Loading 0: 61%|██████ | 221/363 [03:08<03:03, 1.29s/it]
Loading 0: 61%|██████ | 221/363 [03:08<03:03, 1.29s/it]
Loading 0: 63%|██████▎ | 228/363 [03:09<01:16, 1.76it/s]
Loading 0: 63%|██████▎ | 228/363 [03:09<01:16, 1.76it/s]
Loading 0: 64%|██████▍ | 232/363 [03:12<01:20, 1.64it/s]
Loading 0: 64%|██████▍ | 232/363 [03:12<01:20, 1.64it/s]
Loading 0: 64%|██████▍ | 233/363 [03:14<01:41, 1.28it/s]
Loading 0: 64%|██████▍ | 233/363 [03:14<01:41, 1.28it/s]
Loading 0: 64%|██████▍ | 234/363 [03:16<02:06, 1.02it/s]
Loading 0: 64%|██████▍ | 234/363 [03:16<02:06, 1.02it/s]
Loading 0: 65%|██████▌ | 237/363 [03:18<01:52, 1.12it/s]
Loading 0: 65%|██████▌ | 237/363 [03:18<01:52, 1.12it/s]
Loading 0: 66%|██████▌ | 238/363 [03:20<02:14, 1.08s/it]
Loading 0: 66%|██████▌ | 238/363 [03:20<02:14, 1.08s/it]
Loading 0: 66%|██████▌ | 239/363 [03:23<02:40, 1.29s/it]
Loading 0: 66%|██████▌ | 239/363 [03:23<02:40, 1.29s/it]
Loading 0: 68%|██████▊ | 246/363 [03:24<01:06, 1.76it/s]
Loading 0: 68%|██████▊ | 246/363 [03:24<01:06, 1.76it/s]
Loading 0: 69%|██████▉ | 250/363 [03:27<01:09, 1.63it/s]
Loading 0: 69%|██████▉ | 250/363 [03:27<01:09, 1.63it/s]
Loading 0: 69%|██████▉ | 251/363 [03:29<01:27, 1.28it/s]
Loading 0: 69%|██████▉ | 251/363 [03:29<01:27, 1.28it/s]
Loading 0: 69%|██████▉ | 252/363 [03:31<01:49, 1.01it/s]
Loading 0: 69%|██████▉ | 252/363 [03:31<01:49, 1.01it/s]
Loading 0: 70%|███████ | 255/363 [03:33<01:36, 1.12it/s]
Loading 0: 70%|███████ | 255/363 [03:33<01:36, 1.12it/s]
Loading 0: 71%|███████ | 256/363 [03:35<01:55, 1.08s/it]
Loading 0: 71%|███████ | 256/363 [03:35<01:55, 1.08s/it]
Loading 0: 71%|███████ | 257/363 [03:38<02:17, 1.30s/it]
Loading 0: 71%|███████ | 257/363 [03:38<02:17, 1.30s/it]
Loading 0: 73%|███████▎ | 264/363 [03:39<00:56, 1.74it/s]
Loading 0: 73%|███████▎ | 264/363 [03:39<00:56, 1.74it/s]
Loading 0: 74%|███████▍ | 268/363 [03:42<00:58, 1.62it/s]
Loading 0: 74%|███████▍ | 268/363 [03:42<00:58, 1.62it/s]
Loading 0: 74%|███████▍ | 269/363 [03:44<01:13, 1.27it/s]
Loading 0: 74%|███████▍ | 269/363 [03:44<01:13, 1.27it/s]
Loading 0: 74%|███████▍ | 270/363 [03:46<01:31, 1.01it/s]
Loading 0: 74%|███████▍ | 270/363 [03:46<01:31, 1.01it/s]
Loading 0: 75%|███████▌ | 273/363 [04:03<03:57, 2.64s/it]
Loading 0: 75%|███████▌ | 273/363 [04:03<03:57, 2.64s/it]
Loading 0: 75%|███████▌ | 274/363 [04:05<03:49, 2.57s/it]
Loading 0: 75%|███████▌ | 274/363 [04:05<03:49, 2.57s/it]
Loading 0: 76%|███████▌ | 275/363 [04:07<03:42, 2.53s/it]
Loading 0: 76%|███████▌ | 275/363 [04:07<03:42, 2.53s/it]
Loading 0: 78%|███████▊ | 282/363 [04:08<01:22, 1.02s/it]
Loading 0: 78%|███████▊ | 282/363 [04:08<01:22, 1.02s/it]
Loading 0: 79%|███████▉ | 286/363 [04:11<01:09, 1.11it/s]
Loading 0: 79%|███████▉ | 286/363 [04:11<01:09, 1.11it/s]
Loading 0: 79%|███████▉ | 287/363 [04:13<01:18, 1.04s/it]
Loading 0: 79%|███████▉ | 287/363 [04:13<01:18, 1.04s/it]
Loading 0: 79%|███████▉ | 288/363 [04:15<01:30, 1.20s/it]
Loading 0: 79%|███████▉ | 288/363 [04:15<01:30, 1.20s/it]
Loading 0: 80%|████████ | 291/363 [04:17<01:14, 1.03s/it]
Loading 0: 80%|████████ | 291/363 [04:17<01:14, 1.03s/it]
Loading 0: 80%|████████ | 292/363 [04:20<01:25, 1.20s/it]
Loading 0: 80%|████████ | 292/363 [04:20<01:25, 1.20s/it]
Loading 0: 81%|████████ | 293/363 [04:22<01:37, 1.40s/it]
Loading 0: 81%|████████ | 293/363 [04:22<01:37, 1.40s/it]
Loading 0: 83%|████████▎ | 300/363 [04:23<00:38, 1.64it/s]
Loading 0: 83%|████████▎ | 300/363 [04:23<00:38, 1.64it/s]
Loading 0: 84%|████████▎ | 304/363 [04:26<00:38, 1.53it/s]
Loading 0: 84%|████████▎ | 304/363 [04:26<00:38, 1.53it/s]
Loading 0: 84%|████████▍ | 305/363 [04:28<00:47, 1.22it/s]
Loading 0: 84%|████████▍ | 305/363 [04:28<00:47, 1.22it/s]
Loading 0: 84%|████████▍ | 306/363 [04:31<00:58, 1.02s/it]
Loading 0: 84%|████████▍ | 306/363 [04:31<00:58, 1.02s/it]
Loading 0: 85%|████████▌ | 309/363 [04:33<00:49, 1.09it/s]
Loading 0: 85%|████████▌ | 309/363 [04:33<00:49, 1.09it/s]
Loading 0: 85%|████████▌ | 310/363 [04:35<00:58, 1.10s/it]
Loading 0: 85%|████████▌ | 310/363 [04:35<00:58, 1.10s/it]
Loading 0: 86%|████████▌ | 311/363 [04:37<01:08, 1.31s/it]
Loading 0: 86%|████████▌ | 311/363 [04:37<01:08, 1.31s/it]
Loading 0: 88%|████████▊ | 318/363 [04:38<00:25, 1.74it/s]
Loading 0: 88%|████████▊ | 318/363 [04:38<00:25, 1.74it/s]
Loading 0: 89%|████████▊ | 322/363 [04:41<00:25, 1.62it/s]
Loading 0: 89%|████████▊ | 322/363 [04:41<00:25, 1.62it/s]
Loading 0: 89%|████████▉ | 323/363 [04:43<00:31, 1.27it/s]
Loading 0: 89%|████████▉ | 323/363 [04:43<00:31, 1.27it/s]
Loading 0: 89%|████████▉ | 324/363 [04:45<00:38, 1.01it/s]
Loading 0: 89%|████████▉ | 324/363 [04:45<00:38, 1.01it/s]
Loading 0: 90%|█████████ | 327/363 [04:48<00:32, 1.12it/s]
Loading 0: 90%|█████████ | 327/363 [04:48<00:32, 1.12it/s]
Loading 0: 90%|█████████ | 328/363 [04:50<00:37, 1.08s/it]
Loading 0: 90%|█████████ | 328/363 [04:50<00:37, 1.08s/it]
Loading 0: 91%|█████████ | 329/363 [04:52<00:44, 1.30s/it]
Loading 0: 91%|█████████ | 329/363 [04:52<00:44, 1.30s/it]
Loading 0: 92%|█████████▏| 335/363 [04:53<00:17, 1.60it/s]
Loading 0: 92%|█████████▏| 335/363 [04:53<00:17, 1.60it/s]
Loading 0: 94%|█████████▎| 340/363 [04:56<00:14, 1.61it/s]
Loading 0: 94%|█████████▎| 340/363 [04:56<00:14, 1.61it/s]
Loading 0: 94%|█████████▍| 341/363 [04:58<00:17, 1.27it/s]
Loading 0: 94%|█████████▍| 341/363 [04:58<00:17, 1.27it/s]
Loading 0: 94%|█████████▍| 342/363 [05:01<00:20, 1.02it/s]
Loading 0: 94%|█████████▍| 342/363 [05:01<00:20, 1.02it/s]
Loading 0: 95%|█████████▌| 345/363 [05:03<00:16, 1.12it/s]
Loading 0: 95%|█████████▌| 345/363 [05:03<00:16, 1.12it/s]
Loading 0: 95%|█████████▌| 346/363 [05:05<00:18, 1.08s/it]
Loading 0: 95%|█████████▌| 346/363 [05:05<00:18, 1.08s/it]
Loading 0: 96%|█████████▌| 347/363 [05:07<00:20, 1.30s/it]
Loading 0: 96%|█████████▌| 347/363 [05:07<00:20, 1.30s/it]
Loading 0: 98%|█████████▊| 354/363 [05:09<00:05, 1.74it/s]
Loading 0: 98%|█████████▊| 354/363 [05:09<00:05, 1.74it/s]
Loading 0: 99%|█████████▉| 359/363 [05:12<00:02, 1.66it/s]
Loading 0: 99%|█████████▉| 359/363 [05:12<00:02, 1.66it/s]
Loading 0: 99%|█████████▉| 360/363 [05:14<00:02, 1.31it/s]
Loading 0: 99%|█████████▉| 360/363 [05:14<00:02, 1.31it/s]
Loading 0: 99%|█████████▉| 361/363 [05:16<00:01, 1.05it/s]
Loading 0: 99%|█████████▉| 361/363 [05:16<00:01, 1.05it/s]
Loading 0: 100%|██████████| 363/363 [05:16<00:00, 1.05it/s]
Loading 0: 100%|██████████| 363/363 [05:16<00:00, 1.15it/s]
chaiml-mistral-24b-2048-77769-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpo_dd1z2s' 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-mistral-24b-2048-77769-v1-mkmlizer: quantized model in 324.248s
chaiml-mistral-24b-2048-77769-v1-mkmlizer: Processed model ChaiML/mistral_24b_2048_funny_ds_v4_450_2k_base_merged in 411.001s
chaiml-mistral-24b-2048-77769-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-2048-77769-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-2048-77769-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia
chaiml-mistral-24b-2048-77769-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia/config.json
chaiml-mistral-24b-2048-77769-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia/special_tokens_map.json
chaiml-mistral-24b-2048-77769-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia/tokenizer_config.json
chaiml-mistral-24b-2048-77769-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia/tokenizer.json
chaiml-mistral-24b-2048-77769-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia/flywheel_model.1.safetensors
chaiml-mistral-24b-2048-77769-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-77769-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral-24b-2048-77769-v1-mkmlizer completed after 499.68s with status: succeeded
Stopping job with name chaiml-mistral-24b-2048-77769-v1-mkmlizer
Pipeline stage MKMLizer completed in 500.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.68s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-24b-2048-77769-v1
Waiting for inference service chaiml-mistral-24b-2048-77769-v1 to be ready
Inference service chaiml-mistral-24b-2048-77769-v1 ready after 171.0559949874878s
Pipeline stage MKMLDeployer completed in 171.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.091554641723633s
Received healthy response to inference request in 2.8402676582336426s
Received healthy response to inference request in 3.1253297328948975s
Received healthy response to inference request in 3.232215166091919s
Received healthy response to inference request in 3.0060160160064697s
5 requests
0 failed requests
5th percentile: 2.873417329788208
10th percentile: 2.9065670013427733
20th percentile: 2.972866344451904
30th percentile: 3.0231237411499023
40th percentile: 3.0573391914367676
50th percentile: 3.091554641723633
60th percentile: 3.1050646781921385
70th percentile: 3.1185747146606446
80th percentile: 3.1467068195343018
90th percentile: 3.1894609928131104
95th percentile: 3.2108380794525146
99th percentile: 3.227939748764038
mean time: 3.0590766429901124
Pipeline stage StressChecker completed in 16.45s
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 0.61s
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 0.57s
Shutdown handler de-registered
chaiml-mistral-24b-2048_77769_v1 status is now deployed due to DeploymentManager action
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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-24b-2048-77769-v1-profiler
Waiting for inference service chaiml-mistral-24b-2048-77769-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2947.08s
Shutdown handler de-registered
chaiml-mistral-24b-2048_77769_v1 status is now torndown due to DeploymentManager action