developer_uid: rirv938
submission_id: chaiml-mistral-24b-2048-_9638_v3
model_name: chaiml-mistral-24b-2048-_9638_v3
model_group: ChaiML/mistral_24b_2048_
status: torndown
timestamp: 2026-01-14T16:59:18+00:00
num_battles: 10463
num_wins: 5475
celo_rating: 1311.71
family_friendly_score: 0.49
family_friendly_standard_error: 0.007069653456853455
submission_type: basic
model_repo: ChaiML/mistral_24b_2048_opus_v1_2500_20k_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 96
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3419688454750782, 'latency_mean': 2.9241632628440857, 'latency_p50': 2.919792652130127, 'latency_p90': 3.128870129585266}, {'batch_size': 2, 'throughput': 0.5294065306448407, 'latency_mean': 3.7690852069854737, 'latency_p50': 3.7676676511764526, 'latency_p90': 3.9885373592376707}, {'batch_size': 3, 'throughput': 0.6614029931895347, 'latency_mean': 4.518410960435867, 'latency_p50': 4.534663200378418, 'latency_p90': 4.7774677038192745}, {'batch_size': 4, 'throughput': 0.754628459712278, 'latency_mean': 5.277520238161087, 'latency_p50': 5.279932856559753, 'latency_p90': 5.869391775131225}, {'batch_size': 5, 'throughput': 0.8190721055701407, 'latency_mean': 6.077685080766678, 'latency_p50': 6.07553768157959, 'latency_p90': 6.519681406021118}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mistral-24b-2048-_9638_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/mistral_24b_2048_opus_v1_2500_20k_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.52
us_pacific_date: 2026-01-09
win_ratio: 0.5232724839912071
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '<|im_end|>', '</s>', '###', '\n', '<|im_start|>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 96}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
Resubmit model
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-2048-9638-v3-mkmlizer
Waiting for job on chaiml-mistral-24b-2048-9638-v3-mkmlizer to finish
chaiml-mistral-24b-2048-9638-v3-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-mistral-24b-2048-9638-v3-mkmlizer: bash: no job control in this shell
chaiml-mistral-24b-2048-9638-v3-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-2048-9638-v3-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-9638-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-24b-2048-9638-v3-mkmlizer: Downloaded to shared memory in 67.846s
chaiml-mistral-24b-2048-9638-v3-mkmlizer: Checking if ChaiML/mistral_24b_2048_opus_v1_2500_20k_merged already exists in ChaiML
chaiml-mistral-24b-2048-9638-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp75txo718, device:0
chaiml-mistral-24b-2048-9638-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-2048-9638-v3-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:54, 1.53it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:54, 1.53it/s]
Loading 0:   1%|          | 4.00/363 [00:03<06:18, 1.05s/it]
Loading 0:   1%|          | 4.00/363 [00:03<06:18, 1.05s/it]
Loading 0:   1%|▏         | 5.00/363 [00:05<08:06, 1.36s/it]
Loading 0:   1%|▏         | 5.00/363 [00:05<08:06, 1.36s/it]
Loading 0:   3%|▎         | 12.0/363 [00:07<02:40, 2.19it/s]
Loading 0:   3%|▎         | 12.0/363 [00:07<02:40, 2.19it/s]
Loading 0:   4%|▎         | 13.0/363 [00:09<03:55, 1.48it/s]
Loading 0:   4%|▎         | 13.0/363 [00:09<03:55, 1.48it/s]
Loading 0:   4%|▍         | 14.0/363 [00:11<05:04, 1.15it/s]
Loading 0:   4%|▍         | 14.0/363 [00:11<05:04, 1.15it/s]
Loading 0:   4%|▍         | 15.0/363 [00:13<06:17, 1.08s/it]
Loading 0:   4%|▍         | 15.0/363 [00:13<06:17, 1.08s/it]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:45, 1.52it/s]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:45, 1.52it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:38, 1.22it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:38, 1.22it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:40, 1.00s/it]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:40, 1.00s/it]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:31, 2.19it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:31, 2.19it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:53, 1.90it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:53, 1.90it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:41, 1.48it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:41, 1.48it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:40, 1.17it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:40, 1.17it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:11, 1.29it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:11, 1.29it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:04, 1.06it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:04, 1.06it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:03, 1.13s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:03, 1.13s/it]
Loading 0:  13%|█▎        | 49.0/363 [00:33<02:29, 2.10it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:33<02:29, 2.10it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:35<02:48, 1.84it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:35<02:48, 1.84it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:37<03:35, 1.44it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:37<03:35, 1.44it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:39<04:30, 1.14it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:39<04:30, 1.14it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:41<04:01, 1.27it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:41<04:01, 1.27it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<04:51, 1.05it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<04:51, 1.05it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:45<05:46, 1.14s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:45<05:46, 1.14s/it]
Loading 0:  18%|█▊        | 67.0/363 [00:46<02:21, 2.09it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:46<02:21, 2.09it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:49<02:40, 1.83it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:49<02:40, 1.83it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:50<03:23, 1.43it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:50<03:23, 1.43it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:52<04:14, 1.14it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:52<04:14, 1.14it/s]
Loading 0:  21%|██        | 75.0/363 [00:54<03:46, 1.27it/s]
Loading 0:  21%|██        | 75.0/363 [00:54<03:46, 1.27it/s]
Loading 0:  21%|██        | 76.0/363 [00:56<04:33, 1.05it/s]
Loading 0:  21%|██        | 76.0/363 [00:56<04:33, 1.05it/s]
Loading 0:  21%|██        | 77.0/363 [00:58<05:26, 1.14s/it]
Loading 0:  21%|██        | 77.0/363 [00:58<05:26, 1.14s/it]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:13, 2.08it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:13, 2.08it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:02<02:30, 1.83it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:02<02:30, 1.83it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:04<03:11, 1.43it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:04<03:11, 1.43it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:06<03:59, 1.14it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:06<03:59, 1.14it/s]
Loading 0:  27%|██▋       | 98.0/363 [01:07<01:54, 2.30it/s]
Loading 0:  27%|██▋       | 98.0/363 [01:07<01:54, 2.30it/s]
Loading 0:  28%|██▊       | 101/363 [01:09<02:10, 2.01it/s] 
Loading 0:  28%|██▊       | 101/363 [01:09<02:10, 2.01it/s]
Loading 0:  28%|██▊       | 102/363 [01:11<02:48, 1.55it/s]
Loading 0:  28%|██▊       | 102/363 [01:11<02:48, 1.55it/s]
Loading 0:  28%|██▊       | 103/363 [01:13<03:33, 1.22it/s]
Loading 0:  28%|██▊       | 103/363 [01:13<03:33, 1.22it/s]
Loading 0:  29%|██▉       | 106/363 [01:15<03:18, 1.30it/s]
Loading 0:  29%|██▉       | 106/363 [01:15<03:18, 1.30it/s]
Loading 0:  29%|██▉       | 107/363 [01:17<03:59, 1.07it/s]
Loading 0:  29%|██▉       | 107/363 [01:17<03:59, 1.07it/s]
Loading 0:  30%|██▉       | 108/363 [01:19<04:46, 1.12s/it]
Loading 0:  30%|██▉       | 108/363 [01:19<04:46, 1.12s/it]
Loading 0:  31%|███       | 111/363 [01:21<03:51, 1.09it/s]
Loading 0:  31%|███       | 111/363 [01:21<03:51, 1.09it/s]
Loading 0:  31%|███       | 112/363 [01:23<04:31, 1.08s/it]
Loading 0:  31%|███       | 112/363 [01:23<04:31, 1.08s/it]
Loading 0:  31%|███       | 113/363 [01:25<05:15, 1.26s/it]
Loading 0:  31%|███       | 113/363 [01:25<05:15, 1.26s/it]
Loading 0:  33%|███▎      | 121/363 [01:26<01:59, 2.02it/s]
Loading 0:  33%|███▎      | 121/363 [01:26<01:59, 2.02it/s]
Loading 0:  34%|███▍      | 124/363 [01:28<02:13, 1.79it/s]
Loading 0:  34%|███▍      | 124/363 [01:28<02:13, 1.79it/s]
Loading 0:  34%|███▍      | 125/363 [01:30<02:49, 1.41it/s]
Loading 0:  34%|███▍      | 125/363 [01:30<02:49, 1.41it/s]
Loading 0:  35%|███▍      | 126/363 [01:32<03:31, 1.12it/s]
Loading 0:  35%|███▍      | 126/363 [01:32<03:31, 1.12it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<03:06, 1.25it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<03:06, 1.25it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<03:44, 1.04it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<03:44, 1.04it/s]
Loading 0:  36%|███▌      | 131/363 [01:38<04:27, 1.15s/it]
Loading 0:  36%|███▌      | 131/363 [01:38<04:27, 1.15s/it]
Loading 0:  38%|███▊      | 139/363 [01:39<01:47, 2.09it/s]
Loading 0:  38%|███▊      | 139/363 [01:39<01:47, 2.09it/s]
Loading 0:  39%|███▉      | 142/363 [01:41<02:00, 1.83it/s]
Loading 0:  39%|███▉      | 142/363 [01:41<02:00, 1.83it/s]
Loading 0:  39%|███▉      | 143/363 [01:43<02:33, 1.43it/s]
Loading 0:  39%|███▉      | 143/363 [01:43<02:33, 1.43it/s]
Loading 0:  40%|███▉      | 144/363 [01:45<03:11, 1.14it/s]
Loading 0:  40%|███▉      | 144/363 [01:45<03:11, 1.14it/s]
Loading 0:  40%|████      | 147/363 [01:47<02:50, 1.27it/s]
Loading 0:  40%|████      | 147/363 [01:47<02:50, 1.27it/s]
Loading 0:  41%|████      | 148/363 [01:49<03:25, 1.05it/s]
Loading 0:  41%|████      | 148/363 [01:49<03:25, 1.05it/s]
Loading 0:  41%|████      | 149/363 [01:51<04:04, 1.14s/it]
Loading 0:  41%|████      | 149/363 [01:51<04:04, 1.14s/it]
Loading 0:  43%|████▎     | 157/363 [01:52<01:39, 2.08it/s]
Loading 0:  43%|████▎     | 157/363 [01:52<01:39, 2.08it/s]
Loading 0:  44%|████▍     | 160/363 [01:54<01:51, 1.83it/s]
Loading 0:  44%|████▍     | 160/363 [01:54<01:51, 1.83it/s]
Loading 0:  44%|████▍     | 161/363 [01:56<02:21, 1.43it/s]
Loading 0:  44%|████▍     | 161/363 [01:56<02:21, 1.43it/s]
Loading 0:  45%|████▍     | 162/363 [01:58<02:56, 1.14it/s]
Loading 0:  45%|████▍     | 162/363 [01:58<02:56, 1.14it/s]
Loading 0:  45%|████▌     | 165/363 [02:00<02:36, 1.27it/s]
Loading 0:  45%|████▌     | 165/363 [02:00<02:36, 1.27it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<03:08, 1.04it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<03:08, 1.04it/s]
Loading 0:  46%|████▌     | 167/363 [02:04<03:44, 1.15s/it]
Loading 0:  46%|████▌     | 167/363 [02:04<03:44, 1.15s/it]
Loading 0:  48%|████▊     | 175/363 [02:05<01:30, 2.08it/s]
Loading 0:  48%|████▊     | 175/363 [02:05<01:30, 2.08it/s]
Loading 0:  49%|████▉     | 178/363 [02:07<01:41, 1.83it/s]
Loading 0:  49%|████▉     | 178/363 [02:07<01:41, 1.83it/s]
Loading 0:  49%|████▉     | 179/363 [02:09<02:08, 1.43it/s]
Loading 0:  49%|████▉     | 179/363 [02:09<02:08, 1.43it/s]
Loading 0:  50%|████▉     | 180/363 [02:11<02:40, 1.14it/s]
Loading 0:  50%|████▉     | 180/363 [02:11<02:40, 1.14it/s]
Loading 0:  50%|█████     | 183/363 [02:13<02:22, 1.27it/s]
Loading 0:  50%|█████     | 183/363 [02:13<02:22, 1.27it/s]
Loading 0:  51%|█████     | 184/363 [02:15<02:53, 1.03it/s]
Loading 0:  51%|█████     | 184/363 [02:15<02:53, 1.03it/s]
Loading 0:  51%|█████     | 185/363 [02:17<03:25, 1.15s/it]
Loading 0:  51%|█████     | 185/363 [02:17<03:25, 1.15s/it]
Loading 0:  53%|█████▎    | 193/363 [02:18<01:21, 2.09it/s]
Loading 0:  53%|█████▎    | 193/363 [02:18<01:21, 2.09it/s]
Loading 0:  54%|█████▍    | 196/363 [02:21<01:31, 1.83it/s]
Loading 0:  54%|█████▍    | 196/363 [02:21<01:31, 1.83it/s]
Loading 0:  54%|█████▍    | 197/363 [02:22<01:55, 1.43it/s]
Loading 0:  54%|█████▍    | 197/363 [02:22<01:55, 1.43it/s]
Loading 0:  55%|█████▍    | 198/363 [02:24<02:24, 1.14it/s]
Loading 0:  55%|█████▍    | 198/363 [02:24<02:24, 1.14it/s]
Loading 0:  55%|█████▌    | 201/363 [02:26<02:07, 1.27it/s]
Loading 0:  55%|█████▌    | 201/363 [02:26<02:07, 1.27it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:33, 1.05it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:33, 1.05it/s]
Loading 0:  56%|█████▌    | 203/363 [02:30<03:02, 1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [02:30<03:02, 1.14s/it]
Loading 0:  58%|█████▊    | 211/363 [02:31<01:12, 2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [02:31<01:12, 2.08it/s]
Loading 0:  59%|█████▉    | 214/363 [02:34<01:21, 1.83it/s]
Loading 0:  59%|█████▉    | 214/363 [02:34<01:21, 1.83it/s]
Loading 0:  59%|█████▉    | 215/363 [02:36<01:43, 1.43it/s]
Loading 0:  59%|█████▉    | 215/363 [02:36<01:43, 1.43it/s]
Loading 0:  60%|█████▉    | 216/363 [02:38<02:08, 1.14it/s]
Loading 0:  60%|█████▉    | 216/363 [02:38<02:08, 1.14it/s]
Loading 0:  60%|██████    | 219/363 [02:39<01:53, 1.27it/s]
Loading 0:  60%|██████    | 219/363 [02:39<01:53, 1.27it/s]
Loading 0:  61%|██████    | 220/363 [02:41<02:16, 1.05it/s]
Loading 0:  61%|██████    | 220/363 [02:41<02:16, 1.05it/s]
Loading 0:  61%|██████    | 221/363 [02:43<02:42, 1.14s/it]
Loading 0:  61%|██████    | 221/363 [02:43<02:42, 1.14s/it]
Loading 0:  63%|██████▎   | 229/363 [02:45<01:03, 2.10it/s]
Loading 0:  63%|██████▎   | 229/363 [02:45<01:03, 2.10it/s]
Loading 0:  64%|██████▍   | 232/363 [02:47<01:11, 1.84it/s]
Loading 0:  64%|██████▍   | 232/363 [02:47<01:11, 1.84it/s]
Loading 0:  64%|██████▍   | 233/363 [02:49<01:30, 1.44it/s]
Loading 0:  64%|██████▍   | 233/363 [02:49<01:30, 1.44it/s]
Loading 0:  64%|██████▍   | 234/363 [02:51<01:52, 1.14it/s]
Loading 0:  64%|██████▍   | 234/363 [02:51<01:52, 1.14it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:39, 1.27it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:39, 1.27it/s]
Loading 0:  66%|██████▌   | 238/363 [02:54<01:59, 1.05it/s]
Loading 0:  66%|██████▌   | 238/363 [02:54<01:59, 1.05it/s]
Loading 0:  66%|██████▌   | 239/363 [02:56<02:21, 1.14s/it]
Loading 0:  66%|██████▌   | 239/363 [02:56<02:21, 1.14s/it]
Loading 0:  68%|██████▊   | 247/363 [02:58<00:55, 2.09it/s]
Loading 0:  68%|██████▊   | 247/363 [02:58<00:55, 2.09it/s]
Loading 0:  69%|██████▉   | 250/363 [03:00<01:01, 1.83it/s]
Loading 0:  69%|██████▉   | 250/363 [03:00<01:01, 1.83it/s]
Loading 0:  69%|██████▉   | 251/363 [03:02<01:18, 1.43it/s]
Loading 0:  69%|██████▉   | 251/363 [03:02<01:18, 1.43it/s]
Loading 0:  69%|██████▉   | 252/363 [03:04<01:37, 1.14it/s]
Loading 0:  69%|██████▉   | 252/363 [03:04<01:37, 1.14it/s]
Loading 0:  70%|███████   | 255/363 [03:06<01:25, 1.27it/s]
Loading 0:  70%|███████   | 255/363 [03:06<01:25, 1.27it/s]
Loading 0:  71%|███████   | 256/363 [03:08<01:42, 1.05it/s]
Loading 0:  71%|███████   | 256/363 [03:08<01:42, 1.05it/s]
Loading 0:  71%|███████   | 257/363 [03:10<02:01, 1.14s/it]
Loading 0:  71%|███████   | 257/363 [03:10<02:01, 1.14s/it]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:47, 2.08it/s]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:47, 2.08it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<00:51, 1.83it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<00:51, 1.83it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:05, 1.43it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:05, 1.43it/s]
Loading 0:  74%|███████▍  | 270/363 [03:17<01:21, 1.14it/s]
Loading 0:  74%|███████▍  | 270/363 [03:17<01:21, 1.14it/s]
Loading 0:  75%|███████▌  | 273/363 [03:32<03:35, 2.40s/it]
Loading 0:  75%|███████▌  | 273/363 [03:32<03:35, 2.40s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<03:26, 2.32s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<03:26, 2.32s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<03:20, 2.27s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<03:20, 2.27s/it]
Loading 0:  78%|███████▊  | 283/363 [03:37<01:08, 1.17it/s]
Loading 0:  78%|███████▊  | 283/363 [03:37<01:08, 1.17it/s]
Loading 0:  79%|███████▉  | 286/363 [03:39<01:03, 1.22it/s]
Loading 0:  79%|███████▉  | 286/363 [03:39<01:03, 1.22it/s]
Loading 0:  79%|███████▉  | 287/363 [03:41<01:11, 1.06it/s]
Loading 0:  79%|███████▉  | 287/363 [03:41<01:11, 1.06it/s]
Loading 0:  79%|███████▉  | 288/363 [03:43<01:21, 1.09s/it]
Loading 0:  79%|███████▉  | 288/363 [03:43<01:21, 1.09s/it]
Loading 0:  80%|████████  | 291/363 [03:45<01:06, 1.08it/s]
Loading 0:  80%|████████  | 291/363 [03:45<01:06, 1.08it/s]
Loading 0:  80%|████████  | 292/363 [03:47<01:16, 1.07s/it]
Loading 0:  80%|████████  | 292/363 [03:47<01:16, 1.07s/it]
Loading 0:  81%|████████  | 293/363 [03:49<01:26, 1.24s/it]
Loading 0:  81%|████████  | 293/363 [03:49<01:26, 1.24s/it]
Loading 0:  83%|████████▎ | 301/363 [03:50<00:31, 1.98it/s]
Loading 0:  83%|████████▎ | 301/363 [03:50<00:31, 1.98it/s]
Loading 0:  84%|████████▎ | 304/363 [03:52<00:33, 1.77it/s]
Loading 0:  84%|████████▎ | 304/363 [03:52<00:33, 1.77it/s]
Loading 0:  84%|████████▍ | 305/363 [03:54<00:41, 1.40it/s]
Loading 0:  84%|████████▍ | 305/363 [03:54<00:41, 1.40it/s]
Loading 0:  84%|████████▍ | 306/363 [03:56<00:50, 1.12it/s]
Loading 0:  84%|████████▍ | 306/363 [03:56<00:50, 1.12it/s]
Loading 0:  85%|████████▌ | 309/363 [03:58<00:43, 1.25it/s]
Loading 0:  85%|████████▌ | 309/363 [03:58<00:43, 1.25it/s]
Loading 0:  85%|████████▌ | 310/363 [04:00<00:51, 1.04it/s]
Loading 0:  85%|████████▌ | 310/363 [04:00<00:51, 1.04it/s]
Loading 0:  86%|████████▌ | 311/363 [04:02<00:59, 1.15s/it]
Loading 0:  86%|████████▌ | 311/363 [04:02<00:59, 1.15s/it]
Loading 0:  88%|████████▊ | 319/363 [04:03<00:21, 2.09it/s]
Loading 0:  88%|████████▊ | 319/363 [04:03<00:21, 2.09it/s]
Loading 0:  89%|████████▊ | 322/363 [04:05<00:22, 1.84it/s]
Loading 0:  89%|████████▊ | 322/363 [04:05<00:22, 1.84it/s]
Loading 0:  89%|████████▉ | 323/363 [04:07<00:27, 1.44it/s]
Loading 0:  89%|████████▉ | 323/363 [04:07<00:27, 1.44it/s]
Loading 0:  89%|████████▉ | 324/363 [04:09<00:34, 1.14it/s]
Loading 0:  89%|████████▉ | 324/363 [04:09<00:34, 1.14it/s]
Loading 0:  90%|█████████ | 327/363 [04:11<00:28, 1.27it/s]
Loading 0:  90%|█████████ | 327/363 [04:11<00:28, 1.27it/s]
Loading 0:  90%|█████████ | 328/363 [04:13<00:33, 1.05it/s]
Loading 0:  90%|█████████ | 328/363 [04:13<00:33, 1.05it/s]
Loading 0:  91%|█████████ | 329/363 [04:15<00:38, 1.14s/it]
Loading 0:  91%|█████████ | 329/363 [04:15<00:38, 1.14s/it]
Loading 0:  93%|█████████▎| 337/363 [04:16<00:12, 2.11it/s]
Loading 0:  93%|█████████▎| 337/363 [04:16<00:12, 2.11it/s]
Loading 0:  94%|█████████▎| 340/363 [04:19<00:12, 1.84it/s]
Loading 0:  94%|█████████▎| 340/363 [04:19<00:12, 1.84it/s]
Loading 0:  94%|█████████▍| 341/363 [04:20<00:15, 1.44it/s]
Loading 0:  94%|█████████▍| 341/363 [04:20<00:15, 1.44it/s]
Loading 0:  94%|█████████▍| 342/363 [04:22<00:18, 1.14it/s]
Loading 0:  94%|█████████▍| 342/363 [04:22<00:18, 1.14it/s]
Loading 0:  95%|█████████▌| 345/363 [04:24<00:14, 1.27it/s]
Loading 0:  95%|█████████▌| 345/363 [04:24<00:14, 1.27it/s]
Loading 0:  95%|█████████▌| 346/363 [04:26<00:16, 1.05it/s]
Loading 0:  95%|█████████▌| 346/363 [04:26<00:16, 1.05it/s]
Loading 0:  96%|█████████▌| 347/363 [04:28<00:18, 1.14s/it]
Loading 0:  96%|█████████▌| 347/363 [04:28<00:18, 1.14s/it]
Loading 0:  98%|█████████▊| 355/363 [04:29<00:03, 2.09it/s]
Loading 0:  98%|█████████▊| 355/363 [04:29<00:03, 2.09it/s]
Loading 0:  99%|█████████▉| 359/363 [04:32<00:02, 1.89it/s]
Loading 0:  99%|█████████▉| 359/363 [04:32<00:02, 1.89it/s]
Loading 0:  99%|█████████▉| 360/363 [04:34<00:02, 1.49it/s]
Loading 0:  99%|█████████▉| 360/363 [04:34<00:02, 1.49it/s]
Loading 0:  99%|█████████▉| 361/363 [04:36<00:01, 1.19it/s]
Loading 0:  99%|█████████▉| 361/363 [04:36<00:01, 1.19it/s]
Loading 0: 100%|██████████| 363/363 [04:36<00:00, 1.19it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [04:36<00:00, 1.31it/s]
chaiml-mistral-24b-2048-9638-v3-mkmlizer: The tokenizer you are loading from '/tmp/tmp75txo718' 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-2048-9638-v3-mkmlizer: quantized model in 282.979s
chaiml-mistral-24b-2048-9638-v3-mkmlizer: Processed model ChaiML/mistral_24b_2048_opus_v1_2500_20k_merged in 350.825s
chaiml-mistral-24b-2048-9638-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-2048-9638-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-2048-9638-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia
chaiml-mistral-24b-2048-9638-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia/config.json
chaiml-mistral-24b-2048-9638-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia/special_tokens_map.json
chaiml-mistral-24b-2048-9638-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia/tokenizer_config.json
chaiml-mistral-24b-2048-9638-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia/tokenizer.json
chaiml-mistral-24b-2048-9638-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia/flywheel_model.1.safetensors
chaiml-mistral-24b-2048-9638-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-9638-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral-24b-2048-9638-v3-mkmlizer completed after 584.74s with status: succeeded
Stopping job with name chaiml-mistral-24b-2048-9638-v3-mkmlizer
Pipeline stage MKMLizer completed in 585.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-24b-2048-9638-v3
Waiting for inference service chaiml-mistral-24b-2048-9638-v3 to be ready
Inference service chaiml-mistral-24b-2048-9638-v3 ready after 160.95848965644836s
Pipeline stage MKMLDeployer completed in 161.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1533145904541016s
Received healthy response to inference request in 2.083789825439453s
Received healthy response to inference request in 2.140410900115967s
Received healthy response to inference request in 2.0911049842834473s
Received healthy response to inference request in 3.1194794178009033s
5 requests
0 failed requests
5th percentile: 2.085252857208252
10th percentile: 2.086715888977051
20th percentile: 2.0896419525146483
30th percentile: 2.1009661674499513
40th percentile: 2.120688533782959
50th percentile: 2.140410900115967
60th percentile: 2.145572376251221
70th percentile: 2.1507338523864745
80th percentile: 2.346547555923462
90th percentile: 2.7330134868621827
95th percentile: 2.926246452331543
99th percentile: 3.080832824707031
mean time: 2.3176199436187743
Pipeline stage StressChecker completed in 13.09s
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 0.90s
Shutdown handler de-registered
chaiml-mistral-24b-2048-_9638_v3 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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2525.66s
Shutdown handler de-registered
chaiml-mistral-24b-2048-_9638_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-24b-2048-_9638_v3 status is now torndown due to DeploymentManager action