developer_uid: rirv938
submission_id: chaiml-mistral-24b-2048_12623_v4
model_name: chaiml-mistral-24b-2048_12623_v4
model_group: ChaiML/mistral_24b_2048_
status: torndown
timestamp: 2026-01-14T16:59:19+00:00
num_battles: 11330
num_wins: 5961
celo_rating: 1313.59
family_friendly_score: 0.48719999999999997
family_friendly_standard_error: 0.007068750384615374
submission_type: basic
model_repo: ChaiML/mistral_24b_2048_opus_v1_2500_40k_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': 0.3402447848262331, 'latency_mean': 2.938982528448105, 'latency_p50': 2.9561604261398315, 'latency_p90': 3.1383631229400635}, {'batch_size': 2, 'throughput': 0.5279790942582601, 'latency_mean': 3.778847233057022, 'latency_p50': 3.7716509103775024, 'latency_p90': 4.016251492500305}, {'batch_size': 3, 'throughput': 0.6581026546384879, 'latency_mean': 4.549450522661209, 'latency_p50': 4.522692799568176, 'latency_p90': 4.796399521827698}, {'batch_size': 4, 'throughput': 0.7511051288270227, 'latency_mean': 5.3118159341812134, 'latency_p50': 5.328533291816711, 'latency_p90': 6.032944774627685}, {'batch_size': 5, 'throughput': 0.812213296802986, 'latency_mean': 6.137440816164017, 'latency_p50': 6.130699157714844, 'latency_p90': 6.829488015174865}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mistral-24b-2048_12623_v4
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/mistral_24b_2048_opus_v1_2500_40k_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.52
us_pacific_date: 2026-01-09
win_ratio: 0.5261253309796999
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': ['\n', '<|im_start|>', '</s>', '<|im_end|>', 'You:', '###'], '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-2048-12623-v4-mkmlizer
Waiting for job on chaiml-mistral-24b-2048-12623-v4-mkmlizer to finish
chaiml-mistral-24b-2048-12623-v4-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-mistral-24b-2048-12623-v4-mkmlizer: bash: no job control in this shell
chaiml-mistral-24b-2048-12623-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-mistral-24b-2048-12623-v4-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-12623-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-24b-2048-12623-v4-mkmlizer: Downloaded to shared memory in 63.897s
chaiml-mistral-24b-2048-12623-v4-mkmlizer: Checking if ChaiML/mistral_24b_2048_opus_v1_2500_40k_merged already exists in ChaiML
chaiml-mistral-24b-2048-12623-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpna4afqak, device:0
chaiml-mistral-24b-2048-12623-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-2048-12623-v4-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:52, 1.55it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:52, 1.55it/s]
Loading 0:   1%|          | 4.00/363 [00:03<06:25, 1.07s/it]
Loading 0:   1%|          | 4.00/363 [00:03<06:25, 1.07s/it]
Loading 0:   1%|▏         | 5.00/363 [00:05<08:10, 1.37s/it]
Loading 0:   1%|▏         | 5.00/363 [00:05<08:10, 1.37s/it]
Loading 0:   3%|▎         | 12.0/363 [00:07<02:38, 2.22it/s]
Loading 0:   3%|▎         | 12.0/363 [00:07<02:38, 2.22it/s]
Loading 0:   4%|▎         | 13.0/363 [00:09<03:51, 1.51it/s]
Loading 0:   4%|▎         | 13.0/363 [00:09<03:51, 1.51it/s]
Loading 0:   4%|▍         | 14.0/363 [00:10<05:00, 1.16it/s]
Loading 0:   4%|▍         | 14.0/363 [00:10<05:00, 1.16it/s]
Loading 0:   4%|▍         | 15.0/363 [00:12<06:13, 1.07s/it]
Loading 0:   4%|▍         | 15.0/363 [00:12<06:13, 1.07s/it]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:42, 1.53it/s]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:42, 1.53it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:36, 1.23it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:36, 1.23it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:38, 1.00it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:38, 1.00it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:30, 2.20it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:30, 2.20it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:52, 1.91it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:52, 1.91it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:40, 1.49it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:40, 1.49it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:37, 1.18it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:37, 1.18it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:09, 1.30it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:09, 1.30it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:02, 1.07it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:02, 1.07it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:01, 1.12s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:01, 1.12s/it]
Loading 0:  13%|█▎        | 49.0/363 [00:33<02:28, 2.12it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:33<02:28, 2.12it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:35<02:47, 1.86it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:35<02:47, 1.86it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:37<03:33, 1.45it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:37<03:33, 1.45it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:39<04:28, 1.15it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:39<04:28, 1.15it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:41<03:59, 1.28it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:41<03:59, 1.28it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<04:49, 1.05it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<04:49, 1.05it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:45<05:45, 1.14s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:45<05:45, 1.14s/it]
Loading 0:  18%|█▊        | 67.0/363 [00:46<02:21, 2.10it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:46<02:21, 2.10it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:48<02:38, 1.84it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:48<02:38, 1.84it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:50<03:22, 1.44it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:50<03:22, 1.44it/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<05:24, 1.14s/it]
Loading 0:  21%|██        | 77.0/363 [00:58<05:24, 1.14s/it]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:12, 2.10it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:12, 2.10it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:01<02:29, 1.84it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:01<02:29, 1.84it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:03<03:09, 1.44it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:03<03:09, 1.44it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:05<03:58, 1.15it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:05<03:58, 1.15it/s]
Loading 0:  27%|██▋       | 98.0/363 [01:06<01:54, 2.32it/s]
Loading 0:  27%|██▋       | 98.0/363 [01:06<01:54, 2.32it/s]
Loading 0:  28%|██▊       | 101/363 [01:08<02:09, 2.03it/s] 
Loading 0:  28%|██▊       | 101/363 [01:08<02:09, 2.03it/s]
Loading 0:  28%|██▊       | 102/363 [01:10<02:46, 1.56it/s]
Loading 0:  28%|██▊       | 102/363 [01:10<02:46, 1.56it/s]
Loading 0:  28%|██▊       | 103/363 [01:12<03:32, 1.23it/s]
Loading 0:  28%|██▊       | 103/363 [01:12<03:32, 1.23it/s]
Loading 0:  29%|██▉       | 106/363 [01:14<03:16, 1.30it/s]
Loading 0:  29%|██▉       | 106/363 [01:14<03:16, 1.30it/s]
Loading 0:  29%|██▉       | 107/363 [01:16<03:58, 1.07it/s]
Loading 0:  29%|██▉       | 107/363 [01:16<03:58, 1.07it/s]
Loading 0:  30%|██▉       | 108/363 [01:18<04:44, 1.12s/it]
Loading 0:  30%|██▉       | 108/363 [01:18<04:44, 1.12s/it]
Loading 0:  31%|███       | 111/363 [01:20<03:49, 1.10it/s]
Loading 0:  31%|███       | 111/363 [01:20<03:49, 1.10it/s]
Loading 0:  31%|███       | 112/363 [01:22<04:30, 1.08s/it]
Loading 0:  31%|███       | 112/363 [01:22<04:30, 1.08s/it]
Loading 0:  31%|███       | 113/363 [01:24<05:14, 1.26s/it]
Loading 0:  31%|███       | 113/363 [01:24<05:14, 1.26s/it]
Loading 0:  33%|███▎      | 121/363 [01:25<01:58, 2.04it/s]
Loading 0:  33%|███▎      | 121/363 [01:25<01:58, 2.04it/s]
Loading 0:  34%|███▍      | 124/363 [01:27<02:12, 1.81it/s]
Loading 0:  34%|███▍      | 124/363 [01:27<02:12, 1.81it/s]
Loading 0:  34%|███▍      | 125/363 [01:29<02:48, 1.42it/s]
Loading 0:  34%|███▍      | 125/363 [01:29<02:48, 1.42it/s]
Loading 0:  35%|███▍      | 126/363 [01:31<03:30, 1.13it/s]
Loading 0:  35%|███▍      | 126/363 [01:31<03:30, 1.13it/s]
Loading 0:  36%|███▌      | 129/363 [01:33<03:05, 1.26it/s]
Loading 0:  36%|███▌      | 129/363 [01:33<03:05, 1.26it/s]
Loading 0:  36%|███▌      | 130/363 [01:35<03:43, 1.04it/s]
Loading 0:  36%|███▌      | 130/363 [01:35<03:43, 1.04it/s]
Loading 0:  36%|███▌      | 131/363 [01:37<04:25, 1.15s/it]
Loading 0:  36%|███▌      | 131/363 [01:37<04:25, 1.15s/it]
Loading 0:  38%|███▊      | 139/363 [01:38<01:47, 2.08it/s]
Loading 0:  38%|███▊      | 139/363 [01:38<01:47, 2.08it/s]
Loading 0:  39%|███▉      | 142/363 [01:40<02:00, 1.83it/s]
Loading 0:  39%|███▉      | 142/363 [01:40<02:00, 1.83it/s]
Loading 0:  39%|███▉      | 143/363 [01:42<02:33, 1.43it/s]
Loading 0:  39%|███▉      | 143/363 [01:42<02:33, 1.43it/s]
Loading 0:  40%|███▉      | 144/363 [01:44<03:11, 1.14it/s]
Loading 0:  40%|███▉      | 144/363 [01:44<03:11, 1.14it/s]
Loading 0:  40%|████      | 147/363 [01:46<02:50, 1.27it/s]
Loading 0:  40%|████      | 147/363 [01:46<02:50, 1.27it/s]
Loading 0:  41%|████      | 148/363 [01:48<03:25, 1.05it/s]
Loading 0:  41%|████      | 148/363 [01:48<03:25, 1.05it/s]
Loading 0:  41%|████      | 149/363 [01:50<04:04, 1.14s/it]
Loading 0:  41%|████      | 149/363 [01:50<04:04, 1.14s/it]
Loading 0:  43%|████▎     | 157/363 [01:51<01:38, 2.10it/s]
Loading 0:  43%|████▎     | 157/363 [01:51<01:38, 2.10it/s]
Loading 0:  44%|████▍     | 160/363 [01:54<01:50, 1.84it/s]
Loading 0:  44%|████▍     | 160/363 [01:54<01:50, 1.84it/s]
Loading 0:  44%|████▍     | 161/363 [01:55<02:20, 1.44it/s]
Loading 0:  44%|████▍     | 161/363 [01:55<02:20, 1.44it/s]
Loading 0:  45%|████▍     | 162/363 [01:57<02:55, 1.15it/s]
Loading 0:  45%|████▍     | 162/363 [01:57<02:55, 1.15it/s]
Loading 0:  45%|████▌     | 165/363 [01:59<02:35, 1.27it/s]
Loading 0:  45%|████▌     | 165/363 [01:59<02:35, 1.27it/s]
Loading 0:  46%|████▌     | 166/363 [02:01<03:07, 1.05it/s]
Loading 0:  46%|████▌     | 166/363 [02:01<03:07, 1.05it/s]
Loading 0:  46%|████▌     | 167/363 [02:03<03:42, 1.14s/it]
Loading 0:  46%|████▌     | 167/363 [02:03<03:42, 1.14s/it]
Loading 0:  48%|████▊     | 175/363 [02:04<01:29, 2.11it/s]
Loading 0:  48%|████▊     | 175/363 [02:04<01:29, 2.11it/s]
Loading 0:  49%|████▉     | 178/363 [02:07<01:40, 1.85it/s]
Loading 0:  49%|████▉     | 178/363 [02:07<01:40, 1.85it/s]
Loading 0:  49%|████▉     | 179/363 [02:08<02:07, 1.44it/s]
Loading 0:  49%|████▉     | 179/363 [02:08<02:07, 1.44it/s]
Loading 0:  50%|████▉     | 180/363 [02:10<02:39, 1.15it/s]
Loading 0:  50%|████▉     | 180/363 [02:10<02:39, 1.15it/s]
Loading 0:  50%|█████     | 183/363 [02:12<02:21, 1.28it/s]
Loading 0:  50%|█████     | 183/363 [02:12<02:21, 1.28it/s]
Loading 0:  51%|█████     | 184/363 [02:14<02:50, 1.05it/s]
Loading 0:  51%|█████     | 184/363 [02:14<02:50, 1.05it/s]
Loading 0:  51%|█████     | 185/363 [02:16<03:22, 1.14s/it]
Loading 0:  51%|█████     | 185/363 [02:16<03:22, 1.14s/it]
Loading 0:  53%|█████▎    | 193/363 [02:17<01:21, 2.09it/s]
Loading 0:  53%|█████▎    | 193/363 [02:17<01:21, 2.09it/s]
Loading 0:  54%|█████▍    | 196/363 [02:20<01:30, 1.84it/s]
Loading 0:  54%|█████▍    | 196/363 [02:20<01:30, 1.84it/s]
Loading 0:  54%|█████▍    | 197/363 [02:22<01:55, 1.44it/s]
Loading 0:  54%|█████▍    | 197/363 [02:22<01:55, 1.44it/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 [02:25<02:07, 1.27it/s]
Loading 0:  55%|█████▌    | 201/363 [02:25<02:07, 1.27it/s]
Loading 0:  56%|█████▌    | 202/363 [02:27<02:33, 1.05it/s]
Loading 0:  56%|█████▌    | 202/363 [02:27<02:33, 1.05it/s]
Loading 0:  56%|█████▌    | 203/363 [02:29<03:02, 1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [02:29<03:02, 1.14s/it]
Loading 0:  58%|█████▊    | 211/363 [02:31<01:12, 2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [02:31<01:12, 2.09it/s]
Loading 0:  59%|█████▉    | 214/363 [02:33<01:20, 1.84it/s]
Loading 0:  59%|█████▉    | 214/363 [02:33<01:20, 1.84it/s]
Loading 0:  59%|█████▉    | 215/363 [02:35<01:42, 1.44it/s]
Loading 0:  59%|█████▉    | 215/363 [02:35<01:42, 1.44it/s]
Loading 0:  60%|█████▉    | 216/363 [02:37<02:08, 1.15it/s]
Loading 0:  60%|█████▉    | 216/363 [02:37<02:08, 1.15it/s]
Loading 0:  60%|██████    | 219/363 [02:39<01:52, 1.28it/s]
Loading 0:  60%|██████    | 219/363 [02:39<01:52, 1.28it/s]
Loading 0:  61%|██████    | 220/363 [02:40<02:15, 1.05it/s]
Loading 0:  61%|██████    | 220/363 [02:40<02:15, 1.05it/s]
Loading 0:  61%|██████    | 221/363 [02:42<02:41, 1.14s/it]
Loading 0:  61%|██████    | 221/363 [02:42<02:41, 1.14s/it]
Loading 0:  63%|██████▎   | 229/363 [02:44<01:03, 2.10it/s]
Loading 0:  63%|██████▎   | 229/363 [02:44<01:03, 2.10it/s]
Loading 0:  64%|██████▍   | 232/363 [02:46<01:11, 1.84it/s]
Loading 0:  64%|██████▍   | 232/363 [02:46<01:11, 1.84it/s]
Loading 0:  64%|██████▍   | 233/363 [02:48<01:30, 1.44it/s]
Loading 0:  64%|██████▍   | 233/363 [02:48<01:30, 1.44it/s]
Loading 0:  64%|██████▍   | 234/363 [02:50<01:52, 1.15it/s]
Loading 0:  64%|██████▍   | 234/363 [02:50<01:52, 1.15it/s]
Loading 0:  65%|██████▌   | 237/363 [02:52<01:38, 1.28it/s]
Loading 0:  65%|██████▌   | 237/363 [02:52<01:38, 1.28it/s]
Loading 0:  66%|██████▌   | 238/363 [02:53<01:58, 1.05it/s]
Loading 0:  66%|██████▌   | 238/363 [02:53<01:58, 1.05it/s]
Loading 0:  66%|██████▌   | 239/363 [02:55<02:20, 1.14s/it]
Loading 0:  66%|██████▌   | 239/363 [02:55<02:20, 1.14s/it]
Loading 0:  68%|██████▊   | 247/363 [02:57<00:55, 2.09it/s]
Loading 0:  68%|██████▊   | 247/363 [02:57<00:55, 2.09it/s]
Loading 0:  69%|██████▉   | 250/363 [02:59<01:01, 1.84it/s]
Loading 0:  69%|██████▉   | 250/363 [02:59<01:01, 1.84it/s]
Loading 0:  69%|██████▉   | 251/363 [03:01<01:17, 1.44it/s]
Loading 0:  69%|██████▉   | 251/363 [03:01<01:17, 1.44it/s]
Loading 0:  69%|██████▉   | 252/363 [03:03<01:37, 1.14it/s]
Loading 0:  69%|██████▉   | 252/363 [03:03<01:37, 1.14it/s]
Loading 0:  70%|███████   | 255/363 [03:05<01:24, 1.27it/s]
Loading 0:  70%|███████   | 255/363 [03:05<01:24, 1.27it/s]
Loading 0:  71%|███████   | 256/363 [03:07<01:41, 1.05it/s]
Loading 0:  71%|███████   | 256/363 [03:07<01:41, 1.05it/s]
Loading 0:  71%|███████   | 257/363 [03:09<02:00, 1.14s/it]
Loading 0:  71%|███████   | 257/363 [03:09<02:00, 1.14s/it]
Loading 0:  73%|███████▎  | 265/363 [03:10<00:46, 2.10it/s]
Loading 0:  73%|███████▎  | 265/363 [03:10<00:46, 2.10it/s]
Loading 0:  74%|███████▍  | 268/363 [03:12<00:51, 1.85it/s]
Loading 0:  74%|███████▍  | 268/363 [03:12<00:51, 1.85it/s]
Loading 0:  74%|███████▍  | 269/363 [03:14<01:05, 1.45it/s]
Loading 0:  74%|███████▍  | 269/363 [03:14<01:05, 1.45it/s]
Loading 0:  74%|███████▍  | 270/363 [03:16<01:21, 1.15it/s]
Loading 0:  74%|███████▍  | 270/363 [03:16<01:21, 1.15it/s]
Loading 0:  75%|███████▌  | 273/363 [03:31<03:32, 2.36s/it]
Loading 0:  75%|███████▌  | 273/363 [03:31<03:32, 2.36s/it]
Loading 0:  75%|███████▌  | 274/363 [03:32<03:23, 2.29s/it]
Loading 0:  75%|███████▌  | 274/363 [03:32<03:23, 2.29s/it]
Loading 0:  76%|███████▌  | 275/363 [03:34<03:17, 2.25s/it]
Loading 0:  76%|███████▌  | 275/363 [03:34<03:17, 2.25s/it]
Loading 0:  78%|███████▊  | 283/363 [03:36<01:07, 1.18it/s]
Loading 0:  78%|███████▊  | 283/363 [03:36<01:07, 1.18it/s]
Loading 0:  79%|███████▉  | 286/363 [03:38<01:02, 1.23it/s]
Loading 0:  79%|███████▉  | 286/363 [03:38<01:02, 1.23it/s]
Loading 0:  79%|███████▉  | 287/363 [03:40<01:10, 1.07it/s]
Loading 0:  79%|███████▉  | 287/363 [03:40<01:10, 1.07it/s]
Loading 0:  79%|███████▉  | 288/363 [03:42<01:20, 1.08s/it]
Loading 0:  79%|███████▉  | 288/363 [03:42<01:20, 1.08s/it]
Loading 0:  80%|████████  | 291/363 [03:44<01:05, 1.09it/s]
Loading 0:  80%|████████  | 291/363 [03:44<01:05, 1.09it/s]
Loading 0:  80%|████████  | 292/363 [03:45<01:15, 1.06s/it]
Loading 0:  80%|████████  | 292/363 [03:45<01:15, 1.06s/it]
Loading 0:  81%|████████  | 293/363 [03:47<01:25, 1.23s/it]
Loading 0:  81%|████████  | 293/363 [03:47<01:25, 1.23s/it]
Loading 0:  83%|████████▎ | 301/363 [03:49<00:30, 2.00it/s]
Loading 0:  83%|████████▎ | 301/363 [03:49<00:30, 2.00it/s]
Loading 0:  84%|████████▎ | 304/363 [03:51<00:33, 1.79it/s]
Loading 0:  84%|████████▎ | 304/363 [03:51<00:33, 1.79it/s]
Loading 0:  84%|████████▍ | 305/363 [03:53<00:41, 1.41it/s]
Loading 0:  84%|████████▍ | 305/363 [03:53<00:41, 1.41it/s]
Loading 0:  84%|████████▍ | 306/363 [03:55<00:50, 1.13it/s]
Loading 0:  84%|████████▍ | 306/363 [03:55<00:50, 1.13it/s]
Loading 0:  85%|████████▌ | 309/363 [03:57<00:43, 1.25it/s]
Loading 0:  85%|████████▌ | 309/363 [03:57<00:43, 1.25it/s]
Loading 0:  85%|████████▌ | 310/363 [03:59<00:51, 1.04it/s]
Loading 0:  85%|████████▌ | 310/363 [03:59<00:51, 1.04it/s]
Loading 0:  86%|████████▌ | 311/363 [04:01<00:59, 1.15s/it]
Loading 0:  86%|████████▌ | 311/363 [04:01<00:59, 1.15s/it]
Loading 0:  88%|████████▊ | 319/363 [04:02<00:20, 2.10it/s]
Loading 0:  88%|████████▊ | 319/363 [04:02<00:20, 2.10it/s]
Loading 0:  89%|████████▊ | 322/363 [04:04<00:22, 1.85it/s]
Loading 0:  89%|████████▊ | 322/363 [04:04<00:22, 1.85it/s]
Loading 0:  89%|████████▉ | 323/363 [04:06<00:27, 1.44it/s]
Loading 0:  89%|████████▉ | 323/363 [04:06<00:27, 1.44it/s]
Loading 0:  89%|████████▉ | 324/363 [04:08<00:34, 1.15it/s]
Loading 0:  89%|████████▉ | 324/363 [04:08<00:34, 1.15it/s]
Loading 0:  90%|█████████ | 327/363 [04:10<00:28, 1.27it/s]
Loading 0:  90%|█████████ | 327/363 [04:10<00:28, 1.27it/s]
Loading 0:  90%|█████████ | 328/363 [04:12<00:33, 1.05it/s]
Loading 0:  90%|█████████ | 328/363 [04:12<00:33, 1.05it/s]
Loading 0:  91%|█████████ | 329/363 [04:14<00:38, 1.14s/it]
Loading 0:  91%|█████████ | 329/363 [04:14<00:38, 1.14s/it]
Loading 0:  93%|█████████▎| 337/363 [04:15<00:12, 2.13it/s]
Loading 0:  93%|█████████▎| 337/363 [04:15<00:12, 2.13it/s]
Loading 0:  94%|█████████▎| 340/363 [04:17<00:12, 1.86it/s]
Loading 0:  94%|█████████▎| 340/363 [04:17<00:12, 1.86it/s]
Loading 0:  94%|█████████▍| 341/363 [04:19<00:15, 1.45it/s]
Loading 0:  94%|█████████▍| 341/363 [04:19<00:15, 1.45it/s]
Loading 0:  94%|█████████▍| 342/363 [04:21<00:18, 1.15it/s]
Loading 0:  94%|█████████▍| 342/363 [04:21<00:18, 1.15it/s]
Loading 0:  95%|█████████▌| 345/363 [04:23<00:14, 1.28it/s]
Loading 0:  95%|█████████▌| 345/363 [04:23<00:14, 1.28it/s]
Loading 0:  95%|█████████▌| 346/363 [04:25<00:16, 1.05it/s]
Loading 0:  95%|█████████▌| 346/363 [04:25<00:16, 1.05it/s]
Loading 0:  96%|█████████▌| 347/363 [04:27<00:18, 1.13s/it]
Loading 0:  96%|█████████▌| 347/363 [04:27<00:18, 1.13s/it]
Loading 0:  98%|█████████▊| 355/363 [04:28<00:03, 2.11it/s]
Loading 0:  98%|█████████▊| 355/363 [04:28<00:03, 2.11it/s]
Loading 0:  99%|█████████▉| 359/363 [04:30<00:02, 1.90it/s]
Loading 0:  99%|█████████▉| 359/363 [04:30<00:02, 1.90it/s]
Loading 0:  99%|█████████▉| 360/363 [04:32<00:02, 1.50it/s]
Loading 0:  99%|█████████▉| 360/363 [04:32<00:02, 1.50it/s]
Loading 0:  99%|█████████▉| 361/363 [04:34<00:01, 1.19it/s]
Loading 0:  99%|█████████▉| 361/363 [04:34<00:01, 1.19it/s]
Loading 0: 100%|██████████| 363/363 [04:34<00:00, 1.19it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [04:34<00:00, 1.32it/s]
chaiml-mistral-24b-2048-12623-v4-mkmlizer: The tokenizer you are loading from '/tmp/tmpna4afqak' 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-2048-12623-v4-mkmlizer: quantized model in 280.569s
chaiml-mistral-24b-2048-12623-v4-mkmlizer: Processed model ChaiML/mistral_24b_2048_opus_v1_2500_40k_merged in 344.467s
chaiml-mistral-24b-2048-12623-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-2048-12623-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-2048-12623-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia
chaiml-mistral-24b-2048-12623-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia/config.json
chaiml-mistral-24b-2048-12623-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia/special_tokens_map.json
chaiml-mistral-24b-2048-12623-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia/tokenizer_config.json
chaiml-mistral-24b-2048-12623-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia/tokenizer.json
chaiml-mistral-24b-2048-12623-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia/flywheel_model.1.safetensors
chaiml-mistral-24b-2048-12623-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-12623-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral-24b-2048-12623-v4-mkmlizer completed after 561.19s with status: succeeded
Stopping job with name chaiml-mistral-24b-2048-12623-v4-mkmlizer
Pipeline stage MKMLizer completed in 561.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-24b-2048-12623-v4
Waiting for inference service chaiml-mistral-24b-2048-12623-v4 to be ready
Inference service chaiml-mistral-24b-2048-12623-v4 ready after 161.06743693351746s
Pipeline stage MKMLDeployer completed in 161.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0430145263671875s
Received healthy response to inference request in 1.774890422821045s
Received healthy response to inference request in 2.739673137664795s
Received healthy response to inference request in 2.729776382446289s
Received healthy response to inference request in 3.021095037460327s
5 requests
0 failed requests
5th percentile: 1.8285152435302734
10th percentile: 1.8821400642395019
20th percentile: 1.989389705657959
30th percentile: 2.1803668975830077
40th percentile: 2.4550716400146486
50th percentile: 2.729776382446289
60th percentile: 2.7337350845336914
70th percentile: 2.7376937866210938
80th percentile: 2.7959575176239015
90th percentile: 2.9085262775421143
95th percentile: 2.9648106575012205
99th percentile: 3.009838161468506
mean time: 2.461689901351929
Pipeline stage StressChecker completed in 13.60s
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 0.64s
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 0.63s
Shutdown handler de-registered
chaiml-mistral-24b-2048_12623_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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2451.46s
Shutdown handler de-registered
chaiml-mistral-24b-2048_12623_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-24b-2048_12623_v4 status is now torndown due to DeploymentManager action