developer_uid: rirv938
submission_id: chaiml-mistral-24b-2048_89940_v2
model_name: chaiml-mistral-24b-2048_89940_v2
model_group: ChaiML/mistral_24b_2048_
status: inactive
timestamp: 2026-01-08T05:17:21+00:00
num_battles: 12704
num_wins: 6563
celo_rating: 1306.93
family_friendly_score: 0.496
family_friendly_standard_error: 0.007070841534074993
submission_type: basic
model_repo: ChaiML/mistral_24b_2048_gemini_ds_v1_1168_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': 0.35175107549048823, 'latency_mean': 2.842857749462128, 'latency_p50': 2.839258551597595, 'latency_p90': 3.0600981950759887}, {'batch_size': 2, 'throughput': 0.5544894760191026, 'latency_mean': 3.5963968551158905, 'latency_p50': 3.601575255393982, 'latency_p90': 3.806648206710815}, {'batch_size': 3, 'throughput': 0.705403545695104, 'latency_mean': 4.246023932695389, 'latency_p50': 4.238922715187073, 'latency_p90': 4.5273806095123295}, {'batch_size': 4, 'throughput': 0.7989705380252243, 'latency_mean': 4.989127863645553, 'latency_p50': 4.995141983032227, 'latency_p90': 5.441555595397949}, {'batch_size': 5, 'throughput': 0.8633069311466255, 'latency_mean': 5.769516673088074, 'latency_p50': 5.788178443908691, 'latency_p90': 6.220074701309204}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral-24b-2048_89940_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/mistral_24b_2048_gemini_ds_v1_1168_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.58
us_pacific_date: 2026-01-07
win_ratio: 0.5166089420654912
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:', '</s>', '\n', '###', '<|im_start|>', '<|im_end|>'], '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-2048-89940-v2-mkmlizer
Waiting for job on chaiml-mistral-24b-2048-89940-v2-mkmlizer to finish
chaiml-mistral-24b-2048-89940-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-mistral-24b-2048-89940-v2-mkmlizer: bash: no job control in this shell
chaiml-mistral-24b-2048-89940-v2-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-2048-89940-v2-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-89940-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-24b-2048-89940-v2-mkmlizer: Downloaded to shared memory in 93.576s
chaiml-mistral-24b-2048-89940-v2-mkmlizer: Checking if ChaiML/mistral_24b_2048_gemini_ds_v1_1168_merged already exists in ChaiML
chaiml-mistral-24b-2048-89940-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp0wa824y7, device:0
chaiml-mistral-24b-2048-89940-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-2048-89940-v2-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:23, 1.37it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:23, 1.37it/s]
Loading 0:   1%|          | 4.00/363 [00:04<07:07, 1.19s/it]
Loading 0:   1%|          | 4.00/363 [00:04<07:07, 1.19s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<09:10, 1.54s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<09:10, 1.54s/it]
Loading 0:   3%|▎         | 11.0/363 [00:07<03:13, 1.82it/s]
Loading 0:   3%|▎         | 11.0/363 [00:07<03:13, 1.82it/s]
Loading 0:   4%|▎         | 13.0/363 [00:10<04:09, 1.40it/s]
Loading 0:   4%|▎         | 13.0/363 [00:10<04:09, 1.40it/s]
Loading 0:   4%|▍         | 14.0/363 [00:12<05:27, 1.07it/s]
Loading 0:   4%|▍         | 14.0/363 [00:12<05:27, 1.07it/s]
Loading 0:   4%|▍         | 15.0/363 [00:14<06:51, 1.18s/it]
Loading 0:   4%|▍         | 15.0/363 [00:14<06:51, 1.18s/it]
Loading 0:   6%|▌         | 21.0/363 [00:17<04:09, 1.37it/s]
Loading 0:   6%|▌         | 21.0/363 [00:17<04:09, 1.37it/s]
Loading 0:   6%|▌         | 22.0/363 [00:19<05:10, 1.10it/s]
Loading 0:   6%|▌         | 22.0/363 [00:19<05:10, 1.10it/s]
Loading 0:   6%|▋         | 23.0/363 [00:21<06:20, 1.12s/it]
Loading 0:   6%|▋         | 23.0/363 [00:21<06:20, 1.12s/it]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:58, 1.87it/s]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:58, 1.87it/s]
Loading 0:   9%|▉         | 34.0/363 [00:25<03:13, 1.70it/s]
Loading 0:   9%|▉         | 34.0/363 [00:25<03:13, 1.70it/s]
Loading 0:  10%|▉         | 35.0/363 [00:27<04:07, 1.32it/s]
Loading 0:  10%|▉         | 35.0/363 [00:27<04:07, 1.32it/s]
Loading 0:  10%|▉         | 36.0/363 [00:29<05:12, 1.05it/s]
Loading 0:  10%|▉         | 36.0/363 [00:29<05:12, 1.05it/s]
Loading 0:  11%|█         | 39.0/363 [00:32<04:42, 1.15it/s]
Loading 0:  11%|█         | 39.0/363 [00:32<04:42, 1.15it/s]
Loading 0:  11%|█         | 40.0/363 [00:34<05:42, 1.06s/it]
Loading 0:  11%|█         | 40.0/363 [00:34<05:42, 1.06s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:36<06:50, 1.28s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:36<06:50, 1.28s/it]
Loading 0:  13%|█▎        | 48.0/363 [00:37<02:58, 1.76it/s]
Loading 0:  13%|█▎        | 48.0/363 [00:37<02:58, 1.76it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:40<03:11, 1.62it/s]
Loading 0:  14%|█▍        | 52.0/363 [00:40<03:11, 1.62it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:42<04:05, 1.26it/s]
Loading 0:  15%|█▍        | 53.0/363 [00:42<04:05, 1.26it/s]
Loading 0:  15%|█▍        | 54.0/363 [00:45<05:10, 1.01s/it]
Loading 0:  15%|█▍        | 54.0/363 [00:45<05:10, 1.01s/it]
Loading 0:  16%|█▌        | 57.0/363 [00:47<04:39, 1.10it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:47<04:39, 1.10it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:50<06:02, 1.19s/it]
Loading 0:  16%|█▌        | 58.0/363 [00:50<06:02, 1.19s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:52<07:03, 1.39s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:52<07:03, 1.39s/it]
Loading 0:  18%|█▊        | 66.0/363 [00:53<03:01, 1.64it/s]
Loading 0:  18%|█▊        | 66.0/363 [00:53<03:01, 1.64it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:56<03:09, 1.55it/s]
Loading 0:  19%|█▉        | 70.0/363 [00:56<03:09, 1.55it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:58<04:03, 1.20it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:58<04:03, 1.20it/s]
Loading 0:  20%|█▉        | 72.0/363 [01:01<05:01, 1.04s/it]
Loading 0:  20%|█▉        | 72.0/363 [01:01<05:01, 1.04s/it]
Loading 0:  21%|██        | 75.0/363 [01:03<04:28, 1.07it/s]
Loading 0:  21%|██        | 75.0/363 [01:03<04:28, 1.07it/s]
Loading 0:  21%|██        | 76.0/363 [01:05<05:23, 1.13s/it]
Loading 0:  21%|██        | 76.0/363 [01:05<05:23, 1.13s/it]
Loading 0:  21%|██        | 77.0/363 [01:08<06:25, 1.35s/it]
Loading 0:  21%|██        | 77.0/363 [01:08<06:25, 1.35s/it]
Loading 0:  23%|██▎       | 84.0/363 [01:09<02:45, 1.69it/s]
Loading 0:  23%|██▎       | 84.0/363 [01:09<02:45, 1.69it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:12<02:55, 1.56it/s]
Loading 0:  24%|██▍       | 88.0/363 [01:12<02:55, 1.56it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:14<03:43, 1.23it/s]
Loading 0:  25%|██▍       | 89.0/363 [01:14<03:43, 1.23it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:16<04:39, 1.02s/it]
Loading 0:  25%|██▍       | 90.0/363 [01:16<04:39, 1.02s/it]
Loading 0:  27%|██▋       | 97.0/363 [01:17<02:20, 1.89it/s]
Loading 0:  27%|██▋       | 97.0/363 [01:17<02:20, 1.89it/s]
Loading 0:  28%|██▊       | 101/363 [01:20<02:29, 1.75it/s] 
Loading 0:  28%|██▊       | 101/363 [01:20<02:29, 1.75it/s]
Loading 0:  28%|██▊       | 102/363 [01:22<03:12, 1.35it/s]
Loading 0:  28%|██▊       | 102/363 [01:22<03:12, 1.35it/s]
Loading 0:  28%|██▊       | 103/363 [01:25<04:05, 1.06it/s]
Loading 0:  28%|██▊       | 103/363 [01:25<04:05, 1.06it/s]
Loading 0:  29%|██▉       | 106/363 [01:27<03:48, 1.12it/s]
Loading 0:  29%|██▉       | 106/363 [01:27<03:48, 1.12it/s]
Loading 0:  29%|██▉       | 107/363 [01:29<04:35, 1.08s/it]
Loading 0:  29%|██▉       | 107/363 [01:29<04:35, 1.08s/it]
Loading 0:  30%|██▉       | 108/363 [01:32<05:28, 1.29s/it]
Loading 0:  30%|██▉       | 108/363 [01:32<05:28, 1.29s/it]
Loading 0:  31%|███       | 111/363 [01:34<04:25, 1.05s/it]
Loading 0:  31%|███       | 111/363 [01:34<04:25, 1.05s/it]
Loading 0:  31%|███       | 112/363 [01:36<05:12, 1.24s/it]
Loading 0:  31%|███       | 112/363 [01:36<05:12, 1.24s/it]
Loading 0:  31%|███       | 113/363 [01:38<06:03, 1.46s/it]
Loading 0:  31%|███       | 113/363 [01:38<06:03, 1.46s/it]
Loading 0:  33%|███▎      | 120/363 [01:39<02:26, 1.66it/s]
Loading 0:  33%|███▎      | 120/363 [01:39<02:26, 1.66it/s]
Loading 0:  34%|███▍      | 124/363 [01:42<02:33, 1.55it/s]
Loading 0:  34%|███▍      | 124/363 [01:42<02:33, 1.55it/s]
Loading 0:  34%|███▍      | 125/363 [01:44<03:13, 1.23it/s]
Loading 0:  34%|███▍      | 125/363 [01:44<03:13, 1.23it/s]
Loading 0:  35%|███▍      | 126/363 [01:47<04:00, 1.02s/it]
Loading 0:  35%|███▍      | 126/363 [01:47<04:00, 1.02s/it]
Loading 0:  36%|███▌      | 129/363 [01:49<03:37, 1.08it/s]
Loading 0:  36%|███▌      | 129/363 [01:49<03:37, 1.08it/s]
Loading 0:  36%|███▌      | 130/363 [01:51<04:19, 1.11s/it]
Loading 0:  36%|███▌      | 130/363 [01:51<04:19, 1.11s/it]
Loading 0:  36%|███▌      | 131/363 [01:54<05:06, 1.32s/it]
Loading 0:  36%|███▌      | 131/363 [01:54<05:06, 1.32s/it]
Loading 0:  38%|███▊      | 138/363 [01:55<02:10, 1.73it/s]
Loading 0:  38%|███▊      | 138/363 [01:55<02:10, 1.73it/s]
Loading 0:  39%|███▉      | 142/363 [01:57<02:17, 1.61it/s]
Loading 0:  39%|███▉      | 142/363 [01:57<02:17, 1.61it/s]
Loading 0:  39%|███▉      | 143/363 [02:00<02:53, 1.27it/s]
Loading 0:  39%|███▉      | 143/363 [02:00<02:53, 1.27it/s]
Loading 0:  40%|███▉      | 144/363 [02:02<03:36, 1.01it/s]
Loading 0:  40%|███▉      | 144/363 [02:02<03:36, 1.01it/s]
Loading 0:  40%|████      | 147/363 [02:04<03:13, 1.12it/s]
Loading 0:  40%|████      | 147/363 [02:04<03:13, 1.12it/s]
Loading 0:  41%|████      | 148/363 [02:06<03:52, 1.08s/it]
Loading 0:  41%|████      | 148/363 [02:06<03:52, 1.08s/it]
Loading 0:  41%|████      | 149/363 [02:08<04:36, 1.29s/it]
Loading 0:  41%|████      | 149/363 [02:08<04:36, 1.29s/it]
Loading 0:  43%|████▎     | 156/363 [02:10<01:58, 1.75it/s]
Loading 0:  43%|████▎     | 156/363 [02:10<01:58, 1.75it/s]
Loading 0:  44%|████▍     | 160/363 [02:12<02:04, 1.63it/s]
Loading 0:  44%|████▍     | 160/363 [02:12<02:04, 1.63it/s]
Loading 0:  44%|████▍     | 161/363 [02:15<02:38, 1.28it/s]
Loading 0:  44%|████▍     | 161/363 [02:15<02:38, 1.28it/s]
Loading 0:  45%|████▍     | 162/363 [02:17<03:18, 1.01it/s]
Loading 0:  45%|████▍     | 162/363 [02:17<03:18, 1.01it/s]
Loading 0:  45%|████▌     | 165/363 [02:19<02:56, 1.12it/s]
Loading 0:  45%|████▌     | 165/363 [02:19<02:56, 1.12it/s]
Loading 0:  46%|████▌     | 166/363 [02:21<03:33, 1.08s/it]
Loading 0:  46%|████▌     | 166/363 [02:21<03:33, 1.08s/it]
Loading 0:  46%|████▌     | 167/363 [02:24<04:13, 1.29s/it]
Loading 0:  46%|████▌     | 167/363 [02:24<04:13, 1.29s/it]
Loading 0:  48%|████▊     | 174/363 [02:25<01:47, 1.75it/s]
Loading 0:  48%|████▊     | 174/363 [02:25<01:47, 1.75it/s]
Loading 0:  49%|████▉     | 178/363 [02:27<01:54, 1.62it/s]
Loading 0:  49%|████▉     | 178/363 [02:27<01:54, 1.62it/s]
Loading 0:  49%|████▉     | 179/363 [02:30<02:24, 1.27it/s]
Loading 0:  49%|████▉     | 179/363 [02:30<02:24, 1.27it/s]
Loading 0:  50%|████▉     | 180/363 [02:32<03:01, 1.01it/s]
Loading 0:  50%|████▉     | 180/363 [02:32<03:01, 1.01it/s]
Loading 0:  50%|█████     | 183/363 [02:34<02:40, 1.12it/s]
Loading 0:  50%|█████     | 183/363 [02:34<02:40, 1.12it/s]
Loading 0:  51%|█████     | 184/363 [02:36<03:13, 1.08s/it]
Loading 0:  51%|█████     | 184/363 [02:36<03:13, 1.08s/it]
Loading 0:  51%|█████     | 185/363 [02:39<03:49, 1.29s/it]
Loading 0:  51%|█████     | 185/363 [02:39<03:49, 1.29s/it]
Loading 0:  53%|█████▎    | 192/363 [02:40<01:37, 1.76it/s]
Loading 0:  53%|█████▎    | 192/363 [02:40<01:37, 1.76it/s]
Loading 0:  54%|█████▍    | 196/363 [02:42<01:42, 1.64it/s]
Loading 0:  54%|█████▍    | 196/363 [02:42<01:42, 1.64it/s]
Loading 0:  54%|█████▍    | 197/363 [02:45<02:09, 1.28it/s]
Loading 0:  54%|█████▍    | 197/363 [02:45<02:09, 1.28it/s]
Loading 0:  55%|█████▍    | 198/363 [02:47<02:42, 1.02it/s]
Loading 0:  55%|█████▍    | 198/363 [02:47<02:42, 1.02it/s]
Loading 0:  55%|█████▌    | 201/363 [02:49<02:27, 1.10it/s]
Loading 0:  55%|█████▌    | 201/363 [02:49<02:27, 1.10it/s]
Loading 0:  56%|█████▌    | 202/363 [02:51<02:56, 1.09s/it]
Loading 0:  56%|█████▌    | 202/363 [02:51<02:56, 1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [02:54<03:27, 1.30s/it]
Loading 0:  56%|█████▌    | 203/363 [02:54<03:27, 1.30s/it]
Loading 0:  58%|█████▊    | 210/363 [02:55<01:27, 1.74it/s]
Loading 0:  58%|█████▊    | 210/363 [02:55<01:27, 1.74it/s]
Loading 0:  59%|█████▉    | 214/363 [02:58<01:31, 1.63it/s]
Loading 0:  59%|█████▉    | 214/363 [02:58<01:31, 1.63it/s]
Loading 0:  59%|█████▉    | 215/363 [03:00<01:55, 1.28it/s]
Loading 0:  59%|█████▉    | 215/363 [03:00<01:55, 1.28it/s]
Loading 0:  60%|█████▉    | 216/363 [03:02<02:24, 1.02it/s]
Loading 0:  60%|█████▉    | 216/363 [03:02<02:24, 1.02it/s]
Loading 0:  60%|██████    | 219/363 [03:04<02:07, 1.13it/s]
Loading 0:  60%|██████    | 219/363 [03:04<02:07, 1.13it/s]
Loading 0:  61%|██████    | 220/363 [03:06<02:33, 1.08s/it]
Loading 0:  61%|██████    | 220/363 [03:06<02:33, 1.08s/it]
Loading 0:  61%|██████    | 221/363 [03:09<03:02, 1.29s/it]
Loading 0:  61%|██████    | 221/363 [03:09<03:02, 1.29s/it]
Loading 0:  63%|██████▎   | 228/363 [03:10<01:16, 1.77it/s]
Loading 0:  63%|██████▎   | 228/363 [03:10<01:16, 1.77it/s]
Loading 0:  64%|██████▍   | 232/363 [03:12<01:20, 1.62it/s]
Loading 0:  64%|██████▍   | 232/363 [03:12<01:20, 1.62it/s]
Loading 0:  64%|██████▍   | 233/363 [03:15<01:42, 1.27it/s]
Loading 0:  64%|██████▍   | 233/363 [03:15<01:42, 1.27it/s]
Loading 0:  64%|██████▍   | 234/363 [03:17<02:11, 1.02s/it]
Loading 0:  64%|██████▍   | 234/363 [03:17<02:11, 1.02s/it]
Loading 0:  65%|██████▌   | 237/363 [03:19<01:55, 1.09it/s]
Loading 0:  65%|██████▌   | 237/363 [03:19<01:55, 1.09it/s]
Loading 0:  66%|██████▌   | 238/363 [03:22<02:17, 1.10s/it]
Loading 0:  66%|██████▌   | 238/363 [03:22<02:17, 1.10s/it]
Loading 0:  66%|██████▌   | 239/363 [03:24<02:41, 1.31s/it]
Loading 0:  66%|██████▌   | 239/363 [03:24<02:41, 1.31s/it]
Loading 0:  68%|██████▊   | 246/363 [03:25<01:07, 1.73it/s]
Loading 0:  68%|██████▊   | 246/363 [03:25<01:07, 1.73it/s]
Loading 0:  69%|██████▉   | 250/363 [03:28<01:09, 1.62it/s]
Loading 0:  69%|██████▉   | 250/363 [03:28<01:09, 1.62it/s]
Loading 0:  69%|██████▉   | 251/363 [03:30<01:27, 1.28it/s]
Loading 0:  69%|██████▉   | 251/363 [03:30<01:27, 1.28it/s]
Loading 0:  69%|██████▉   | 252/363 [03:32<01:49, 1.02it/s]
Loading 0:  69%|██████▉   | 252/363 [03:32<01:49, 1.02it/s]
Loading 0:  70%|███████   | 255/363 [03:34<01:35, 1.13it/s]
Loading 0:  70%|███████   | 255/363 [03:34<01:35, 1.13it/s]
Loading 0:  71%|███████   | 256/363 [03:36<01:55, 1.08s/it]
Loading 0:  71%|███████   | 256/363 [03:36<01:55, 1.08s/it]
Loading 0:  71%|███████   | 257/363 [03:39<02:16, 1.29s/it]
Loading 0:  71%|███████   | 257/363 [03:39<02:16, 1.29s/it]
Loading 0:  73%|███████▎  | 264/363 [03:40<00:56, 1.76it/s]
Loading 0:  73%|███████▎  | 264/363 [03:40<00:56, 1.76it/s]
Loading 0:  74%|███████▍  | 268/363 [03:43<00:58, 1.63it/s]
Loading 0:  74%|███████▍  | 268/363 [03:43<00:58, 1.63it/s]
Loading 0:  74%|███████▍  | 269/363 [03:45<01:13, 1.28it/s]
Loading 0:  74%|███████▍  | 269/363 [03:45<01:13, 1.28it/s]
Loading 0:  74%|███████▍  | 270/363 [03:47<01:31, 1.02it/s]
Loading 0:  74%|███████▍  | 270/363 [03:47<01:31, 1.02it/s]
Loading 0:  75%|███████▌  | 273/363 [04:03<03:55, 2.62s/it]
Loading 0:  75%|███████▌  | 273/363 [04:03<03:55, 2.62s/it]
Loading 0:  75%|███████▌  | 274/363 [04:06<03:46, 2.55s/it]
Loading 0:  75%|███████▌  | 274/363 [04:06<03:46, 2.55s/it]
Loading 0:  76%|███████▌  | 275/363 [04:08<03:40, 2.50s/it]
Loading 0:  76%|███████▌  | 275/363 [04:08<03:40, 2.50s/it]
Loading 0:  78%|███████▊  | 282/363 [04:09<01:21, 1.01s/it]
Loading 0:  78%|███████▊  | 282/363 [04:09<01:21, 1.01s/it]
Loading 0:  79%|███████▉  | 286/363 [04:12<01:08, 1.12it/s]
Loading 0:  79%|███████▉  | 286/363 [04:12<01:08, 1.12it/s]
Loading 0:  79%|███████▉  | 287/363 [04:14<01:17, 1.02s/it]
Loading 0:  79%|███████▉  | 287/363 [04:14<01:17, 1.02s/it]
Loading 0:  79%|███████▉  | 288/363 [04:16<01:29, 1.19s/it]
Loading 0:  79%|███████▉  | 288/363 [04:16<01:29, 1.19s/it]
Loading 0:  80%|████████  | 291/363 [04:18<01:14, 1.03s/it]
Loading 0:  80%|████████  | 291/363 [04:18<01:14, 1.03s/it]
Loading 0:  80%|████████  | 292/363 [04:20<01:25, 1.21s/it]
Loading 0:  80%|████████  | 292/363 [04:20<01:25, 1.21s/it]
Loading 0:  81%|████████  | 293/363 [04:23<01:38, 1.40s/it]
Loading 0:  81%|████████  | 293/363 [04:23<01:38, 1.40s/it]
Loading 0:  83%|████████▎ | 300/363 [04:24<00:38, 1.62it/s]
Loading 0:  83%|████████▎ | 300/363 [04:24<00:38, 1.62it/s]
Loading 0:  84%|████████▎ | 304/363 [04:27<00:37, 1.57it/s]
Loading 0:  84%|████████▎ | 304/363 [04:27<00:37, 1.57it/s]
Loading 0:  84%|████████▍ | 305/363 [04:29<00:46, 1.24it/s]
Loading 0:  84%|████████▍ | 305/363 [04:29<00:46, 1.24it/s]
Loading 0:  84%|████████▍ | 306/363 [04:31<00:57, 1.01s/it]
Loading 0:  84%|████████▍ | 306/363 [04:31<00:57, 1.01s/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 [04:36<00:58, 1.11s/it]
Loading 0:  85%|████████▌ | 310/363 [04:36<00:58, 1.11s/it]
Loading 0:  86%|████████▌ | 311/363 [04:38<01:08, 1.32s/it]
Loading 0:  86%|████████▌ | 311/363 [04:38<01:08, 1.32s/it]
Loading 0:  88%|████████▊ | 318/363 [04:39<00:25, 1.74it/s]
Loading 0:  88%|████████▊ | 318/363 [04:39<00:25, 1.74it/s]
Loading 0:  89%|████████▊ | 322/363 [04:42<00:25, 1.62it/s]
Loading 0:  89%|████████▊ | 322/363 [04:42<00:25, 1.62it/s]
Loading 0:  89%|████████▉ | 323/363 [04:44<00:31, 1.26it/s]
Loading 0:  89%|████████▉ | 323/363 [04:44<00:31, 1.26it/s]
Loading 0:  89%|████████▉ | 324/363 [04:47<00:42, 1.08s/it]
Loading 0:  89%|████████▉ | 324/363 [04:47<00:42, 1.08s/it]
Loading 0:  90%|█████████ | 327/363 [04:49<00:34, 1.04it/s]
Loading 0:  90%|█████████ | 327/363 [04:49<00:34, 1.04it/s]
Loading 0:  90%|█████████ | 328/363 [04:51<00:40, 1.15s/it]
Loading 0:  90%|█████████ | 328/363 [04:51<00:40, 1.15s/it]
Loading 0:  91%|█████████ | 329/363 [04:54<00:46, 1.36s/it]
Loading 0:  91%|█████████ | 329/363 [04:54<00:46, 1.36s/it]
Loading 0:  93%|█████████▎| 336/363 [04:55<00:15, 1.69it/s]
Loading 0:  93%|█████████▎| 336/363 [04:55<00:15, 1.69it/s]
Loading 0:  94%|█████████▎| 340/363 [04:58<00:14, 1.59it/s]
Loading 0:  94%|█████████▎| 340/363 [04:58<00:14, 1.59it/s]
Loading 0:  94%|█████████▍| 341/363 [05:00<00:17, 1.25it/s]
Loading 0:  94%|█████████▍| 341/363 [05:00<00:17, 1.25it/s]
Loading 0:  94%|█████████▍| 342/363 [05:02<00:21, 1.03s/it]
Loading 0:  94%|█████████▍| 342/363 [05:02<00:21, 1.03s/it]
Loading 0:  95%|█████████▌| 345/363 [05:05<00:16, 1.08it/s]
Loading 0:  95%|█████████▌| 345/363 [05:05<00:16, 1.08it/s]
Loading 0:  95%|█████████▌| 346/363 [05:07<00:18, 1.11s/it]
Loading 0:  95%|█████████▌| 346/363 [05:07<00:18, 1.11s/it]
Loading 0:  96%|█████████▌| 347/363 [05:09<00:21, 1.32s/it]
Loading 0:  96%|█████████▌| 347/363 [05:09<00:21, 1.32s/it]
Loading 0:  98%|█████████▊| 354/363 [05:10<00:05, 1.74it/s]
Loading 0:  98%|█████████▊| 354/363 [05:10<00:05, 1.74it/s]
Loading 0:  99%|█████████▉| 359/363 [05:13<00:02, 1.67it/s]
Loading 0:  99%|█████████▉| 359/363 [05:13<00:02, 1.67it/s]
Loading 0:  99%|█████████▉| 360/363 [05:16<00:02, 1.32it/s]
Loading 0:  99%|█████████▉| 360/363 [05:16<00:02, 1.32it/s]
Loading 0:  99%|█████████▉| 361/363 [05:18<00:01, 1.05it/s]
Loading 0:  99%|█████████▉| 361/363 [05:18<00:01, 1.05it/s]
Loading 0: 100%|██████████| 363/363 [05:18<00:00, 1.05it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [05:18<00:00, 1.14it/s]
chaiml-mistral-24b-2048-89940-v2-mkmlizer: The tokenizer you are loading from '/tmp/tmp0wa824y7' 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-2048-89940-v2-mkmlizer: quantized model in 325.534s
chaiml-mistral-24b-2048-89940-v2-mkmlizer: Processed model ChaiML/mistral_24b_2048_gemini_ds_v1_1168_merged in 419.111s
chaiml-mistral-24b-2048-89940-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-2048-89940-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-2048-89940-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia
chaiml-mistral-24b-2048-89940-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia/config.json
chaiml-mistral-24b-2048-89940-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia/special_tokens_map.json
chaiml-mistral-24b-2048-89940-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia/tokenizer_config.json
chaiml-mistral-24b-2048-89940-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia/tokenizer.json
chaiml-mistral-24b-2048-89940-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia/flywheel_model.1.safetensors
chaiml-mistral-24b-2048-89940-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-89940-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral-24b-2048-89940-v2-mkmlizer completed after 520.22s with status: succeeded
Stopping job with name chaiml-mistral-24b-2048-89940-v2-mkmlizer
Pipeline stage MKMLizer completed in 520.65s
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-2048-89940-v2
Waiting for inference service chaiml-mistral-24b-2048-89940-v2 to be ready
Inference service chaiml-mistral-24b-2048-89940-v2 ready after 311.56287240982056s
Pipeline stage MKMLDeployer completed in 312.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7647454738616943s
Received healthy response to inference request in 2.710524559020996s
Received healthy response to inference request in 2.7581350803375244s
Received healthy response to inference request in 2.672339677810669s
Received healthy response to inference request in 2.9253015518188477s
5 requests
0 failed requests
5th percentile: 2.6799766540527346
10th percentile: 2.6876136302947997
20th percentile: 2.7028875827789305
30th percentile: 2.7200466632843017
40th percentile: 2.7390908718109133
50th percentile: 2.7581350803375244
60th percentile: 2.7607792377471925
70th percentile: 2.7634233951568605
80th percentile: 2.796856689453125
90th percentile: 2.8610791206359862
95th percentile: 2.893190336227417
99th percentile: 2.9188793087005616
mean time: 2.766209268569946
Pipeline stage StressChecker completed in 15.09s
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 0.61s
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 0.60s
Shutdown handler de-registered
chaiml-mistral-24b-2048_89940_v2 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-24b-2048-89940-v2-profiler
Waiting for inference service chaiml-mistral-24b-2048-89940-v2-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 2542.36s
Shutdown handler de-registered
chaiml-mistral-24b-2048_89940_v2 status is now inactive due to auto deactivation removed underperforming models