chaiml-2a6f-69d4-linear-w01

developer_uid: richhx
submission_id: chaiml-2a6f-69d4-linear-w01_v23
model_name: chaiml-2a6f-69d4-linear-w01_v23
model_group: ChaiML/2a6f-69d4-linear-
status: torndown
timestamp: 2026-01-16T21:38:23+00:00
num_battles: 12332
num_wins: 6263
celo_rating: 1302.15
family_friendly_score: 0.536
family_friendly_standard_error: 0.007052715788970942
submission_type: basic
model_repo: ChaiML/2a6f-69d4-linear-w01
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 7
max_input_tokens: 1280
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3048219663323685, 'latency_mean': 3.2805383348464967, 'latency_p50': 3.110573410987854, 'latency_p90': 5.627456331253051}, {'batch_size': 3, 'throughput': 1.0280474977932834, 'latency_mean': 2.9114461493492128, 'latency_p50': 2.9143154621124268, 'latency_p90': 3.2416820526123047}, {'batch_size': 5, 'throughput': 1.2882170442445404, 'latency_mean': 3.8553180015087127, 'latency_p50': 3.8462464809417725, 'latency_p90': 4.42471706867218}, {'batch_size': 6, 'throughput': 1.3609496092039342, 'latency_mean': 4.385742189884186, 'latency_p50': 4.426927447319031, 'latency_p90': 4.956046795845031}, {'batch_size': 8, 'throughput': 1.47488162299936, 'latency_mean': 5.392957022190094, 'latency_p50': 5.382807731628418, 'latency_p90': 6.149811029434204}, {'batch_size': 10, 'throughput': 1.5506577829288617, 'latency_mean': 6.3980590736866, 'latency_p50': 6.433342695236206, 'latency_p90': 7.500871992111206}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-2a6f-69d4-linear-w01_v23
is_internal_developer: True
language_model: ChaiML/2a6f-69d4-linear-w01
model_size: 24B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2026-01-13
win_ratio: 0.5078657152124554
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1280, 'best_of': 7, 'max_output_tokens': 64}
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-2a6f-69d4-linear-w01-v23-mkmlizer
Waiting for job on chaiml-2a6f-69d4-linear-w01-v23-mkmlizer to finish
HTTP Request: %s %s "%s %d %s"
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: bash: no job control in this shell
chaiml-2a6f-69d4-linear-w01-v23-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-2a6f-69d4-linear-w01-v23-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  belonging to:                                                      ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: Downloaded to shared memory in 50.090s
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: Checking if ChaiML/2a6f-69d4-linear-w01 already exists in ChaiML
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpxiimum70, device:0
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4.00/363 [00:02<03:04, 1.94it/s]
Loading 0:   1%|          | 4.00/363 [00:02<03:04, 1.94it/s]
Loading 0:   1%|▏         | 5.00/363 [00:03<05:10, 1.15it/s]
Loading 0:   1%|▏         | 5.00/363 [00:03<05:10, 1.15it/s]
Loading 0:   2%|▏         | 6.00/363 [00:05<06:58, 1.17s/it]
Loading 0:   2%|▏         | 6.00/363 [00:05<06:58, 1.17s/it]
Loading 0:   4%|▎         | 13.0/363 [00:08<03:25, 1.71it/s]
Loading 0:   4%|▎         | 13.0/363 [00:08<03:25, 1.71it/s]
Loading 0:   4%|▍         | 14.0/363 [00:10<04:22, 1.33it/s]
Loading 0:   4%|▍         | 14.0/363 [00:10<04:22, 1.33it/s]
Loading 0:   4%|▍         | 15.0/363 [00:12<05:28, 1.06it/s]
Loading 0:   4%|▍         | 15.0/363 [00:12<05:28, 1.06it/s]
Loading 0:   6%|▌         | 22.0/363 [00:15<03:28, 1.64it/s]
Loading 0:   6%|▌         | 22.0/363 [00:15<03:28, 1.64it/s]
Loading 0:   6%|▋         | 23.0/363 [00:16<04:14, 1.33it/s]
Loading 0:   6%|▋         | 23.0/363 [00:16<04:14, 1.33it/s]
Loading 0:   7%|▋         | 24.0/363 [00:18<05:10, 1.09it/s]
Loading 0:   7%|▋         | 24.0/363 [00:18<05:10, 1.09it/s]
Loading 0:   9%|▊         | 31.0/363 [00:21<03:17, 1.68it/s]
Loading 0:   9%|▊         | 31.0/363 [00:21<03:17, 1.68it/s]
Loading 0:   9%|▉         | 32.0/363 [00:23<04:02, 1.37it/s]
Loading 0:   9%|▉         | 32.0/363 [00:23<04:02, 1.37it/s]
Loading 0:   9%|▉         | 33.0/363 [00:25<04:55, 1.12it/s]
Loading 0:   9%|▉         | 33.0/363 [00:25<04:55, 1.12it/s]
Loading 0:  11%|█         | 40.0/363 [00:27<03:11, 1.69it/s]
Loading 0:  11%|█         | 40.0/363 [00:27<03:11, 1.69it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:29<03:52, 1.38it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:29<03:52, 1.38it/s]
Loading 0:  12%|█▏        | 42.0/363 [00:31<04:43, 1.13it/s]
Loading 0:  12%|█▏        | 42.0/363 [00:31<04:43, 1.13it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:34<03:05, 1.69it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:34<03:05, 1.69it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:36<03:46, 1.38it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:36<03:46, 1.38it/s]
Loading 0:  14%|█▍        | 51.0/363 [00:38<04:35, 1.13it/s]
Loading 0:  14%|█▍        | 51.0/363 [00:38<04:35, 1.13it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:40<02:59, 1.69it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:40<02:59, 1.69it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:42<03:45, 1.35it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:42<03:45, 1.35it/s]
Loading 0:  17%|█▋        | 60.0/363 [00:44<04:32, 1.11it/s]
Loading 0:  17%|█▋        | 60.0/363 [00:44<04:32, 1.11it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:47<02:56, 1.67it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:47<02:56, 1.67it/s]
Loading 0:  19%|█▊        | 68.0/363 [00:49<03:34, 1.37it/s]
Loading 0:  19%|█▊        | 68.0/363 [00:49<03:34, 1.37it/s]
Loading 0:  19%|█▉        | 69.0/363 [00:51<04:21, 1.13it/s]
Loading 0:  19%|█▉        | 69.0/363 [00:51<04:21, 1.13it/s]
Loading 0:  21%|██        | 76.0/363 [00:53<02:49, 1.69it/s]
Loading 0:  21%|██        | 76.0/363 [00:53<02:49, 1.69it/s]
Loading 0:  21%|██        | 77.0/363 [00:55<03:26, 1.39it/s]
Loading 0:  21%|██        | 77.0/363 [00:55<03:26, 1.39it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:57<04:11, 1.13it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:57<04:11, 1.13it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:44, 1.69it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:59<02:44, 1.69it/s]
Loading 0:  24%|██▎       | 86.0/363 [01:01<03:19, 1.39it/s]
Loading 0:  24%|██▎       | 86.0/363 [01:01<03:19, 1.39it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:03<04:02, 1.14it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:03<04:02, 1.14it/s]
Loading 0:  26%|██▌       | 94.0/363 [01:06<02:38, 1.70it/s]
Loading 0:  26%|██▌       | 94.0/363 [01:06<02:38, 1.70it/s]
Loading 0:  26%|██▌       | 95.0/363 [01:08<03:12, 1.39it/s]
Loading 0:  26%|██▌       | 95.0/363 [01:08<03:12, 1.39it/s]
Loading 0:  26%|██▋       | 96.0/363 [01:10<04:01, 1.11it/s]
Loading 0:  26%|██▋       | 96.0/363 [01:10<04:01, 1.11it/s]
Loading 0:  28%|██▊       | 103/363 [01:12<02:35, 1.67it/s] 
Loading 0:  28%|██▊       | 103/363 [01:12<02:35, 1.67it/s]
Loading 0:  29%|██▊       | 104/363 [01:14<03:08, 1.38it/s]
Loading 0:  29%|██▊       | 104/363 [01:14<03:08, 1.38it/s]
Loading 0:  29%|██▉       | 105/363 [01:16<03:48, 1.13it/s]
Loading 0:  29%|██▉       | 105/363 [01:16<03:48, 1.13it/s]
Loading 0:  31%|███       | 112/363 [01:19<02:28, 1.70it/s]
Loading 0:  31%|███       | 112/363 [01:19<02:28, 1.70it/s]
Loading 0:  31%|███       | 113/363 [01:20<03:00, 1.39it/s]
Loading 0:  31%|███       | 113/363 [01:20<03:00, 1.39it/s]
Loading 0:  31%|███▏      | 114/363 [01:22<03:39, 1.13it/s]
Loading 0:  31%|███▏      | 114/363 [01:22<03:39, 1.13it/s]
Loading 0:  33%|███▎      | 121/363 [01:25<02:22, 1.70it/s]
Loading 0:  33%|███▎      | 121/363 [01:25<02:22, 1.70it/s]
Loading 0:  34%|███▎      | 122/363 [01:27<02:53, 1.39it/s]
Loading 0:  34%|███▎      | 122/363 [01:27<02:53, 1.39it/s]
Loading 0:  34%|███▍      | 123/363 [01:29<03:31, 1.14it/s]
Loading 0:  34%|███▍      | 123/363 [01:29<03:31, 1.14it/s]
Loading 0:  36%|███▌      | 130/363 [01:31<02:16, 1.70it/s]
Loading 0:  36%|███▌      | 130/363 [01:31<02:16, 1.70it/s]
Loading 0:  36%|███▌      | 131/363 [01:33<02:46, 1.39it/s]
Loading 0:  36%|███▌      | 131/363 [01:33<02:46, 1.39it/s]
Loading 0:  36%|███▋      | 132/363 [01:35<03:22, 1.14it/s]
Loading 0:  36%|███▋      | 132/363 [01:35<03:22, 1.14it/s]
Loading 0:  38%|███▊      | 139/363 [01:38<02:14, 1.67it/s]
Loading 0:  38%|███▊      | 139/363 [01:38<02:14, 1.67it/s]
Loading 0:  39%|███▊      | 140/363 [01:40<02:42, 1.37it/s]
Loading 0:  39%|███▊      | 140/363 [01:40<02:42, 1.37it/s]
Loading 0:  39%|███▉      | 141/363 [01:42<03:16, 1.13it/s]
Loading 0:  39%|███▉      | 141/363 [01:42<03:16, 1.13it/s]
Loading 0:  41%|████      | 148/363 [01:44<02:06, 1.70it/s]
Loading 0:  41%|████      | 148/363 [01:44<02:06, 1.70it/s]
Loading 0:  41%|████      | 149/363 [01:46<02:33, 1.39it/s]
Loading 0:  41%|████      | 149/363 [01:46<02:33, 1.39it/s]
Loading 0:  41%|████▏     | 150/363 [01:48<03:07, 1.14it/s]
Loading 0:  41%|████▏     | 150/363 [01:48<03:07, 1.14it/s]
Loading 0:  43%|████▎     | 157/363 [01:51<02:01, 1.70it/s]
Loading 0:  43%|████▎     | 157/363 [01:51<02:01, 1.70it/s]
Loading 0:  44%|████▎     | 158/363 [01:52<02:27, 1.39it/s]
Loading 0:  44%|████▎     | 158/363 [01:52<02:27, 1.39it/s]
Loading 0:  44%|████▍     | 159/363 [01:54<02:59, 1.14it/s]
Loading 0:  44%|████▍     | 159/363 [01:54<02:59, 1.14it/s]
Loading 0:  46%|████▌     | 166/363 [01:57<01:55, 1.70it/s]
Loading 0:  46%|████▌     | 166/363 [01:57<01:55, 1.70it/s]
Loading 0:  46%|████▌     | 167/363 [01:59<02:20, 1.39it/s]
Loading 0:  46%|████▌     | 167/363 [01:59<02:20, 1.39it/s]
Loading 0:  46%|████▋     | 168/363 [02:01<02:51, 1.14it/s]
Loading 0:  46%|████▋     | 168/363 [02:01<02:51, 1.14it/s]
Loading 0:  48%|████▊     | 175/363 [02:03<01:50, 1.70it/s]
Loading 0:  48%|████▊     | 175/363 [02:03<01:50, 1.70it/s]
Loading 0:  48%|████▊     | 176/363 [02:05<02:17, 1.36it/s]
Loading 0:  48%|████▊     | 176/363 [02:05<02:17, 1.36it/s]
Loading 0:  49%|████▉     | 177/363 [02:07<02:45, 1.12it/s]
Loading 0:  49%|████▉     | 177/363 [02:07<02:45, 1.12it/s]
Loading 0:  51%|█████     | 184/363 [02:10<01:46, 1.68it/s]
Loading 0:  51%|█████     | 184/363 [02:10<01:46, 1.68it/s]
Loading 0:  51%|█████     | 185/363 [02:12<02:08, 1.38it/s]
Loading 0:  51%|█████     | 185/363 [02:12<02:08, 1.38it/s]
Loading 0:  51%|█████     | 186/363 [02:14<02:36, 1.13it/s]
Loading 0:  51%|█████     | 186/363 [02:14<02:36, 1.13it/s]
Loading 0:  53%|█████▎    | 193/363 [02:16<01:40, 1.69it/s]
Loading 0:  53%|█████▎    | 193/363 [02:16<01:40, 1.69it/s]
Loading 0:  53%|█████▎    | 194/363 [02:18<02:01, 1.39it/s]
Loading 0:  53%|█████▎    | 194/363 [02:18<02:01, 1.39it/s]
Loading 0:  54%|█████▎    | 195/363 [02:20<02:27, 1.14it/s]
Loading 0:  54%|█████▎    | 195/363 [02:20<02:27, 1.14it/s]
Loading 0:  56%|█████▌    | 202/363 [02:22<01:34, 1.70it/s]
Loading 0:  56%|█████▌    | 202/363 [02:22<01:34, 1.70it/s]
Loading 0:  56%|█████▌    | 203/363 [02:24<01:54, 1.39it/s]
Loading 0:  56%|█████▌    | 203/363 [02:24<01:54, 1.39it/s]
Loading 0:  56%|█████▌    | 204/363 [02:26<02:19, 1.14it/s]
Loading 0:  56%|█████▌    | 204/363 [02:26<02:19, 1.14it/s]
Loading 0:  58%|█████▊    | 211/363 [02:29<01:29, 1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [02:29<01:29, 1.70it/s]
Loading 0:  58%|█████▊    | 212/363 [02:31<01:48, 1.39it/s]
Loading 0:  58%|█████▊    | 212/363 [02:31<01:48, 1.39it/s]
Loading 0:  59%|█████▊    | 213/363 [02:33<02:15, 1.11it/s]
Loading 0:  59%|█████▊    | 213/363 [02:33<02:15, 1.11it/s]
Loading 0:  61%|██████    | 220/363 [02:35<01:25, 1.67it/s]
Loading 0:  61%|██████    | 220/363 [02:35<01:25, 1.67it/s]
Loading 0:  61%|██████    | 221/363 [02:37<01:43, 1.38it/s]
Loading 0:  61%|██████    | 221/363 [02:37<01:43, 1.38it/s]
Loading 0:  61%|██████    | 222/363 [02:39<02:04, 1.13it/s]
Loading 0:  61%|██████    | 222/363 [02:39<02:04, 1.13it/s]
Loading 0:  63%|██████▎   | 229/363 [02:42<01:18, 1.70it/s]
Loading 0:  63%|██████▎   | 229/363 [02:42<01:18, 1.70it/s]
Loading 0:  63%|██████▎   | 230/363 [02:43<01:35, 1.39it/s]
Loading 0:  63%|██████▎   | 230/363 [02:43<01:35, 1.39it/s]
Loading 0:  64%|██████▎   | 231/363 [02:58<05:34, 2.53s/it]
Loading 0:  64%|██████▎   | 231/363 [02:58<05:34, 2.53s/it]
Loading 0:  66%|██████▌   | 238/363 [03:01<02:43, 1.31s/it]
Loading 0:  66%|██████▌   | 238/363 [03:01<02:43, 1.31s/it]
Loading 0:  66%|██████▌   | 239/363 [03:02<02:47, 1.35s/it]
Loading 0:  66%|██████▌   | 239/363 [03:02<02:47, 1.35s/it]
Loading 0:  66%|██████▌   | 240/363 [03:04<02:55, 1.43s/it]
Loading 0:  66%|██████▌   | 240/363 [03:04<02:55, 1.43s/it]
Loading 0:  68%|██████▊   | 247/363 [03:07<01:34, 1.23it/s]
Loading 0:  68%|██████▊   | 247/363 [03:07<01:34, 1.23it/s]
Loading 0:  68%|██████▊   | 248/363 [03:08<01:44, 1.10it/s]
Loading 0:  68%|██████▊   | 248/363 [03:08<01:44, 1.10it/s]
Loading 0:  69%|██████▊   | 249/363 [03:10<01:58, 1.04s/it]
Loading 0:  69%|██████▊   | 249/363 [03:10<01:58, 1.04s/it]
Loading 0:  71%|███████   | 256/363 [03:13<01:11, 1.50it/s]
Loading 0:  71%|███████   | 256/363 [03:13<01:11, 1.50it/s]
Loading 0:  71%|███████   | 257/363 [03:15<01:23, 1.27it/s]
Loading 0:  71%|███████   | 257/363 [03:15<01:23, 1.27it/s]
Loading 0:  71%|███████   | 258/363 [03:17<01:38, 1.07it/s]
Loading 0:  71%|███████   | 258/363 [03:17<01:38, 1.07it/s]
Loading 0:  73%|███████▎  | 265/363 [03:19<00:59, 1.66it/s]
Loading 0:  73%|███████▎  | 265/363 [03:19<00:59, 1.66it/s]
Loading 0:  73%|███████▎  | 266/363 [03:21<01:09, 1.39it/s]
Loading 0:  73%|███████▎  | 266/363 [03:21<01:09, 1.39it/s]
Loading 0:  74%|███████▎  | 267/363 [03:23<01:24, 1.14it/s]
Loading 0:  74%|███████▎  | 267/363 [03:23<01:24, 1.14it/s]
Loading 0:  75%|███████▌  | 274/363 [03:25<00:50, 1.75it/s]
Loading 0:  75%|███████▌  | 274/363 [03:25<00:50, 1.75it/s]
Loading 0:  76%|███████▌  | 275/363 [03:27<01:01, 1.42it/s]
Loading 0:  76%|███████▌  | 275/363 [03:27<01:01, 1.42it/s]
Loading 0:  76%|███████▌  | 276/363 [03:29<01:15, 1.16it/s]
Loading 0:  76%|███████▌  | 276/363 [03:29<01:15, 1.16it/s]
Loading 0:  78%|███████▊  | 283/363 [03:31<00:45, 1.76it/s]
Loading 0:  78%|███████▊  | 283/363 [03:31<00:45, 1.76it/s]
Loading 0:  78%|███████▊  | 284/363 [03:33<00:54, 1.45it/s]
Loading 0:  78%|███████▊  | 284/363 [03:33<00:54, 1.45it/s]
Loading 0:  79%|███████▊  | 285/363 [03:35<01:06, 1.17it/s]
Loading 0:  79%|███████▊  | 285/363 [03:35<01:06, 1.17it/s]
Loading 0:  80%|████████  | 292/363 [03:38<00:39, 1.78it/s]
Loading 0:  80%|████████  | 292/363 [03:38<00:39, 1.78it/s]
Loading 0:  81%|████████  | 293/363 [03:39<00:48, 1.43it/s]
Loading 0:  81%|████████  | 293/363 [03:39<00:48, 1.43it/s]
Loading 0:  81%|████████  | 294/363 [03:41<00:59, 1.16it/s]
Loading 0:  81%|████████  | 294/363 [03:41<00:59, 1.16it/s]
Loading 0:  83%|████████▎ | 301/363 [03:44<00:35, 1.72it/s]
Loading 0:  83%|████████▎ | 301/363 [03:44<00:35, 1.72it/s]
Loading 0:  83%|████████▎ | 302/363 [03:46<00:43, 1.41it/s]
Loading 0:  83%|████████▎ | 302/363 [03:46<00:43, 1.41it/s]
Loading 0:  83%|████████▎ | 303/363 [03:48<00:52, 1.15it/s]
Loading 0:  83%|████████▎ | 303/363 [03:48<00:52, 1.15it/s]
Loading 0:  85%|████████▌ | 310/363 [03:50<00:30, 1.72it/s]
Loading 0:  85%|████████▌ | 310/363 [03:50<00:30, 1.72it/s]
Loading 0:  86%|████████▌ | 311/363 [03:52<00:36, 1.41it/s]
Loading 0:  86%|████████▌ | 311/363 [03:52<00:36, 1.41it/s]
Loading 0:  86%|████████▌ | 312/363 [03:54<00:44, 1.15it/s]
Loading 0:  86%|████████▌ | 312/363 [03:54<00:44, 1.15it/s]
Loading 0:  88%|████████▊ | 319/363 [03:57<00:25, 1.72it/s]
Loading 0:  88%|████████▊ | 319/363 [03:57<00:25, 1.72it/s]
Loading 0:  88%|████████▊ | 320/363 [03:58<00:30, 1.40it/s]
Loading 0:  88%|████████▊ | 320/363 [03:58<00:30, 1.40it/s]
Loading 0:  88%|████████▊ | 321/363 [04:00<00:36, 1.15it/s]
Loading 0:  88%|████████▊ | 321/363 [04:00<00:36, 1.15it/s]
Loading 0:  90%|█████████ | 328/363 [04:03<00:20, 1.72it/s]
Loading 0:  90%|█████████ | 328/363 [04:03<00:20, 1.72it/s]
Loading 0:  91%|█████████ | 329/363 [04:05<00:24, 1.40it/s]
Loading 0:  91%|█████████ | 329/363 [04:05<00:24, 1.40it/s]
Loading 0:  91%|█████████ | 330/363 [04:07<00:29, 1.11it/s]
Loading 0:  91%|█████████ | 330/363 [04:07<00:29, 1.11it/s]
Loading 0:  93%|█████████▎| 337/363 [04:09<00:15, 1.69it/s]
Loading 0:  93%|█████████▎| 337/363 [04:09<00:15, 1.69it/s]
Loading 0:  93%|█████████▎| 338/363 [04:11<00:18, 1.38it/s]
Loading 0:  93%|█████████▎| 338/363 [04:11<00:18, 1.38it/s]
Loading 0:  93%|█████████▎| 339/363 [04:13<00:21, 1.14it/s]
Loading 0:  93%|█████████▎| 339/363 [04:13<00:21, 1.14it/s]
Loading 0:  95%|█████████▌| 346/363 [04:16<00:09, 1.71it/s]
Loading 0:  95%|█████████▌| 346/363 [04:16<00:09, 1.71it/s]
Loading 0:  96%|█████████▌| 347/363 [04:17<00:11, 1.40it/s]
Loading 0:  96%|█████████▌| 347/363 [04:17<00:11, 1.40it/s]
Loading 0:  96%|█████████▌| 348/363 [04:19<00:13, 1.14it/s]
Loading 0:  96%|█████████▌| 348/363 [04:19<00:13, 1.14it/s]
Loading 0:  98%|█████████▊| 355/363 [04:22<00:04, 1.71it/s]
Loading 0:  98%|█████████▊| 355/363 [04:22<00:04, 1.71it/s]
Loading 0:  98%|█████████▊| 356/363 [04:24<00:05, 1.40it/s]
Loading 0:  98%|█████████▊| 356/363 [04:24<00:05, 1.40it/s]
Loading 0:  98%|█████████▊| 357/363 [04:26<00:05, 1.14it/s]
Loading 0:  98%|█████████▊| 357/363 [04:26<00:05, 1.14it/s]
Loading 0: 100%|██████████| 363/363 [04:26<00:00, 2.09it/s]
Loading 0: 100%|██████████| 363/363 [04:26<00:00, 2.09it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [04:26<00:00, 1.36it/s]
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: The tokenizer you are loading from '/tmp/tmpxiimum70' 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-2a6f-69d4-linear-w01-v23-mkmlizer: quantized model in 273.258s
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: Processed model ChaiML/2a6f-69d4-linear-w01 in 323.349s
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/config.json
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/chat_template.jinja s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/chat_template.jinja
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/special_tokens_map.json
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/tokenizer_config.json
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/tokenizer.json
HTTP Request: %s %s "%s %d %s"
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/flywheel_model.1.safetensors
chaiml-2a6f-69d4-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v23/nvidia/flywheel_model.0.safetensors
Job chaiml-2a6f-69d4-linear-w01-v23-mkmlizer completed after 451.67s with status: succeeded
Stopping job with name chaiml-2a6f-69d4-linear-w01-v23-mkmlizer
Pipeline stage MKMLizer completed in 452.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-2a6f-69d4-linear-w01-v23
Waiting for inference service chaiml-2a6f-69d4-linear-w01-v23 to be ready
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-2a6f-69d4-linear-w01-v23 ready after 181.60968351364136s
Pipeline stage MKMLDeployer completed in 182.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.049225330352783s
Received healthy response to inference request in 3.0673887729644775s
Received healthy response to inference request in 1.878103494644165s
Received healthy response to inference request in 2.6607372760772705s
Received healthy response to inference request in 2.189147472381592s
5 requests
0 failed requests
5th percentile: 1.9123278617858888
10th percentile: 1.9465522289276123
20th percentile: 2.0150009632110595
30th percentile: 2.0772097587585447
40th percentile: 2.1331786155700683
50th percentile: 2.189147472381592
60th percentile: 2.3777833938598634
70th percentile: 2.5664193153381345
80th percentile: 2.742067575454712
90th percentile: 2.9047281742095947
95th percentile: 2.986058473587036
99th percentile: 3.051122713088989
mean time: 2.3689204692840575
Pipeline stage StressChecker completed in 13.14s
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 0.71s
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 0.59s
Shutdown handler de-registered
chaiml-2a6f-69d4-linear-w01_v23 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-2a6f-69d4-linear-w01-v23-profiler
Waiting for inference service chaiml-2a6f-69d4-linear-w01-v23-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 2796.86s
Shutdown handler de-registered
chaiml-2a6f-69d4-linear-w01_v23 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-2a6f-69d4-linear-w01_v23
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Falling back to EndpointApi.from_submission implementation
run pipeline stage %s
Running pipeline stage MKMLDeleter
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Checking if service chaiml-2a6f-69d4-linear-w01-v23 is running
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Tearing down inference service chaiml-2a6f-69d4-linear-w01-v23
Service chaiml-2a6f-69d4-linear-w01-v23 has been torndown
Pipeline stage MKMLDeleter completed in 0.88s
run pipeline stage %s
Falling back to EndpointApi.from_submission implementation
Running pipeline stage MKMLModelDeleter
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Cleaning model data from S3
Falling back to EndpointApi.from_submission implementation
Cleaning model data from model cache
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/chat_template.jinja from bucket guanaco-mkml-models
Falling back to EndpointApi.from_submission implementation
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/config.json from bucket guanaco-mkml-models
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/flywheel_model.1.safetensors from bucket guanaco-mkml-models
HTTP Request: %s %s "%s %d %s"
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/special_tokens_map.json from bucket guanaco-mkml-models
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/tokenizer.json from bucket guanaco-mkml-models
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Deleting key chaiml-2a6f-69d4-linear-w01-v23/nvidia/tokenizer_config.json from bucket guanaco-mkml-models
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Pipeline stage MKMLModelDeleter completed in 6.66s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Shutdown handler de-registered
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
chaiml-2a6f-69d4-linear-w01_v23 status is now torndown due to DeploymentManager action
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation