chaiml-4d70-fd43-linear-w01

developer_uid: chai_backend_admin
submission_id: chaiml-4d70-fd43-linear-w01_v26
model_name: chaiml-4d70-fd43-linear-w01_v26
model_group: ChaiML/4d70-fd43-linear-
status: torndown
timestamp: 2025-12-30T03:21:36+00:00
num_battles: 8612
num_wins: 4427
celo_rating: 1323.49
family_friendly_score: 0.5174000000000001
family_friendly_standard_error: 0.007066784841779181
submission_type: basic
model_repo: ChaiML/4d70-fd43-linear-w01
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1800
max_output_tokens: 74
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.7245303511093915, 'latency_mean': 1.3801419425010681, 'latency_p50': 1.380471110343933, 'latency_p90': 1.513028049468994}, {'batch_size': 3, 'throughput': 1.3705824835533158, 'latency_mean': 2.185387716293335, 'latency_p50': 2.1678595542907715, 'latency_p90': 2.3730018615722654}, {'batch_size': 5, 'throughput': 1.67655740189324, 'latency_mean': 2.9738988280296326, 'latency_p50': 2.95649516582489, 'latency_p90': 3.3647944211959837}, {'batch_size': 6, 'throughput': 1.7660739938864836, 'latency_mean': 3.372633408308029, 'latency_p50': 3.3647643327713013, 'latency_p90': 3.7734200239181517}, {'batch_size': 8, 'throughput': 1.8893575771212894, 'latency_mean': 4.186230306625366, 'latency_p50': 4.151395559310913, 'latency_p90': 4.7081313848495485}, {'batch_size': 10, 'throughput': 1.9556816012016285, 'latency_mean': 5.0812655961513515, 'latency_p50': 5.042842984199524, 'latency_p90': 5.7289972543716425}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-4d70-fd43-linear-w01_v26
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/4d70-fd43-linear-w01
model_size: 13B
ranking_group: single
throughput_3p7s: 1.84
us_pacific_date: 2025-12-26
win_ratio: 0.5140501625638644
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['</s>', '<|im_start|>', '<|im_end|>', '###', '\n'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-4d70-fd43-linear-w01-v26-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v26-mkmlizer to finish
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: bash: no job control in this shell
chaiml-4d70-fd43-linear-w01-v26-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-4d70-fd43-linear-w01-v26-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  belonging to:                                                      ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: Downloaded to shared memory in 20.558s
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: Checking if ChaiML/4d70-fd43-linear-w01 already exists in ChaiML
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpnf4x3wex, device:0
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4.00/363 [00:01<01:30, 3.95it/s]
Loading 0:   1%|          | 4.00/363 [00:01<01:30, 3.95it/s]
Loading 0:   2%|▏         | 6.00/363 [00:02<03:06, 1.91it/s]
Loading 0:   2%|▏         | 6.00/363 [00:02<03:06, 1.91it/s]
Loading 0:   4%|▎         | 13.0/363 [00:04<01:51, 3.15it/s]
Loading 0:   4%|▎         | 13.0/363 [00:04<01:51, 3.15it/s]
Loading 0:   4%|▍         | 15.0/363 [00:06<02:37, 2.21it/s]
Loading 0:   4%|▍         | 15.0/363 [00:06<02:37, 2.21it/s]
Loading 0:   6%|▌         | 22.0/363 [00:07<01:52, 3.04it/s]
Loading 0:   6%|▌         | 22.0/363 [00:07<01:52, 3.04it/s]
Loading 0:   7%|▋         | 24.0/363 [00:09<02:24, 2.35it/s]
Loading 0:   7%|▋         | 24.0/363 [00:09<02:24, 2.35it/s]
Loading 0:   9%|▊         | 31.0/363 [00:11<01:49, 3.04it/s]
Loading 0:   9%|▊         | 31.0/363 [00:11<01:49, 3.04it/s]
Loading 0:   9%|▉         | 33.0/363 [00:12<02:18, 2.39it/s]
Loading 0:   9%|▉         | 33.0/363 [00:12<02:18, 2.39it/s]
Loading 0:  11%|█         | 40.0/363 [00:14<01:49, 2.94it/s]
Loading 0:  11%|█         | 40.0/363 [00:14<01:49, 2.94it/s]
Loading 0:  12%|█▏        | 42.0/363 [00:16<02:16, 2.36it/s]
Loading 0:  12%|█▏        | 42.0/363 [00:16<02:16, 2.36it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:17<01:45, 2.99it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:17<01:45, 2.99it/s]
Loading 0:  14%|█▍        | 51.0/363 [00:19<02:10, 2.39it/s]
Loading 0:  14%|█▍        | 51.0/363 [00:19<02:10, 2.39it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:21<01:41, 3.01it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:21<01:41, 3.01it/s]
Loading 0:  17%|█▋        | 60.0/363 [00:22<02:05, 2.41it/s]
Loading 0:  17%|█▋        | 60.0/363 [00:22<02:05, 2.41it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:24<01:37, 3.03it/s]
Loading 0:  18%|█▊        | 67.0/363 [00:24<01:37, 3.03it/s]
Loading 0:  19%|█▉        | 69.0/363 [00:26<02:01, 2.42it/s]
Loading 0:  19%|█▉        | 69.0/363 [00:26<02:01, 2.42it/s]
Loading 0:  21%|██        | 76.0/363 [00:27<01:34, 3.04it/s]
Loading 0:  21%|██        | 76.0/363 [00:27<01:34, 3.04it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:29<01:57, 2.43it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:29<01:57, 2.43it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:30<01:31, 3.05it/s]
Loading 0:  23%|██▎       | 85.0/363 [00:30<01:31, 3.05it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:32<01:52, 2.44it/s]
Loading 0:  24%|██▍       | 87.0/363 [00:32<01:52, 2.44it/s]
Loading 0:  26%|██▌       | 94.0/363 [00:34<01:28, 3.05it/s]
Loading 0:  26%|██▌       | 94.0/363 [00:34<01:28, 3.05it/s]
Loading 0:  26%|██▋       | 96.0/363 [00:35<01:49, 2.44it/s]
Loading 0:  26%|██▋       | 96.0/363 [00:35<01:49, 2.44it/s]
Loading 0:  28%|██▊       | 103/363 [00:37<01:24, 3.07it/s] 
Loading 0:  28%|██▊       | 103/363 [00:37<01:24, 3.07it/s]
Loading 0:  29%|██▉       | 105/363 [00:39<01:45, 2.45it/s]
Loading 0:  29%|██▉       | 105/363 [00:39<01:45, 2.45it/s]
Loading 0:  31%|███       | 112/363 [00:40<01:21, 3.06it/s]
Loading 0:  31%|███       | 112/363 [00:40<01:21, 3.06it/s]
Loading 0:  31%|███▏      | 114/363 [00:42<01:41, 2.45it/s]
Loading 0:  31%|███▏      | 114/363 [00:42<01:41, 2.45it/s]
Loading 0:  33%|███▎      | 121/363 [00:44<01:21, 2.97it/s]
Loading 0:  33%|███▎      | 121/363 [00:44<01:21, 2.97it/s]
Loading 0:  34%|███▍      | 123/363 [00:45<01:40, 2.40it/s]
Loading 0:  34%|███▍      | 123/363 [00:45<01:40, 2.40it/s]
Loading 0:  36%|███▌      | 130/363 [00:47<01:17, 3.02it/s]
Loading 0:  36%|███▌      | 130/363 [00:47<01:17, 3.02it/s]
Loading 0:  36%|███▋      | 132/363 [00:49<01:35, 2.43it/s]
Loading 0:  36%|███▋      | 132/363 [00:49<01:35, 2.43it/s]
Loading 0:  38%|███▊      | 139/363 [00:50<01:13, 3.05it/s]
Loading 0:  38%|███▊      | 139/363 [00:50<01:13, 3.05it/s]
Loading 0:  39%|███▉      | 141/363 [00:52<01:31, 2.44it/s]
Loading 0:  39%|███▉      | 141/363 [00:52<01:31, 2.44it/s]
Loading 0:  41%|████      | 148/363 [00:54<01:10, 3.05it/s]
Loading 0:  41%|████      | 148/363 [00:54<01:10, 3.05it/s]
Loading 0:  41%|████▏     | 150/363 [00:55<01:27, 2.44it/s]
Loading 0:  41%|████▏     | 150/363 [00:55<01:27, 2.44it/s]
Loading 0:  43%|████▎     | 157/363 [00:57<01:06, 3.08it/s]
Loading 0:  43%|████▎     | 157/363 [00:57<01:06, 3.08it/s]
Loading 0:  44%|████▍     | 159/363 [00:58<01:22, 2.46it/s]
Loading 0:  44%|████▍     | 159/363 [00:58<01:22, 2.46it/s]
Loading 0:  46%|████▌     | 166/363 [01:00<01:03, 3.09it/s]
Loading 0:  46%|████▌     | 166/363 [01:00<01:03, 3.09it/s]
Loading 0:  46%|████▋     | 168/363 [01:02<01:18, 2.47it/s]
Loading 0:  46%|████▋     | 168/363 [01:02<01:18, 2.47it/s]
Loading 0:  48%|████▊     | 175/363 [01:03<01:00, 3.09it/s]
Loading 0:  48%|████▊     | 175/363 [01:03<01:00, 3.09it/s]
Loading 0:  49%|████▉     | 177/363 [01:05<01:15, 2.46it/s]
Loading 0:  49%|████▉     | 177/363 [01:05<01:15, 2.46it/s]
Loading 0:  51%|█████     | 184/363 [01:06<00:58, 3.08it/s]
Loading 0:  51%|█████     | 184/363 [01:06<00:58, 3.08it/s]
Loading 0:  51%|█████     | 186/363 [01:08<01:11, 2.47it/s]
Loading 0:  51%|█████     | 186/363 [01:08<01:11, 2.47it/s]
Loading 0:  53%|█████▎    | 193/363 [01:10<00:55, 3.08it/s]
Loading 0:  53%|█████▎    | 193/363 [01:10<00:55, 3.08it/s]
Loading 0:  54%|█████▎    | 195/363 [01:11<01:08, 2.46it/s]
Loading 0:  54%|█████▎    | 195/363 [01:11<01:08, 2.46it/s]
Loading 0:  56%|█████▌    | 202/363 [01:13<00:54, 2.98it/s]
Loading 0:  56%|█████▌    | 202/363 [01:13<00:54, 2.98it/s]
Loading 0:  56%|█████▌    | 204/363 [01:15<01:05, 2.41it/s]
Loading 0:  56%|█████▌    | 204/363 [01:15<01:05, 2.41it/s]
Loading 0:  58%|█████▊    | 211/363 [01:16<00:50, 3.03it/s]
Loading 0:  58%|█████▊    | 211/363 [01:16<00:50, 3.03it/s]
Loading 0:  59%|█████▊    | 213/363 [01:18<01:01, 2.44it/s]
Loading 0:  59%|█████▊    | 213/363 [01:18<01:01, 2.44it/s]
Loading 0:  61%|██████    | 220/363 [01:20<00:46, 3.05it/s]
Loading 0:  61%|██████    | 220/363 [01:20<00:46, 3.05it/s]
Loading 0:  61%|██████    | 222/363 [01:21<00:57, 2.45it/s]
Loading 0:  61%|██████    | 222/363 [01:21<00:57, 2.45it/s]
Loading 0:  63%|██████▎   | 229/363 [01:23<00:43, 3.06it/s]
Loading 0:  63%|██████▎   | 229/363 [01:23<00:43, 3.06it/s]
Loading 0:  64%|██████▎   | 231/363 [01:25<00:53, 2.45it/s]
Loading 0:  64%|██████▎   | 231/363 [01:25<00:53, 2.45it/s]
Loading 0:  66%|██████▌   | 238/363 [01:26<00:40, 3.07it/s]
Loading 0:  66%|██████▌   | 238/363 [01:26<00:40, 3.07it/s]
Loading 0:  66%|██████▌   | 240/363 [01:28<00:50, 2.46it/s]
Loading 0:  66%|██████▌   | 240/363 [01:28<00:50, 2.46it/s]
Loading 0:  68%|██████▊   | 247/363 [01:29<00:37, 3.07it/s]
Loading 0:  68%|██████▊   | 247/363 [01:29<00:37, 3.07it/s]
Loading 0:  69%|██████▊   | 249/363 [01:31<00:46, 2.46it/s]
Loading 0:  69%|██████▊   | 249/363 [01:31<00:46, 2.46it/s]
Loading 0:  71%|███████   | 256/363 [01:33<00:34, 3.08it/s]
Loading 0:  71%|███████   | 256/363 [01:33<00:34, 3.08it/s]
Loading 0:  71%|███████   | 258/363 [01:34<00:42, 2.46it/s]
Loading 0:  71%|███████   | 258/363 [01:34<00:42, 2.46it/s]
Loading 0:  73%|███████▎  | 265/363 [01:36<00:31, 3.07it/s]
Loading 0:  73%|███████▎  | 265/363 [01:36<00:31, 3.07it/s]
Loading 0:  74%|███████▎  | 267/363 [01:38<00:39, 2.46it/s]
Loading 0:  74%|███████▎  | 267/363 [01:38<00:39, 2.46it/s]
Loading 0:  75%|███████▌  | 274/363 [01:39<00:29, 3.07it/s]
Loading 0:  75%|███████▌  | 274/363 [01:39<00:29, 3.07it/s]
Loading 0:  76%|███████▌  | 276/363 [01:41<00:35, 2.46it/s]
Loading 0:  76%|███████▌  | 276/363 [01:41<00:35, 2.46it/s]
Loading 0:  78%|███████▊  | 283/363 [01:43<00:26, 2.98it/s]
Loading 0:  78%|███████▊  | 283/363 [01:43<00:26, 2.98it/s]
Loading 0:  79%|███████▊  | 285/363 [01:44<00:32, 2.41it/s]
Loading 0:  79%|███████▊  | 285/363 [01:44<00:32, 2.41it/s]
Loading 0:  80%|████████  | 292/363 [01:46<00:23, 3.03it/s]
Loading 0:  80%|████████  | 292/363 [01:46<00:23, 3.03it/s]
Loading 0:  81%|████████  | 294/363 [01:48<00:28, 2.44it/s]
Loading 0:  81%|████████  | 294/363 [01:48<00:28, 2.44it/s]
Loading 0:  83%|████████▎ | 301/363 [01:49<00:20, 3.06it/s]
Loading 0:  83%|████████▎ | 301/363 [01:49<00:20, 3.06it/s]
Loading 0:  83%|████████▎ | 303/363 [01:51<00:24, 2.45it/s]
Loading 0:  83%|████████▎ | 303/363 [01:51<00:24, 2.45it/s]
Loading 0:  85%|████████▌ | 310/363 [01:52<00:17, 3.06it/s]
Loading 0:  85%|████████▌ | 310/363 [01:52<00:17, 3.06it/s]
Loading 0:  86%|████████▌ | 312/363 [01:54<00:20, 2.45it/s]
Loading 0:  86%|████████▌ | 312/363 [01:54<00:20, 2.45it/s]
Loading 0:  88%|████████▊ | 319/363 [01:56<00:14, 3.06it/s]
Loading 0:  88%|████████▊ | 319/363 [01:56<00:14, 3.06it/s]
Loading 0:  88%|████████▊ | 321/363 [01:57<00:17, 2.45it/s]
Loading 0:  88%|████████▊ | 321/363 [01:57<00:17, 2.45it/s]
Loading 0:  90%|█████████ | 328/363 [01:59<00:11, 3.06it/s]
Loading 0:  90%|█████████ | 328/363 [01:59<00:11, 3.06it/s]
Loading 0:  91%|█████████ | 330/363 [02:01<00:13, 2.45it/s]
Loading 0:  91%|█████████ | 330/363 [02:01<00:13, 2.45it/s]
Loading 0:  93%|█████████▎| 337/363 [02:02<00:08, 3.07it/s]
Loading 0:  93%|█████████▎| 337/363 [02:02<00:08, 3.07it/s]
Loading 0:  93%|█████████▎| 339/363 [02:04<00:09, 2.46it/s]
Loading 0:  93%|█████████▎| 339/363 [02:04<00:09, 2.46it/s]
Loading 0:  95%|█████████▌| 346/363 [02:05<00:05, 3.07it/s]
Loading 0:  95%|█████████▌| 346/363 [02:05<00:05, 3.07it/s]
Loading 0:  96%|█████████▌| 348/363 [02:07<00:06, 2.46it/s]
Loading 0:  96%|█████████▌| 348/363 [02:07<00:06, 2.46it/s]
Loading 0:  98%|█████████▊| 355/363 [02:09<00:02, 3.07it/s]
Loading 0:  98%|█████████▊| 355/363 [02:09<00:02, 3.07it/s]
Loading 0:  98%|█████████▊| 357/363 [02:11<00:02, 2.45it/s]
Loading 0:  98%|█████████▊| 357/363 [02:11<00:02, 2.45it/s]
Loading 0: 100%|██████████| 363/363 [02:11<00:00, 3.36it/s]
Loading 0: 100%|██████████| 363/363 [02:11<00:00, 3.36it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [02:11<00:00, 2.76it/s]
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: The tokenizer you are loading from '/tmp/tmpnf4x3wex' 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-4d70-fd43-linear-w01-v26-mkmlizer: quantized model in 143.377s
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: Processed model ChaiML/4d70-fd43-linear-w01 in 163.935s
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: creating bucket guanaco-mkml-models
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia/config.json
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: cp /dev/shm/model_cache/chat_template.jinja s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia/chat_template.jinja
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia/special_tokens_map.json
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia/tokenizer_config.json
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia/tokenizer.json
chaiml-4d70-fd43-linear-w01-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v26/nvidia/flywheel_model.0.safetensors
Job chaiml-4d70-fd43-linear-w01-v26-mkmlizer completed after 225.62s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w01-v26-mkmlizer
Pipeline stage MKMLizer completed in 226.13s
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-4d70-fd43-linear-w01-v26
Waiting for inference service chaiml-4d70-fd43-linear-w01-v26 to be ready
Inference service chaiml-4d70-fd43-linear-w01-v26 ready after 241.3953685760498s
Pipeline stage MKMLDeployer completed in 241.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6764683723449707s
Received healthy response to inference request in 1.5558650493621826s
Received healthy response to inference request in 1.5333752632141113s
Received healthy response to inference request in 1.568223237991333s
Received healthy response to inference request in 1.5534067153930664s
5 requests
0 failed requests
5th percentile: 1.5373815536499023
10th percentile: 1.5413878440856934
20th percentile: 1.5494004249572755
30th percentile: 1.5538983821868897
40th percentile: 1.554881715774536
50th percentile: 1.5558650493621826
60th percentile: 1.5608083248138427
70th percentile: 1.565751600265503
80th percentile: 1.5898722648620605
90th percentile: 1.6331703186035156
95th percentile: 1.6548193454742433
99th percentile: 1.6721385669708253
mean time: 1.5774677276611329
Pipeline stage StressChecker completed in 9.02s
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 0.61s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v26 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 0.09s
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-4d70-fd43-linear-w01-v26-profiler
Waiting for inference service chaiml-4d70-fd43-linear-w01-v26-profiler to be ready
Inference service chaiml-4d70-fd43-linear-w01-v26-profiler ready after 151.2522678375244s
Pipeline stage MKMLProfilerDeployer completed in 151.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-4d70-fd43-linc75f419f0868b1d6a0c5ea11ea48e42e-deplo8fkt2:/code/chaiverse_profiler_1766805300 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-4d70-fd43-linc75f419f0868b1d6a0c5ea11ea48e42e-deplo8fkt2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1766805300 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1800 --output_tokens 74 --summary /code/chaiverse_profiler_1766805300/summary.json'
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 1986.15s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v26 status is now torndown due to DeploymentManager action