chaiml-kimid-v4-eos-lr5e6g32

developer_uid: zonemercy
submission_id: chaiml-kimid-v4-eos-lr5e6g32_v3
model_name: test
model_group: ChaiML/kimid-v4_eos-lr5e
status: torndown
timestamp: 2025-12-12T18:28:10+00:00
num_battles: 6509
num_wins: 3384
celo_rating: 1307.0
family_friendly_score: 0.5062
family_friendly_standard_error: 0.007070524167273598
submission_type: basic
model_repo: ChaiML/kimid-v4_eos-lr5e6g32
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 72
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.44048314455226356, 'latency_mean': 2.2701588571071625, 'latency_p50': 2.2519819736480713, 'latency_p90': 2.4796372413635255}, {'batch_size': 2, 'throughput': 0.6611960630639764, 'latency_mean': 3.015838153362274, 'latency_p50': 3.0207899808883667, 'latency_p90': 3.241884875297546}, {'batch_size': 3, 'throughput': 0.8199037817058726, 'latency_mean': 3.648163310289383, 'latency_p50': 3.635565400123596, 'latency_p90': 4.010374927520752}, {'batch_size': 4, 'throughput': 0.9112029894694316, 'latency_mean': 4.368471685647965, 'latency_p50': 4.356450915336609, 'latency_p90': 4.907070326805115}, {'batch_size': 5, 'throughput': 0.9836346467198674, 'latency_mean': 5.061363278627396, 'latency_p50': 5.076114058494568, 'latency_p90': 5.546133637428284}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v4_eos-lr5e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.83
us_pacific_date: 2025-12-06
win_ratio: 0.5198955292671685
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 72}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{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-kimid-v4-eos-lr5e6g32-v3-mkmlizer
Waiting for job on chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer to finish
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: Downloaded to shared memory in 40.626s
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: Checking if ChaiML/kimid-v4_eos-lr5e6g32 already exists in ChaiML
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpa09xwltv, device:0
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:27, 1.35it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:27, 1.35it/s]
Loading 0:   1%|          | 4.00/363 [00:04<07:00, 1.17s/it]
Loading 0:   1%|          | 4.00/363 [00:04<07:00, 1.17s/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%|▎         | 10.0/363 [00:07<03:42, 1.59it/s]
Loading 0:   3%|▎         | 10.0/363 [00:07<03:42, 1.59it/s]
Loading 0:   3%|▎         | 12.0/363 [00:09<04:22, 1.34it/s]
Loading 0:   3%|▎         | 12.0/363 [00:09<04:22, 1.34it/s]
Loading 0:   4%|▎         | 13.0/363 [00:11<05:38, 1.04it/s]
Loading 0:   4%|▎         | 13.0/363 [00:11<05:38, 1.04it/s]
Loading 0:   4%|▍         | 14.0/363 [00:14<06:56, 1.19s/it]
Loading 0:   4%|▍         | 14.0/363 [00:14<06:56, 1.19s/it]
Loading 0:   6%|▌         | 21.0/363 [00:16<03:50, 1.49it/s]
Loading 0:   6%|▌         | 21.0/363 [00:16<03:50, 1.49it/s]
Loading 0:   6%|▌         | 22.0/363 [00:18<04:46, 1.19it/s]
Loading 0:   6%|▌         | 22.0/363 [00:18<04:46, 1.19it/s]
Loading 0:   6%|▋         | 23.0/363 [00:21<05:52, 1.04s/it]
Loading 0:   6%|▋         | 23.0/363 [00:21<05:52, 1.04s/it]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:50, 1.96it/s]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:50, 1.96it/s]
Loading 0:   9%|▉         | 34.0/363 [00:24<03:00, 1.82it/s]
Loading 0:   9%|▉         | 34.0/363 [00:24<03:00, 1.82it/s]
Loading 0:  10%|▉         | 35.0/363 [00:26<03:49, 1.43it/s]
Loading 0:  10%|▉         | 35.0/363 [00:26<03:49, 1.43it/s]
Loading 0:  10%|▉         | 36.0/363 [00:28<04:49, 1.13it/s]
Loading 0:  10%|▉         | 36.0/363 [00:28<04:49, 1.13it/s]
Loading 0:  11%|█         | 39.0/363 [00:30<04:20, 1.25it/s]
Loading 0:  11%|█         | 39.0/363 [00:30<04:20, 1.25it/s]
Loading 0:  11%|█         | 40.0/363 [00:32<05:13, 1.03it/s]
Loading 0:  11%|█         | 40.0/363 [00:32<05:13, 1.03it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:34<06:15, 1.16s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:34<06:15, 1.16s/it]
Loading 0:  13%|█▎        | 48.0/363 [00:37<03:31, 1.49it/s]
Loading 0:  13%|█▎        | 48.0/363 [00:37<03:31, 1.49it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:39<04:16, 1.22it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:39<04:16, 1.22it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:41<05:11, 1.00it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:41<05:11, 1.00it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:44<03:14, 1.57it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:44<03:14, 1.57it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:46<03:57, 1.29it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:46<03:57, 1.29it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:48<04:48, 1.05it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:48<04:48, 1.05it/s]
Loading 0:  18%|█▊        | 65.0/363 [00:50<03:23, 1.47it/s]
Loading 0:  18%|█▊        | 65.0/363 [00:50<03:23, 1.47it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:53<02:54, 1.67it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:53<02:54, 1.67it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:55<03:30, 1.38it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:55<03:30, 1.38it/s]
Loading 0:  20%|██        | 73.0/363 [00:57<04:16, 1.13it/s]
Loading 0:  20%|██        | 73.0/363 [00:57<04:16, 1.13it/s]
Loading 0:  22%|██▏       | 79.0/363 [01:00<03:09, 1.50it/s]
Loading 0:  22%|██▏       | 79.0/363 [01:00<03:09, 1.50it/s]
Loading 0:  22%|██▏       | 80.0/363 [01:02<03:51, 1.22it/s]
Loading 0:  22%|██▏       | 80.0/363 [01:02<03:51, 1.22it/s]
Loading 0:  24%|██▎       | 86.0/363 [01:05<03:00, 1.53it/s]
Loading 0:  24%|██▎       | 86.0/363 [01:05<03:00, 1.53it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:07<03:40, 1.25it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:07<03:40, 1.25it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:09<03:25, 1.33it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:09<03:25, 1.33it/s]
Loading 0:  25%|██▌       | 91.0/363 [01:11<04:06, 1.10it/s]
Loading 0:  25%|██▌       | 91.0/363 [01:11<04:06, 1.10it/s]
Loading 0:  25%|██▌       | 92.0/363 [01:13<04:54, 1.09s/it]
Loading 0:  25%|██▌       | 92.0/363 [01:13<04:54, 1.09s/it]
Loading 0:  27%|██▋       | 99.0/363 [01:16<02:53, 1.52it/s]
Loading 0:  27%|██▋       | 99.0/363 [01:16<02:53, 1.52it/s]
Loading 0:  28%|██▊       | 100/363 [01:18<03:30, 1.25it/s] 
Loading 0:  28%|██▊       | 100/363 [01:18<03:30, 1.25it/s]
Loading 0:  28%|██▊       | 101/363 [01:20<04:15, 1.03it/s]
Loading 0:  28%|██▊       | 101/363 [01:20<04:15, 1.03it/s]
Loading 0:  30%|██▉       | 108/363 [01:23<02:46, 1.54it/s]
Loading 0:  30%|██▉       | 108/363 [01:23<02:46, 1.54it/s]
Loading 0:  31%|███       | 111/363 [01:25<02:44, 1.54it/s]
Loading 0:  31%|███       | 111/363 [01:25<02:44, 1.54it/s]
Loading 0:  31%|███       | 112/363 [01:27<03:19, 1.26it/s]
Loading 0:  31%|███       | 112/363 [01:27<03:19, 1.26it/s]
Loading 0:  31%|███       | 113/363 [01:29<04:03, 1.03it/s]
Loading 0:  31%|███       | 113/363 [01:29<04:03, 1.03it/s]
Loading 0:  33%|███▎      | 120/363 [01:31<02:33, 1.58it/s]
Loading 0:  33%|███▎      | 120/363 [01:31<02:33, 1.58it/s]
Loading 0:  33%|███▎      | 121/363 [01:33<03:06, 1.29it/s]
Loading 0:  33%|███▎      | 121/363 [01:33<03:06, 1.29it/s]
Loading 0:  34%|███▎      | 122/363 [01:35<03:46, 1.06it/s]
Loading 0:  34%|███▎      | 122/363 [01:35<03:46, 1.06it/s]
Loading 0:  36%|███▌      | 129/363 [01:38<02:25, 1.61it/s]
Loading 0:  36%|███▌      | 129/363 [01:38<02:25, 1.61it/s]
Loading 0:  36%|███▌      | 130/363 [01:40<02:57, 1.32it/s]
Loading 0:  36%|███▌      | 130/363 [01:40<02:57, 1.32it/s]
Loading 0:  36%|███▌      | 131/363 [01:42<03:35, 1.07it/s]
Loading 0:  36%|███▌      | 131/363 [01:42<03:35, 1.07it/s]
Loading 0:  38%|███▊      | 138/363 [01:45<02:19, 1.61it/s]
Loading 0:  38%|███▊      | 138/363 [01:45<02:19, 1.61it/s]
Loading 0:  38%|███▊      | 139/363 [01:47<02:49, 1.32it/s]
Loading 0:  38%|███▊      | 139/363 [01:47<02:49, 1.32it/s]
Loading 0:  39%|███▊      | 140/363 [01:49<03:26, 1.08it/s]
Loading 0:  39%|███▊      | 140/363 [01:49<03:26, 1.08it/s]
Loading 0:  41%|████      | 148/363 [01:50<01:40, 2.15it/s]
Loading 0:  41%|████      | 148/363 [01:50<01:40, 2.15it/s]
Loading 0:  42%|████▏     | 151/363 [01:52<01:55, 1.84it/s]
Loading 0:  42%|████▏     | 151/363 [01:52<01:55, 1.84it/s]
Loading 0:  42%|████▏     | 152/363 [01:54<02:25, 1.45it/s]
Loading 0:  42%|████▏     | 152/363 [01:54<02:25, 1.45it/s]
Loading 0:  42%|████▏     | 153/363 [01:56<03:02, 1.15it/s]
Loading 0:  42%|████▏     | 153/363 [01:56<03:02, 1.15it/s]
Loading 0:  43%|████▎     | 156/363 [01:58<02:44, 1.26it/s]
Loading 0:  43%|████▎     | 156/363 [01:58<02:44, 1.26it/s]
Loading 0:  43%|████▎     | 157/363 [02:00<03:18, 1.04it/s]
Loading 0:  43%|████▎     | 157/363 [02:00<03:18, 1.04it/s]
Loading 0:  44%|████▎     | 158/363 [02:02<03:58, 1.16s/it]
Loading 0:  44%|████▎     | 158/363 [02:02<03:58, 1.16s/it]
Loading 0:  45%|████▌     | 165/363 [02:05<02:17, 1.44it/s]
Loading 0:  45%|████▌     | 165/363 [02:05<02:17, 1.44it/s]
Loading 0:  46%|████▌     | 166/363 [02:07<02:45, 1.19it/s]
Loading 0:  46%|████▌     | 166/363 [02:07<02:45, 1.19it/s]
Loading 0:  46%|████▌     | 167/363 [02:09<03:19, 1.02s/it]
Loading 0:  46%|████▌     | 167/363 [02:09<03:19, 1.02s/it]
Loading 0:  48%|████▊     | 174/363 [02:12<02:05, 1.50it/s]
Loading 0:  48%|████▊     | 174/363 [02:12<02:05, 1.50it/s]
Loading 0:  48%|████▊     | 175/363 [02:14<02:30, 1.25it/s]
Loading 0:  48%|████▊     | 175/363 [02:14<02:30, 1.25it/s]
Loading 0:  48%|████▊     | 176/363 [02:16<03:01, 1.03it/s]
Loading 0:  48%|████▊     | 176/363 [02:16<03:01, 1.03it/s]
Loading 0:  50%|█████     | 182/363 [02:19<02:05, 1.44it/s]
Loading 0:  50%|█████     | 182/363 [02:19<02:05, 1.44it/s]
Loading 0:  52%|█████▏    | 188/363 [02:22<01:44, 1.67it/s]
Loading 0:  52%|█████▏    | 188/363 [02:22<01:44, 1.67it/s]
Loading 0:  52%|█████▏    | 189/363 [02:24<02:08, 1.35it/s]
Loading 0:  52%|█████▏    | 189/363 [02:24<02:08, 1.35it/s]
Loading 0:  53%|█████▎    | 192/363 [02:26<02:02, 1.40it/s]
Loading 0:  53%|█████▎    | 192/363 [02:26<02:02, 1.40it/s]
Loading 0:  53%|█████▎    | 193/363 [02:28<02:26, 1.16it/s]
Loading 0:  53%|█████▎    | 193/363 [02:28<02:26, 1.16it/s]
Loading 0:  53%|█████▎    | 194/363 [02:30<02:56, 1.04s/it]
Loading 0:  53%|█████▎    | 194/363 [02:30<02:56, 1.04s/it]
Loading 0:  55%|█████▌    | 201/363 [02:33<01:45, 1.53it/s]
Loading 0:  55%|█████▌    | 201/363 [02:33<01:45, 1.53it/s]
Loading 0:  56%|█████▌    | 202/363 [02:35<02:07, 1.26it/s]
Loading 0:  56%|█████▌    | 202/363 [02:35<02:07, 1.26it/s]
Loading 0:  56%|█████▌    | 203/363 [02:37<02:34, 1.03it/s]
Loading 0:  56%|█████▌    | 203/363 [02:37<02:34, 1.03it/s]
Loading 0:  58%|█████▊    | 210/363 [02:39<01:36, 1.59it/s]
Loading 0:  58%|█████▊    | 210/363 [02:39<01:36, 1.59it/s]
Loading 0:  58%|█████▊    | 211/363 [02:41<01:56, 1.30it/s]
Loading 0:  58%|█████▊    | 211/363 [02:41<01:56, 1.30it/s]
Loading 0:  58%|█████▊    | 212/363 [02:43<02:21, 1.07it/s]
Loading 0:  58%|█████▊    | 212/363 [02:43<02:21, 1.07it/s]
Loading 0:  60%|██████    | 218/363 [02:46<01:38, 1.48it/s]
Loading 0:  60%|██████    | 218/363 [02:46<01:38, 1.48it/s]
Loading 0:  60%|██████    | 219/363 [02:48<02:00, 1.20it/s]
Loading 0:  60%|██████    | 219/363 [02:48<02:00, 1.20it/s]
Loading 0:  62%|██████▏   | 225/363 [02:51<01:30, 1.52it/s]
Loading 0:  62%|██████▏   | 225/363 [02:51<01:30, 1.52it/s]
Loading 0:  63%|██████▎   | 228/363 [02:53<01:28, 1.52it/s]
Loading 0:  63%|██████▎   | 228/363 [02:53<01:28, 1.52it/s]
Loading 0:  63%|██████▎   | 229/363 [02:55<01:47, 1.25it/s]
Loading 0:  63%|██████▎   | 229/363 [02:55<01:47, 1.25it/s]
Loading 0:  63%|██████▎   | 230/363 [02:57<02:09, 1.03it/s]
Loading 0:  63%|██████▎   | 230/363 [02:57<02:09, 1.03it/s]
Loading 0:  65%|██████▌   | 237/363 [03:00<01:19, 1.58it/s]
Loading 0:  65%|██████▌   | 237/363 [03:00<01:19, 1.58it/s]
Loading 0:  66%|██████▌   | 238/363 [03:02<01:36, 1.29it/s]
Loading 0:  66%|██████▌   | 238/363 [03:02<01:36, 1.29it/s]
Loading 0:  66%|██████▌   | 239/363 [03:04<01:57, 1.06it/s]
Loading 0:  66%|██████▌   | 239/363 [03:04<01:57, 1.06it/s]
Loading 0:  68%|██████▊   | 246/363 [03:06<01:12, 1.61it/s]
Loading 0:  68%|██████▊   | 246/363 [03:06<01:12, 1.61it/s]
Loading 0:  68%|██████▊   | 247/363 [03:08<01:28, 1.31it/s]
Loading 0:  68%|██████▊   | 247/363 [03:08<01:28, 1.31it/s]
Loading 0:  68%|██████▊   | 248/363 [03:10<01:47, 1.07it/s]
Loading 0:  68%|██████▊   | 248/363 [03:10<01:47, 1.07it/s]
Loading 0:  70%|███████   | 255/363 [03:13<01:06, 1.62it/s]
Loading 0:  70%|███████   | 255/363 [03:13<01:06, 1.62it/s]
Loading 0:  71%|███████   | 256/363 [03:15<01:20, 1.32it/s]
Loading 0:  71%|███████   | 256/363 [03:15<01:20, 1.32it/s]
Loading 0:  71%|███████   | 257/363 [03:17<01:38, 1.08it/s]
Loading 0:  71%|███████   | 257/363 [03:17<01:38, 1.08it/s]
Loading 0:  73%|███████▎  | 265/363 [03:18<00:45, 2.15it/s]
Loading 0:  73%|███████▎  | 265/363 [03:18<00:45, 2.15it/s]
Loading 0:  74%|███████▍  | 268/363 [03:21<00:51, 1.85it/s]
Loading 0:  74%|███████▍  | 268/363 [03:21<00:51, 1.85it/s]
Loading 0:  74%|███████▍  | 269/363 [03:23<01:04, 1.45it/s]
Loading 0:  74%|███████▍  | 269/363 [03:23<01:04, 1.45it/s]
Loading 0:  74%|███████▍  | 270/363 [03:25<01:20, 1.15it/s]
Loading 0:  74%|███████▍  | 270/363 [03:25<01:20, 1.15it/s]
Loading 0:  75%|███████▌  | 273/363 [03:41<03:46, 2.51s/it]
Loading 0:  75%|███████▌  | 273/363 [03:41<03:46, 2.51s/it]
Loading 0:  75%|███████▌  | 274/363 [03:43<03:36, 2.44s/it]
Loading 0:  75%|███████▌  | 274/363 [03:43<03:36, 2.44s/it]
Loading 0:  76%|███████▌  | 275/363 [03:45<03:30, 2.39s/it]
Loading 0:  76%|███████▌  | 275/363 [03:45<03:30, 2.39s/it]
Loading 0:  78%|███████▊  | 282/363 [03:48<01:30, 1.12s/it]
Loading 0:  78%|███████▊  | 282/363 [03:48<01:30, 1.12s/it]
Loading 0:  78%|███████▊  | 283/363 [03:50<01:36, 1.20s/it]
Loading 0:  78%|███████▊  | 283/363 [03:50<01:36, 1.20s/it]
Loading 0:  78%|███████▊  | 284/363 [03:52<01:45, 1.33s/it]
Loading 0:  78%|███████▊  | 284/363 [03:52<01:45, 1.33s/it]
Loading 0:  80%|████████  | 291/363 [03:55<00:55, 1.29it/s]
Loading 0:  80%|████████  | 291/363 [03:55<00:55, 1.29it/s]
Loading 0:  80%|████████  | 292/363 [03:57<01:03, 1.11it/s]
Loading 0:  80%|████████  | 292/363 [03:57<01:03, 1.11it/s]
Loading 0:  81%|████████  | 293/363 [03:59<01:13, 1.06s/it]
Loading 0:  81%|████████  | 293/363 [03:59<01:13, 1.06s/it]
Loading 0:  82%|████████▏ | 299/363 [04:01<00:47, 1.34it/s]
Loading 0:  82%|████████▏ | 299/363 [04:01<00:47, 1.34it/s]
Loading 0:  84%|████████▍ | 305/363 [04:04<00:36, 1.58it/s]
Loading 0:  84%|████████▍ | 305/363 [04:04<00:36, 1.58it/s]
Loading 0:  84%|████████▍ | 306/363 [04:06<00:43, 1.30it/s]
Loading 0:  84%|████████▍ | 306/363 [04:06<00:43, 1.30it/s]
Loading 0:  85%|████████▌ | 309/363 [04:08<00:39, 1.35it/s]
Loading 0:  85%|████████▌ | 309/363 [04:08<00:39, 1.35it/s]
Loading 0:  85%|████████▌ | 310/363 [04:10<00:47, 1.12it/s]
Loading 0:  85%|████████▌ | 310/363 [04:10<00:47, 1.12it/s]
Loading 0:  86%|████████▌ | 311/363 [04:13<00:55, 1.06s/it]
Loading 0:  86%|████████▌ | 311/363 [04:13<00:55, 1.06s/it]
Loading 0:  88%|████████▊ | 318/363 [04:15<00:29, 1.53it/s]
Loading 0:  88%|████████▊ | 318/363 [04:15<00:29, 1.53it/s]
Loading 0:  88%|████████▊ | 319/363 [04:17<00:35, 1.26it/s]
Loading 0:  88%|████████▊ | 319/363 [04:17<00:35, 1.26it/s]
Loading 0:  88%|████████▊ | 320/363 [04:19<00:41, 1.03it/s]
Loading 0:  88%|████████▊ | 320/363 [04:19<00:41, 1.03it/s]
Loading 0:  90%|█████████ | 327/363 [04:22<00:22, 1.60it/s]
Loading 0:  90%|█████████ | 327/363 [04:22<00:22, 1.60it/s]
Loading 0:  90%|█████████ | 328/363 [04:24<00:26, 1.31it/s]
Loading 0:  90%|█████████ | 328/363 [04:24<00:26, 1.31it/s]
Loading 0:  91%|█████████ | 329/363 [04:26<00:31, 1.07it/s]
Loading 0:  91%|█████████ | 329/363 [04:26<00:31, 1.07it/s]
Loading 0:  92%|█████████▏| 335/363 [04:28<00:18, 1.49it/s]
Loading 0:  92%|█████████▏| 335/363 [04:28<00:18, 1.49it/s]
Loading 0:  93%|█████████▎| 336/363 [04:31<00:22, 1.20it/s]
Loading 0:  93%|█████████▎| 336/363 [04:31<00:22, 1.20it/s]
Loading 0:  94%|█████████▍| 341/363 [04:32<00:12, 1.80it/s]
Loading 0:  94%|█████████▍| 341/363 [04:32<00:12, 1.80it/s]
Loading 0:  94%|█████████▍| 343/363 [04:34<00:12, 1.56it/s]
Loading 0:  94%|█████████▍| 343/363 [04:34<00:12, 1.56it/s]
Loading 0:  95%|█████████▌| 346/363 [04:36<00:10, 1.55it/s]
Loading 0:  95%|█████████▌| 346/363 [04:36<00:10, 1.55it/s]
Loading 0:  96%|█████████▌| 347/363 [04:38<00:12, 1.23it/s]
Loading 0:  96%|█████████▌| 347/363 [04:38<00:12, 1.23it/s]
Loading 0:  96%|█████████▌| 348/363 [04:40<00:15, 1.00s/it]
Loading 0:  96%|█████████▌| 348/363 [04:40<00:15, 1.00s/it]
Loading 0:  98%|█████████▊| 355/363 [04:42<00:05, 1.59it/s]
Loading 0:  98%|█████████▊| 355/363 [04:42<00:05, 1.59it/s]
Loading 0:  98%|█████████▊| 356/363 [04:44<00:05, 1.29it/s]
Loading 0:  98%|█████████▊| 356/363 [04:44<00:05, 1.29it/s]
Loading 0:  98%|█████████▊| 357/363 [04:46<00:05, 1.05it/s]
Loading 0:  98%|█████████▊| 357/363 [04:46<00:05, 1.05it/s]
Loading 0: 100%|██████████| 363/363 [04:47<00:00, 1.96it/s]
Loading 0: 100%|██████████| 363/363 [04:47<00:00, 1.96it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [04:47<00:00, 1.26it/s]
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: The tokenizer you are loading from '/tmp/tmpa09xwltv' 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-kimid-v4-eos-lr5e6g32-v3-mkmlizer: quantized model in 295.259s
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: Processed model ChaiML/kimid-v4_eos-lr5e6g32 in 335.886s
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia/config.json
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia/special_tokens_map.json
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia/tokenizer_config.json
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia/tokenizer.json
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-eos-lr5e6g32-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer completed after 378.17s with status: succeeded
Stopping job with name chaiml-kimid-v4-eos-lr5e6g32-v3-mkmlizer
Pipeline stage MKMLizer completed in 379.21s
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-kimid-v4-eos-lr5e6g32-v3
Waiting for inference service chaiml-kimid-v4-eos-lr5e6g32-v3 to be ready
Inference service chaiml-kimid-v4-eos-lr5e6g32-v3 ready after 201.42830181121826s
Pipeline stage MKMLDeployer completed in 202.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.36503267288208s
Received healthy response to inference request in 2.5134663581848145s
Received healthy response to inference request in 2.39812970161438s
Received healthy response to inference request in 2.696657180786133s
Received healthy response to inference request in 1.8968286514282227s
5 requests
0 failed requests
5th percentile: 1.9904694557189941
10th percentile: 2.0841102600097656
20th percentile: 2.2713918685913086
30th percentile: 2.37165207862854
40th percentile: 2.38489089012146
50th percentile: 2.39812970161438
60th percentile: 2.444264364242554
70th percentile: 2.4903990268707275
80th percentile: 2.550104522705078
90th percentile: 2.6233808517456056
95th percentile: 2.6600190162658692
99th percentile: 2.68932954788208
mean time: 2.374022912979126
Pipeline stage StressChecker completed in 13.08s
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 0.78s
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-kimid-v4-eos-lr5e6g32_v3 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-kimid-v4-eos-lr5e6g32-v3-profiler
Waiting for inference service chaiml-kimid-v4-eos-lr5e6g32-v3-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 2424.67s
Shutdown handler de-registered
chaiml-kimid-v4-eos-lr5e6g32_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-kimid-v4-eos-lr5e6g32_v3 status is now torndown due to DeploymentManager action