developer_uid: zonemercy
submission_id: chaiml-cai-synth-v4-eos_69759_v2
model_name: test
model_group: ChaiML/cai-synth-v4_eos-
status: torndown
timestamp: 2025-12-12T18:27:16+00:00
num_battles: 6092
num_wins: 3052
celo_rating: 1293.35
family_friendly_score: 0.6082000000000001
family_friendly_standard_error: 0.006903517364358549
submission_type: basic
model_repo: ChaiML/cai-synth-v4_eos-cosine
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': 0.42929141065925236, 'latency_mean': 2.329338628053665, 'latency_p50': 2.3180540800094604, 'latency_p90': 2.5327377796173094}, {'batch_size': 2, 'throughput': 0.6427735621339196, 'latency_mean': 3.1091125166416167, 'latency_p50': 3.115000009536743, 'latency_p90': 3.3418284177780153}, {'batch_size': 3, 'throughput': 0.7864704419378858, 'latency_mean': 3.8064650964736937, 'latency_p50': 3.800731062889099, 'latency_p90': 4.06506872177124}, {'batch_size': 4, 'throughput': 0.8914016564865714, 'latency_mean': 4.471464519500732, 'latency_p50': 4.468768954277039, 'latency_p90': 5.07213327884674}, {'batch_size': 5, 'throughput': 0.9493527587823535, 'latency_mean': 5.24668243765831, 'latency_p50': 5.261900544166565, 'latency_p90': 6.018527698516846}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/cai-synth-v4_eos-cosine
model_size: 24B
ranking_group: single
throughput_3p7s: 0.77
us_pacific_date: 2025-12-05
win_ratio: 0.5009848982271832
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': ['You:', '</s>', 'User:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 72}
formatter: {'memory_template': '', '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-cai-synth-v4-eos-69759-v2-mkmlizer
Waiting for job on chaiml-cai-synth-v4-eos-69759-v2-mkmlizer to finish
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: bash: no job control in this shell
chaiml-cai-synth-v4-eos-69759-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-cai-synth-v4-eos-69759-v2-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: Downloaded to shared memory in 93.269s
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: Checking if ChaiML/cai-synth-v4_eos-cosine already exists in ChaiML
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp39yh8yqx, device:0
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:57, 1.52it/s]
Loading 0:   1%|          | 3.00/363 [00:01<03:57, 1.52it/s]
Loading 0:   1%|          | 4.00/363 [00:03<06:23, 1.07s/it]
Loading 0:   1%|          | 4.00/363 [00:03<06:23, 1.07s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<08:20, 1.40s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<08:20, 1.40s/it]
Loading 0:   3%|▎         | 12.0/363 [00:08<03:48, 1.54it/s]
Loading 0:   3%|▎         | 12.0/363 [00:08<03:48, 1.54it/s]
Loading 0:   4%|▎         | 13.0/363 [00:10<04:47, 1.22it/s]
Loading 0:   4%|▎         | 13.0/363 [00:10<04:47, 1.22it/s]
Loading 0:   4%|▍         | 14.0/363 [00:12<05:55, 1.02s/it]
Loading 0:   4%|▍         | 14.0/363 [00:12<05:55, 1.02s/it]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:33, 1.60it/s]
Loading 0:   6%|▌         | 21.0/363 [00:15<03:33, 1.60it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:22, 1.30it/s]
Loading 0:   6%|▌         | 22.0/363 [00:17<04:22, 1.30it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:20, 1.06it/s]
Loading 0:   6%|▋         | 23.0/363 [00:19<05:20, 1.06it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:32, 2.18it/s]
Loading 0:   9%|▊         | 31.0/363 [00:20<02:32, 2.18it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:55, 1.88it/s]
Loading 0:   9%|▉         | 34.0/363 [00:22<02:55, 1.88it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:42, 1.47it/s]
Loading 0:  10%|▉         | 35.0/363 [00:24<03:42, 1.47it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:39, 1.17it/s]
Loading 0:  10%|▉         | 36.0/363 [00:26<04:39, 1.17it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:12, 1.28it/s]
Loading 0:  11%|█         | 39.0/363 [00:28<04:12, 1.28it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:05, 1.06it/s]
Loading 0:  11%|█         | 40.0/363 [00:30<05:05, 1.06it/s]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:05, 1.14s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:32<06:05, 1.14s/it]
Loading 0:  13%|█▎        | 48.0/363 [00:35<03:25, 1.54it/s]
Loading 0:  13%|█▎        | 48.0/363 [00:35<03:25, 1.54it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:37<04:10, 1.26it/s]
Loading 0:  13%|█▎        | 49.0/363 [00:37<04:10, 1.26it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:39<05:03, 1.03it/s]
Loading 0:  14%|█▍        | 50.0/363 [00:39<05:03, 1.03it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:42<03:10, 1.60it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:42<03:10, 1.60it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<03:52, 1.31it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:43<03:52, 1.31it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:45<04:42, 1.08it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:45<04:42, 1.08it/s]
Loading 0:  18%|█▊        | 65.0/363 [00:48<03:18, 1.50it/s]
Loading 0:  18%|█▊        | 65.0/363 [00:48<03:18, 1.50it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:51<02:48, 1.73it/s]
Loading 0:  20%|█▉        | 71.0/363 [00:51<02:48, 1.73it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:53<03:24, 1.42it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:53<03:24, 1.42it/s]
Loading 0:  20%|██        | 73.0/363 [00:55<04:08, 1.17it/s]
Loading 0:  20%|██        | 73.0/363 [00:55<04:08, 1.17it/s]
Loading 0:  22%|██▏       | 79.0/363 [00:57<03:03, 1.55it/s]
Loading 0:  22%|██▏       | 79.0/363 [00:57<03:03, 1.55it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:59<03:44, 1.26it/s]
Loading 0:  22%|██▏       | 80.0/363 [00:59<03:44, 1.26it/s]
Loading 0:  24%|██▎       | 86.0/363 [01:02<02:52, 1.60it/s]
Loading 0:  24%|██▎       | 86.0/363 [01:02<02:52, 1.60it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:04<03:31, 1.30it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:04<03:31, 1.30it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:06<03:18, 1.37it/s]
Loading 0:  25%|██▍       | 90.0/363 [01:06<03:18, 1.37it/s]
Loading 0:  25%|██▌       | 91.0/363 [01:08<03:58, 1.14it/s]
Loading 0:  25%|██▌       | 91.0/363 [01:08<03:58, 1.14it/s]
Loading 0:  25%|██▌       | 92.0/363 [01:10<04:45, 1.05s/it]
Loading 0:  25%|██▌       | 92.0/363 [01:10<04:45, 1.05s/it]
Loading 0:  27%|██▋       | 99.0/363 [01:13<02:49, 1.56it/s]
Loading 0:  27%|██▋       | 99.0/363 [01:13<02:49, 1.56it/s]
Loading 0:  28%|██▊       | 100/363 [01:14<03:25, 1.28it/s] 
Loading 0:  28%|██▊       | 100/363 [01:14<03:25, 1.28it/s]
Loading 0:  28%|██▊       | 101/363 [01:16<04:08, 1.05it/s]
Loading 0:  28%|██▊       | 101/363 [01:16<04:08, 1.05it/s]
Loading 0:  30%|██▉       | 108/363 [01:19<02:40, 1.59it/s]
Loading 0:  30%|██▉       | 108/363 [01:19<02:40, 1.59it/s]
Loading 0:  31%|███       | 111/363 [01:21<02:39, 1.58it/s]
Loading 0:  31%|███       | 111/363 [01:21<02:39, 1.58it/s]
Loading 0:  31%|███       | 112/363 [01:23<03:14, 1.29it/s]
Loading 0:  31%|███       | 112/363 [01:23<03:14, 1.29it/s]
Loading 0:  31%|███       | 113/363 [01:25<03:56, 1.06it/s]
Loading 0:  31%|███       | 113/363 [01:25<03:56, 1.06it/s]
Loading 0:  33%|███▎      | 120/363 [01:28<02:29, 1.63it/s]
Loading 0:  33%|███▎      | 120/363 [01:28<02:29, 1.63it/s]
Loading 0:  33%|███▎      | 121/363 [01:30<03:01, 1.33it/s]
Loading 0:  33%|███▎      | 121/363 [01:30<03:01, 1.33it/s]
Loading 0:  34%|███▎      | 122/363 [01:32<03:41, 1.09it/s]
Loading 0:  34%|███▎      | 122/363 [01:32<03:41, 1.09it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<02:22, 1.64it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<02:22, 1.64it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<02:53, 1.35it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<02:53, 1.35it/s]
Loading 0:  36%|███▌      | 131/363 [01:38<03:30, 1.10it/s]
Loading 0:  36%|███▌      | 131/363 [01:38<03:30, 1.10it/s]
Loading 0:  38%|███▊      | 138/363 [01:41<02:16, 1.65it/s]
Loading 0:  38%|███▊      | 138/363 [01:41<02:16, 1.65it/s]
Loading 0:  38%|███▊      | 139/363 [01:43<02:45, 1.35it/s]
Loading 0:  38%|███▊      | 139/363 [01:43<02:45, 1.35it/s]
Loading 0:  39%|███▊      | 140/363 [01:45<03:22, 1.10it/s]
Loading 0:  39%|███▊      | 140/363 [01:45<03:22, 1.10it/s]
Loading 0:  41%|████      | 148/363 [01:46<01:38, 2.19it/s]
Loading 0:  41%|████      | 148/363 [01:46<01:38, 2.19it/s]
Loading 0:  42%|████▏     | 151/363 [01:48<01:51, 1.90it/s]
Loading 0:  42%|████▏     | 151/363 [01:48<01:51, 1.90it/s]
Loading 0:  42%|████▏     | 152/363 [01:50<02:21, 1.50it/s]
Loading 0:  42%|████▏     | 152/363 [01:50<02:21, 1.50it/s]
Loading 0:  42%|████▏     | 153/363 [01:52<02:56, 1.19it/s]
Loading 0:  42%|████▏     | 153/363 [01:52<02:56, 1.19it/s]
Loading 0:  43%|████▎     | 156/363 [01:54<02:38, 1.30it/s]
Loading 0:  43%|████▎     | 156/363 [01:54<02:38, 1.30it/s]
Loading 0:  43%|████▎     | 157/363 [01:56<03:12, 1.07it/s]
Loading 0:  43%|████▎     | 157/363 [01:56<03:12, 1.07it/s]
Loading 0:  44%|████▎     | 158/363 [01:58<03:49, 1.12s/it]
Loading 0:  44%|████▎     | 158/363 [01:58<03:49, 1.12s/it]
Loading 0:  45%|████▌     | 165/363 [02:00<02:07, 1.55it/s]
Loading 0:  45%|████▌     | 165/363 [02:00<02:07, 1.55it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<02:35, 1.27it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<02:35, 1.27it/s]
Loading 0:  46%|████▌     | 167/363 [02:04<03:08, 1.04it/s]
Loading 0:  46%|████▌     | 167/363 [02:04<03:08, 1.04it/s]
Loading 0:  48%|████▊     | 174/363 [02:07<01:56, 1.62it/s]
Loading 0:  48%|████▊     | 174/363 [02:07<01:56, 1.62it/s]
Loading 0:  48%|████▊     | 175/363 [02:09<02:21, 1.33it/s]
Loading 0:  48%|████▊     | 175/363 [02:09<02:21, 1.33it/s]
Loading 0:  48%|████▊     | 176/363 [02:11<02:51, 1.09it/s]
Loading 0:  48%|████▊     | 176/363 [02:11<02:51, 1.09it/s]
Loading 0:  50%|█████     | 182/363 [02:13<01:59, 1.52it/s]
Loading 0:  50%|█████     | 182/363 [02:13<01:59, 1.52it/s]
Loading 0:  52%|█████▏    | 188/363 [02:16<01:39, 1.75it/s]
Loading 0:  52%|█████▏    | 188/363 [02:16<01:39, 1.75it/s]
Loading 0:  52%|█████▏    | 189/363 [02:18<02:02, 1.42it/s]
Loading 0:  52%|█████▏    | 189/363 [02:18<02:02, 1.42it/s]
Loading 0:  53%|█████▎    | 192/363 [02:20<01:56, 1.46it/s]
Loading 0:  53%|█████▎    | 192/363 [02:20<01:56, 1.46it/s]
Loading 0:  53%|█████▎    | 193/363 [02:22<02:20, 1.21it/s]
Loading 0:  53%|█████▎    | 193/363 [02:22<02:20, 1.21it/s]
Loading 0:  53%|█████▎    | 194/363 [02:24<02:48, 1.00it/s]
Loading 0:  53%|█████▎    | 194/363 [02:24<02:48, 1.00it/s]
Loading 0:  55%|█████▌    | 201/363 [02:27<01:41, 1.60it/s]
Loading 0:  55%|█████▌    | 201/363 [02:27<01:41, 1.60it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:02, 1.31it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:02, 1.31it/s]
Loading 0:  56%|█████▌    | 203/363 [02:30<02:28, 1.08it/s]
Loading 0:  56%|█████▌    | 203/363 [02:30<02:28, 1.08it/s]
Loading 0:  58%|█████▊    | 210/363 [02:33<01:33, 1.64it/s]
Loading 0:  58%|█████▊    | 210/363 [02:33<01:33, 1.64it/s]
Loading 0:  58%|█████▊    | 211/363 [02:35<01:52, 1.35it/s]
Loading 0:  58%|█████▊    | 211/363 [02:35<01:52, 1.35it/s]
Loading 0:  58%|█████▊    | 212/363 [02:37<02:16, 1.10it/s]
Loading 0:  58%|█████▊    | 212/363 [02:37<02:16, 1.10it/s]
Loading 0:  60%|██████    | 218/363 [02:39<01:34, 1.53it/s]
Loading 0:  60%|██████    | 218/363 [02:39<01:34, 1.53it/s]
Loading 0:  60%|██████    | 219/363 [02:41<01:55, 1.24it/s]
Loading 0:  60%|██████    | 219/363 [02:41<01:55, 1.24it/s]
Loading 0:  62%|██████▏   | 225/363 [02:44<01:27, 1.58it/s]
Loading 0:  62%|██████▏   | 225/363 [02:44<01:27, 1.58it/s]
Loading 0:  63%|██████▎   | 228/363 [02:46<01:25, 1.58it/s]
Loading 0:  63%|██████▎   | 228/363 [02:46<01:25, 1.58it/s]
Loading 0:  63%|██████▎   | 229/363 [02:48<01:43, 1.30it/s]
Loading 0:  63%|██████▎   | 229/363 [02:48<01:43, 1.30it/s]
Loading 0:  63%|██████▎   | 230/363 [02:50<02:04, 1.07it/s]
Loading 0:  63%|██████▎   | 230/363 [02:50<02:04, 1.07it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:16, 1.64it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:16, 1.64it/s]
Loading 0:  66%|██████▌   | 238/363 [02:54<01:33, 1.34it/s]
Loading 0:  66%|██████▌   | 238/363 [02:54<01:33, 1.34it/s]
Loading 0:  66%|██████▌   | 239/363 [02:56<01:52, 1.10it/s]
Loading 0:  66%|██████▌   | 239/363 [02:56<01:52, 1.10it/s]
Loading 0:  68%|██████▊   | 246/363 [02:59<01:10, 1.67it/s]
Loading 0:  68%|██████▊   | 246/363 [02:59<01:10, 1.67it/s]
Loading 0:  68%|██████▊   | 247/363 [03:01<01:25, 1.36it/s]
Loading 0:  68%|██████▊   | 247/363 [03:01<01:25, 1.36it/s]
Loading 0:  68%|██████▊   | 248/363 [03:03<01:42, 1.12it/s]
Loading 0:  68%|██████▊   | 248/363 [03:03<01:42, 1.12it/s]
Loading 0:  70%|███████   | 255/363 [03:05<01:04, 1.67it/s]
Loading 0:  70%|███████   | 255/363 [03:05<01:04, 1.67it/s]
Loading 0:  71%|███████   | 256/363 [03:07<01:18, 1.37it/s]
Loading 0:  71%|███████   | 256/363 [03:07<01:18, 1.37it/s]
Loading 0:  71%|███████   | 257/363 [03:09<01:34, 1.12it/s]
Loading 0:  71%|███████   | 257/363 [03:09<01:34, 1.12it/s]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:44, 2.21it/s]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:44, 2.21it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<00:49, 1.92it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<00:49, 1.92it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:02, 1.51it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:02, 1.51it/s]
Loading 0:  74%|███████▍  | 270/363 [03:17<01:17, 1.20it/s]
Loading 0:  74%|███████▍  | 270/363 [03:17<01:17, 1.20it/s]
Loading 0:  75%|███████▌  | 273/363 [03:32<03:29, 2.32s/it]
Loading 0:  75%|███████▌  | 273/363 [03:32<03:29, 2.32s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<03:21, 2.26s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<03:21, 2.26s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<03:15, 2.23s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<03:15, 2.23s/it]
Loading 0:  78%|███████▊  | 282/363 [03:38<01:24, 1.04s/it]
Loading 0:  78%|███████▊  | 282/363 [03:38<01:24, 1.04s/it]
Loading 0:  78%|███████▊  | 283/363 [03:40<01:29, 1.12s/it]
Loading 0:  78%|███████▊  | 283/363 [03:40<01:29, 1.12s/it]
Loading 0:  78%|███████▊  | 284/363 [03:42<01:38, 1.25s/it]
Loading 0:  78%|███████▊  | 284/363 [03:42<01:38, 1.25s/it]
Loading 0:  80%|████████  | 291/363 [03:44<00:52, 1.37it/s]
Loading 0:  80%|████████  | 291/363 [03:44<00:52, 1.37it/s]
Loading 0:  80%|████████  | 292/363 [03:46<01:00, 1.17it/s]
Loading 0:  80%|████████  | 292/363 [03:46<01:00, 1.17it/s]
Loading 0:  81%|████████  | 293/363 [03:48<01:10, 1.00s/it]
Loading 0:  81%|████████  | 293/363 [03:48<01:10, 1.00s/it]
Loading 0:  82%|████████▏ | 299/363 [03:51<00:44, 1.44it/s]
Loading 0:  82%|████████▏ | 299/363 [03:51<00:44, 1.44it/s]
Loading 0:  84%|████████▍ | 305/363 [03:53<00:33, 1.73it/s]
Loading 0:  84%|████████▍ | 305/363 [03:53<00:33, 1.73it/s]
Loading 0:  84%|████████▍ | 306/363 [03:55<00:39, 1.43it/s]
Loading 0:  84%|████████▍ | 306/363 [03:55<00:39, 1.43it/s]
Loading 0:  85%|████████▌ | 309/363 [03:57<00:36, 1.47it/s]
Loading 0:  85%|████████▌ | 309/363 [03:57<00:36, 1.47it/s]
Loading 0:  85%|████████▌ | 310/363 [03:59<00:43, 1.21it/s]
Loading 0:  85%|████████▌ | 310/363 [03:59<00:43, 1.21it/s]
Loading 0:  86%|████████▌ | 311/363 [04:01<00:51, 1.00it/s]
Loading 0:  86%|████████▌ | 311/363 [04:01<00:51, 1.00it/s]
Loading 0:  88%|████████▊ | 318/363 [04:04<00:27, 1.62it/s]
Loading 0:  88%|████████▊ | 318/363 [04:04<00:27, 1.62it/s]
Loading 0:  88%|████████▊ | 319/363 [04:05<00:33, 1.32it/s]
Loading 0:  88%|████████▊ | 319/363 [04:05<00:33, 1.32it/s]
Loading 0:  88%|████████▊ | 320/363 [04:07<00:39, 1.08it/s]
Loading 0:  88%|████████▊ | 320/363 [04:07<00:39, 1.08it/s]
Loading 0:  90%|█████████ | 327/363 [04:10<00:21, 1.67it/s]
Loading 0:  90%|█████████ | 327/363 [04:10<00:21, 1.67it/s]
Loading 0:  90%|█████████ | 328/363 [04:12<00:25, 1.36it/s]
Loading 0:  90%|█████████ | 328/363 [04:12<00:25, 1.36it/s]
Loading 0:  91%|█████████ | 329/363 [04:14<00:30, 1.11it/s]
Loading 0:  91%|█████████ | 329/363 [04:14<00:30, 1.11it/s]
Loading 0:  92%|█████████▏| 335/363 [04:16<00:18, 1.55it/s]
Loading 0:  92%|█████████▏| 335/363 [04:16<00:18, 1.55it/s]
Loading 0:  93%|█████████▎| 336/363 [04:18<00:21, 1.26it/s]
Loading 0:  93%|█████████▎| 336/363 [04:18<00:21, 1.26it/s]
Loading 0:  94%|█████████▍| 343/363 [04:21<00:11, 1.69it/s]
Loading 0:  94%|█████████▍| 343/363 [04:21<00:11, 1.69it/s]
Loading 0:  95%|█████████▌| 346/363 [04:23<00:10, 1.66it/s]
Loading 0:  95%|█████████▌| 346/363 [04:23<00:10, 1.66it/s]
Loading 0:  96%|█████████▌| 347/363 [04:25<00:11, 1.36it/s]
Loading 0:  96%|█████████▌| 347/363 [04:25<00:11, 1.36it/s]
Loading 0:  96%|█████████▌| 348/363 [04:27<00:13, 1.11it/s]
Loading 0:  96%|█████████▌| 348/363 [04:27<00:13, 1.11it/s]
Loading 0:  98%|█████████▊| 355/363 [04:30<00:04, 1.67it/s]
Loading 0:  98%|█████████▊| 355/363 [04:30<00:04, 1.67it/s]
Loading 0:  98%|█████████▊| 356/363 [04:31<00:05, 1.37it/s]
Loading 0:  98%|█████████▊| 356/363 [04:31<00:05, 1.37it/s]
Loading 0:  98%|█████████▊| 357/363 [04:33<00:05, 1.12it/s]
Loading 0:  98%|█████████▊| 357/363 [04:33<00:05, 1.12it/s]
Loading 0: 100%|██████████| 363/363 [04:34<00:00, 2.05it/s]
Loading 0: 100%|██████████| 363/363 [04:34<00:00, 2.05it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [04:34<00:00, 1.32it/s]
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: The tokenizer you are loading from '/tmp/tmp39yh8yqx' 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-cai-synth-v4-eos-69759-v2-mkmlizer: quantized model in 280.807s
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: Processed model ChaiML/cai-synth-v4_eos-cosine in 374.076s
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia/config.json
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia/special_tokens_map.json
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia/tokenizer_config.json
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia/tokenizer.json
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia/flywheel_model.1.safetensors
chaiml-cai-synth-v4-eos-69759-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-eos-69759-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-synth-v4-eos-69759-v2-mkmlizer completed after 449.07s with status: succeeded
Stopping job with name chaiml-cai-synth-v4-eos-69759-v2-mkmlizer
Pipeline stage MKMLizer completed in 449.55s
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-cai-synth-v4-eos-69759-v2
Waiting for inference service chaiml-cai-synth-v4-eos-69759-v2 to be ready
Inference service chaiml-cai-synth-v4-eos-69759-v2 ready after 191.0056939125061s
Pipeline stage MKMLDeployer completed in 191.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.529371500015259s
Received healthy response to inference request in 2.492555856704712s
Received healthy response to inference request in 2.4133331775665283s
Received healthy response to inference request in 2.4212405681610107s
Received healthy response to inference request in 2.4192357063293457s
5 requests
0 failed requests
5th percentile: 2.414513683319092
10th percentile: 2.4156941890716555
20th percentile: 2.418055200576782
30th percentile: 2.419636678695679
40th percentile: 2.420438623428345
50th percentile: 2.4212405681610107
60th percentile: 2.449766683578491
70th percentile: 2.4782927989959718
80th percentile: 2.499918985366821
90th percentile: 2.51464524269104
95th percentile: 2.5220083713531496
99th percentile: 2.5278988742828368
mean time: 2.455147361755371
Pipeline stage StressChecker completed in 13.49s
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 0.84s
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 0.62s
Shutdown handler de-registered
chaiml-cai-synth-v4-eos_69759_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 0.11s
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-cai-synth-v4-eos-69759-v2-profiler
Waiting for inference service chaiml-cai-synth-v4-eos-69759-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 2478.70s
Shutdown handler de-registered
chaiml-cai-synth-v4-eos_69759_v2 status is now torndown due to DeploymentManager action