developer_uid: zonemercy
submission_id: chaiml-kimid-v2-cosine-_21546_v4
model_name: test
model_group: ChaiML/kimid-v2_cosine-l
status: inactive
timestamp: 2025-12-04T23:17:06+00:00
num_battles: 5431
num_wins: 2776
celo_rating: 1303.15
family_friendly_score: 0.5074000000000001
family_friendly_standard_error: 0.007070293346106653
submission_type: basic
model_repo: ChaiML/kimid-v2_cosine-lr2e6g32
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': 0.4235875070675929, 'latency_mean': 2.3607192075252534, 'latency_p50': 2.3682188987731934, 'latency_p90': 2.5655566453933716}, {'batch_size': 2, 'throughput': 0.6337459842810053, 'latency_mean': 3.148845307826996, 'latency_p50': 3.173172116279602, 'latency_p90': 3.3839675188064575}, {'batch_size': 3, 'throughput': 0.7707701905928381, 'latency_mean': 3.8728738713264463, 'latency_p50': 3.8600239753723145, 'latency_p90': 4.356191992759705}, {'batch_size': 4, 'throughput': 0.8699147586910705, 'latency_mean': 4.572830835580826, 'latency_p50': 4.576477289199829, 'latency_p90': 5.227373027801514}, {'batch_size': 5, 'throughput': 0.9276701362697649, 'latency_mean': 5.372180552482605, 'latency_p50': 5.376553058624268, 'latency_p90': 6.042883419990539}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v2_cosine-lr2e6g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.75
us_pacific_date: 2025-12-04
win_ratio: 0.5111397532682748
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': ['</s>', 'User:', 'You:'], '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-v2-cosine-21546-v4-mkmlizer
Waiting for job on chaiml-kimid-v2-cosine-21546-v4-mkmlizer to finish
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: bash: no job control in this shell
chaiml-kimid-v2-cosine-21546-v4-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-v2-cosine-21546-v4-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ belonging to: ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ║ ║
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: Downloaded to shared memory in 47.210s
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: Checking if ChaiML/kimid-v2_cosine-lr2e6g32 already exists in ChaiML
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpvfx5g9ci, device:0
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s] Loading 0: 1%| | 3.00/363 [00:02<04:23, 1.37it/s] Loading 0: 1%| | 3.00/363 [00:02<04:23, 1.37it/s] Loading 0: 1%| | 4.00/363 [00:04<07:09, 1.20s/it] Loading 0: 1%| | 4.00/363 [00:04<07:09, 1.20s/it] Loading 0: 1%|▏ | 5.00/363 [00:06<09:21, 1.57s/it] Loading 0: 1%|▏ | 5.00/363 [00:06<09:21, 1.57s/it] Loading 0: 3%|▎ | 12.0/363 [00:09<04:10, 1.40it/s] Loading 0: 3%|▎ | 12.0/363 [00:09<04:10, 1.40it/s] Loading 0: 4%|▎ | 13.0/363 [00:12<05:22, 1.08it/s] Loading 0: 4%|▎ | 13.0/363 [00:12<05:22, 1.08it/s] Loading 0: 4%|▍ | 14.0/363 [00:14<06:42, 1.15s/it] Loading 0: 4%|▍ | 14.0/363 [00:14<06:42, 1.15s/it] Loading 0: 6%|▌ | 21.0/363 [00:17<04:03, 1.41it/s] Loading 0: 6%|▌ | 21.0/363 [00:17<04:03, 1.41it/s] Loading 0: 6%|▌ | 22.0/363 [00:19<05:00, 1.13it/s] Loading 0: 6%|▌ | 22.0/363 [00:19<05:00, 1.13it/s] Loading 0: 6%|▋ | 23.0/363 [00:22<06:09, 1.09s/it] Loading 0: 6%|▋ | 23.0/363 [00:22<06:09, 1.09s/it] Loading 0: 8%|▊ | 30.0/363 [00:23<03:02, 1.82it/s] Loading 0: 8%|▊ | 30.0/363 [00:23<03:02, 1.82it/s] Loading 0: 9%|▉ | 34.0/363 [00:26<03:18, 1.65it/s] Loading 0: 9%|▉ | 34.0/363 [00:26<03:18, 1.65it/s] Loading 0: 10%|▉ | 35.0/363 [00:28<04:13, 1.30it/s] Loading 0: 10%|▉ | 35.0/363 [00:28<04:13, 1.30it/s] Loading 0: 10%|▉ | 36.0/363 [00:30<05:20, 1.02it/s] Loading 0: 10%|▉ | 36.0/363 [00:30<05:20, 1.02it/s] Loading 0: 11%|█ | 39.0/363 [00:33<04:51, 1.11it/s] Loading 0: 11%|█ | 39.0/363 [00:33<04:51, 1.11it/s] Loading 0: 11%|█ | 40.0/363 [00:35<05:52, 1.09s/it] Loading 0: 11%|█ | 40.0/363 [00:35<05:52, 1.09s/it] Loading 0: 11%|█▏ | 41.0/363 [00:37<07:00, 1.31s/it] Loading 0: 11%|█▏ | 41.0/363 [00:37<07:00, 1.31s/it] Loading 0: 13%|█▎ | 48.0/363 [00:40<03:57, 1.33it/s] Loading 0: 13%|█▎ | 48.0/363 [00:40<03:57, 1.33it/s] Loading 0: 13%|█▎ | 49.0/363 [00:42<04:49, 1.08it/s] Loading 0: 13%|█▎ | 49.0/363 [00:42<04:49, 1.08it/s] Loading 0: 14%|█▍ | 50.0/363 [00:45<05:51, 1.12s/it] Loading 0: 14%|█▍ | 50.0/363 [00:45<05:51, 1.12s/it] Loading 0: 16%|█▌ | 57.0/363 [00:48<03:40, 1.39it/s] Loading 0: 16%|█▌ | 57.0/363 [00:48<03:40, 1.39it/s] Loading 0: 16%|█▌ | 58.0/363 [00:50<04:29, 1.13it/s] Loading 0: 16%|█▌ | 58.0/363 [00:50<04:29, 1.13it/s] Loading 0: 16%|█▋ | 59.0/363 [00:52<05:27, 1.08s/it] Loading 0: 16%|█▋ | 59.0/363 [00:52<05:27, 1.08s/it] Loading 0: 18%|█▊ | 65.0/363 [00:55<03:50, 1.29it/s] Loading 0: 18%|█▊ | 65.0/363 [00:55<03:50, 1.29it/s] Loading 0: 20%|█▉ | 71.0/363 [00:59<03:15, 1.49it/s] Loading 0: 20%|█▉ | 71.0/363 [00:59<03:15, 1.49it/s] Loading 0: 20%|█▉ | 72.0/363 [01:01<03:57, 1.23it/s] Loading 0: 20%|█▉ | 72.0/363 [01:01<03:57, 1.23it/s] Loading 0: 20%|██ | 73.0/363 [01:03<04:48, 1.01it/s] Loading 0: 20%|██ | 73.0/363 [01:03<04:48, 1.01it/s] Loading 0: 22%|██▏ | 79.0/363 [01:06<03:31, 1.34it/s] Loading 0: 22%|██▏ | 79.0/363 [01:06<03:31, 1.34it/s] Loading 0: 22%|██▏ | 80.0/363 [01:08<04:18, 1.09it/s] Loading 0: 22%|██▏ | 80.0/363 [01:08<04:18, 1.09it/s] Loading 0: 24%|██▎ | 86.0/363 [01:11<03:18, 1.39it/s] Loading 0: 24%|██▎ | 86.0/363 [01:11<03:18, 1.39it/s] Loading 0: 24%|██▍ | 87.0/363 [01:14<04:03, 1.13it/s] Loading 0: 24%|██▍ | 87.0/363 [01:14<04:03, 1.13it/s] Loading 0: 25%|██▍ | 90.0/363 [01:16<03:49, 1.19it/s] Loading 0: 25%|██▍ | 90.0/363 [01:16<03:49, 1.19it/s] Loading 0: 25%|██▌ | 91.0/363 [01:18<04:36, 1.02s/it] Loading 0: 25%|██▌ | 91.0/363 [01:18<04:36, 1.02s/it] Loading 0: 25%|██▌ | 92.0/363 [01:21<05:30, 1.22s/it] Loading 0: 25%|██▌ | 92.0/363 [01:21<05:30, 1.22s/it] Loading 0: 27%|██▋ | 99.0/363 [01:24<03:16, 1.35it/s] Loading 0: 27%|██▋ | 99.0/363 [01:24<03:16, 1.35it/s] Loading 0: 28%|██▊ | 100/363 [01:26<03:57, 1.11it/s] Loading 0: 28%|██▊ | 100/363 [01:26<03:57, 1.11it/s] Loading 0: 28%|██▊ | 101/363 [01:28<04:48, 1.10s/it] Loading 0: 28%|██▊ | 101/363 [01:28<04:48, 1.10s/it] Loading 0: 30%|██▉ | 108/363 [01:31<03:04, 1.38it/s] Loading 0: 30%|██▉ | 108/363 [01:31<03:04, 1.38it/s] Loading 0: 31%|███ | 111/363 [01:34<03:03, 1.37it/s] Loading 0: 31%|███ | 111/363 [01:34<03:03, 1.37it/s] Loading 0: 31%|███ | 112/363 [01:36<03:44, 1.12it/s] Loading 0: 31%|███ | 112/363 [01:36<03:44, 1.12it/s] Loading 0: 31%|███ | 113/363 [01:38<04:33, 1.09s/it] Loading 0: 31%|███ | 113/363 [01:38<04:33, 1.09s/it] Loading 0: 33%|███▎ | 120/363 [01:41<02:52, 1.41it/s] Loading 0: 33%|███▎ | 120/363 [01:41<02:52, 1.41it/s] Loading 0: 33%|███▎ | 121/363 [01:43<03:30, 1.15it/s] Loading 0: 33%|███▎ | 121/363 [01:43<03:30, 1.15it/s] Loading 0: 34%|███▎ | 122/363 [01:46<04:16, 1.06s/it] Loading 0: 34%|███▎ | 122/363 [01:46<04:16, 1.06s/it] Loading 0: 36%|███▌ | 129/363 [01:49<02:44, 1.42it/s] Loading 0: 36%|███▌ | 129/363 [01:49<02:44, 1.42it/s] Loading 0: 36%|███▌ | 130/363 [01:51<03:20, 1.16it/s] Loading 0: 36%|███▌ | 130/363 [01:51<03:20, 1.16it/s] Loading 0: 36%|███▌ | 131/363 [01:53<04:03, 1.05s/it] Loading 0: 36%|███▌ | 131/363 [01:53<04:03, 1.05s/it] Loading 0: 38%|███▊ | 138/363 [01:56<02:37, 1.43it/s] Loading 0: 38%|███▊ | 138/363 [01:56<02:37, 1.43it/s] Loading 0: 38%|███▊ | 139/363 [01:58<03:11, 1.17it/s] Loading 0: 38%|███▊ | 139/363 [01:58<03:11, 1.17it/s] Loading 0: 39%|███▊ | 140/363 [02:01<03:53, 1.05s/it] Loading 0: 39%|███▊ | 140/363 [02:01<03:53, 1.05s/it] Loading 0: 40%|████ | 147/363 [02:02<01:57, 1.84it/s] Loading 0: 40%|████ | 147/363 [02:02<01:57, 1.84it/s] Loading 0: 42%|████▏ | 151/363 [02:05<02:06, 1.67it/s] Loading 0: 42%|████▏ | 151/363 [02:05<02:06, 1.67it/s] Loading 0: 42%|████▏ | 152/363 [02:07<02:40, 1.31it/s] Loading 0: 42%|████▏ | 152/363 [02:07<02:40, 1.31it/s] Loading 0: 42%|████▏ | 153/363 [02:09<03:21, 1.04it/s] Loading 0: 42%|████▏ | 153/363 [02:09<03:21, 1.04it/s] Loading 0: 43%|████▎ | 156/363 [02:12<03:02, 1.13it/s] Loading 0: 43%|████▎ | 156/363 [02:12<03:02, 1.13it/s] Loading 0: 43%|████▎ | 157/363 [02:14<03:41, 1.08s/it] Loading 0: 43%|████▎ | 157/363 [02:14<03:41, 1.08s/it] Loading 0: 44%|████▎ | 158/363 [02:16<04:24, 1.29s/it] Loading 0: 44%|████▎ | 158/363 [02:16<04:24, 1.29s/it] Loading 0: 45%|████▌ | 165/363 [02:19<02:28, 1.34it/s] Loading 0: 45%|████▌ | 165/363 [02:19<02:28, 1.34it/s] Loading 0: 46%|████▌ | 166/363 [02:21<03:00, 1.09it/s] Loading 0: 46%|████▌ | 166/363 [02:21<03:00, 1.09it/s] Loading 0: 46%|████▌ | 167/363 [02:24<03:38, 1.12s/it] Loading 0: 46%|████▌ | 167/363 [02:24<03:38, 1.12s/it] Loading 0: 48%|████▊ | 174/363 [02:27<02:14, 1.40it/s] Loading 0: 48%|████▊ | 174/363 [02:27<02:14, 1.40it/s] Loading 0: 48%|████▊ | 175/363 [02:29<02:44, 1.15it/s] Loading 0: 48%|████▊ | 175/363 [02:29<02:44, 1.15it/s] Loading 0: 48%|████▊ | 176/363 [02:31<03:19, 1.07s/it] Loading 0: 48%|████▊ | 176/363 [02:31<03:19, 1.07s/it] Loading 0: 50%|█████ | 182/363 [02:34<02:17, 1.31it/s] Loading 0: 50%|█████ | 182/363 [02:34<02:17, 1.31it/s] Loading 0: 51%|█████ | 186/363 [02:35<01:44, 1.69it/s] Loading 0: 51%|█████ | 186/363 [02:35<01:44, 1.69it/s] Loading 0: 52%|█████▏ | 188/363 [02:38<02:04, 1.41it/s] Loading 0: 52%|█████▏ | 188/363 [02:38<02:04, 1.41it/s] Loading 0: 52%|█████▏ | 189/363 [02:40<02:37, 1.10it/s] Loading 0: 52%|█████▏ | 189/363 [02:40<02:37, 1.10it/s] Loading 0: 53%|█████▎ | 192/363 [02:42<02:24, 1.18it/s] Loading 0: 53%|█████▎ | 192/363 [02:42<02:24, 1.18it/s] Loading 0: 53%|█████▎ | 193/363 [02:44<02:57, 1.04s/it] Loading 0: 53%|█████▎ | 193/363 [02:44<02:57, 1.04s/it] Loading 0: 53%|█████▎ | 194/363 [02:47<03:32, 1.26s/it] Loading 0: 53%|█████▎ | 194/363 [02:47<03:32, 1.26s/it] Loading 0: 55%|█████▌ | 201/363 [02:50<01:59, 1.36it/s] Loading 0: 55%|█████▌ | 201/363 [02:50<01:59, 1.36it/s] Loading 0: 56%|█████▌ | 202/363 [02:52<02:25, 1.11it/s] Loading 0: 56%|█████▌ | 202/363 [02:52<02:25, 1.11it/s] Loading 0: 56%|█████▌ | 203/363 [02:54<02:56, 1.10s/it] Loading 0: 56%|█████▌ | 203/363 [02:54<02:56, 1.10s/it] Loading 0: 58%|█████▊ | 210/363 [02:57<01:48, 1.41it/s] Loading 0: 58%|█████▊ | 210/363 [02:57<01:48, 1.41it/s] Loading 0: 58%|█████▊ | 211/363 [02:59<02:11, 1.15it/s] Loading 0: 58%|█████▊ | 211/363 [02:59<02:11, 1.15it/s] Loading 0: 58%|█████▊ | 212/363 [03:02<02:40, 1.06s/it] Loading 0: 58%|█████▊ | 212/363 [03:02<02:40, 1.06s/it] Loading 0: 60%|██████ | 218/363 [03:05<01:50, 1.31it/s] Loading 0: 60%|██████ | 218/363 [03:05<01:50, 1.31it/s] Loading 0: 60%|██████ | 219/363 [03:07<02:15, 1.07it/s] Loading 0: 60%|██████ | 219/363 [03:07<02:15, 1.07it/s] Loading 0: 62%|██████▏ | 225/363 [03:10<01:41, 1.36it/s] Loading 0: 62%|██████▏ | 225/363 [03:10<01:41, 1.36it/s] Loading 0: 63%|██████▎ | 228/363 [03:12<01:39, 1.36it/s] Loading 0: 63%|██████▎ | 228/363 [03:12<01:39, 1.36it/s] Loading 0: 63%|██████▎ | 229/363 [03:15<02:00, 1.11it/s] Loading 0: 63%|██████▎ | 229/363 [03:15<02:00, 1.11it/s] Loading 0: 63%|██████▎ | 230/363 [03:17<02:24, 1.09s/it] Loading 0: 63%|██████▎ | 230/363 [03:17<02:24, 1.09s/it] Loading 0: 65%|██████▌ | 237/363 [03:20<01:29, 1.41it/s] Loading 0: 65%|██████▌ | 237/363 [03:20<01:29, 1.41it/s] Loading 0: 66%|██████▌ | 238/363 [03:22<01:48, 1.16it/s] Loading 0: 66%|██████▌ | 238/363 [03:22<01:48, 1.16it/s] Loading 0: 66%|██████▌ | 239/363 [03:24<02:10, 1.05s/it] Loading 0: 66%|██████▌ | 239/363 [03:24<02:10, 1.05s/it] Loading 0: 68%|██████▊ | 246/363 [03:27<01:21, 1.44it/s] Loading 0: 68%|██████▊ | 246/363 [03:27<01:21, 1.44it/s] Loading 0: 68%|██████▊ | 247/363 [03:30<01:38, 1.18it/s] Loading 0: 68%|██████▊ | 247/363 [03:30<01:38, 1.18it/s] Loading 0: 68%|██████▊ | 248/363 [03:32<01:59, 1.04s/it] Loading 0: 68%|██████▊ | 248/363 [03:32<01:59, 1.04s/it] Loading 0: 70%|███████ | 255/363 [03:35<01:14, 1.45it/s] Loading 0: 70%|███████ | 255/363 [03:35<01:14, 1.45it/s] Loading 0: 71%|███████ | 256/363 [03:37<01:30, 1.18it/s] Loading 0: 71%|███████ | 256/363 [03:37<01:30, 1.18it/s] Loading 0: 71%|███████ | 257/363 [03:39<01:49, 1.04s/it] Loading 0: 71%|███████ | 257/363 [03:39<01:49, 1.04s/it] Loading 0: 73%|███████▎ | 264/363 [03:40<00:53, 1.84it/s] Loading 0: 73%|███████▎ | 264/363 [03:40<00:53, 1.84it/s] Loading 0: 74%|███████▍ | 268/363 [03:43<00:56, 1.68it/s] Loading 0: 74%|███████▍ | 268/363 [03:43<00:56, 1.68it/s] Loading 0: 74%|███████▍ | 269/363 [03:45<01:11, 1.32it/s] Loading 0: 74%|███████▍ | 269/363 [03:45<01:11, 1.32it/s] Loading 0: 74%|███████▍ | 270/363 [03:48<01:28, 1.05it/s] Loading 0: 74%|███████▍ | 270/363 [03:48<01:28, 1.05it/s] Loading 0: 75%|███████▌ | 273/363 [04:04<03:50, 2.56s/it] Loading 0: 75%|███████▌ | 273/363 [04:04<03:50, 2.56s/it] Loading 0: 75%|███████▌ | 274/363 [04:07<03:43, 2.51s/it] Loading 0: 75%|███████▌ | 274/363 [04:07<03:43, 2.51s/it] Loading 0: 76%|███████▌ | 275/363 [04:09<03:38, 2.48s/it] Loading 0: 76%|███████▌ | 275/363 [04:09<03:38, 2.48s/it] Loading 0: 78%|███████▊ | 282/363 [04:12<01:35, 1.18s/it] Loading 0: 78%|███████▊ | 282/363 [04:12<01:35, 1.18s/it] Loading 0: 78%|███████▊ | 283/363 [04:14<01:41, 1.27s/it] Loading 0: 78%|███████▊ | 283/363 [04:14<01:41, 1.27s/it] Loading 0: 78%|███████▊ | 284/363 [04:16<01:52, 1.42s/it] Loading 0: 78%|███████▊ | 284/363 [04:16<01:52, 1.42s/it] Loading 0: 80%|████████ | 291/363 [04:19<01:00, 1.20it/s] Loading 0: 80%|████████ | 291/363 [04:19<01:00, 1.20it/s] Loading 0: 80%|████████ | 292/363 [04:21<01:09, 1.02it/s] Loading 0: 80%|████████ | 292/363 [04:21<01:09, 1.02it/s] Loading 0: 81%|████████ | 293/363 [04:24<01:20, 1.16s/it] Loading 0: 81%|████████ | 293/363 [04:24<01:20, 1.16s/it] Loading 0: 82%|████████▏ | 299/363 [04:26<00:51, 1.25it/s] Loading 0: 82%|████████▏ | 299/363 [04:26<00:51, 1.25it/s] Loading 0: 84%|████████▍ | 305/363 [04:29<00:39, 1.48it/s] Loading 0: 84%|████████▍ | 305/363 [04:29<00:39, 1.48it/s] Loading 0: 84%|████████▍ | 306/363 [04:32<00:47, 1.21it/s] Loading 0: 84%|████████▍ | 306/363 [04:32<00:47, 1.21it/s] Loading 0: 85%|████████▌ | 309/363 [04:34<00:43, 1.25it/s] Loading 0: 85%|████████▌ | 309/363 [04:34<00:43, 1.25it/s] Loading 0: 85%|████████▌ | 310/363 [04:36<00:51, 1.03it/s] Loading 0: 85%|████████▌ | 310/363 [04:36<00:51, 1.03it/s] Loading 0: 86%|████████▌ | 311/363 [04:39<01:00, 1.16s/it] Loading 0: 86%|████████▌ | 311/363 [04:39<01:00, 1.16s/it] Loading 0: 88%|████████▊ | 318/363 [04:41<00:32, 1.39it/s] Loading 0: 88%|████████▊ | 318/363 [04:41<00:32, 1.39it/s] Loading 0: 88%|████████▊ | 319/363 [04:44<00:38, 1.14it/s] Loading 0: 88%|████████▊ | 319/363 [04:44<00:38, 1.14it/s] Loading 0: 88%|████████▊ | 320/363 [04:46<00:45, 1.07s/it] Loading 0: 88%|████████▊ | 320/363 [04:46<00:45, 1.07s/it] Loading 0: 90%|█████████ | 327/363 [04:49<00:25, 1.42it/s] Loading 0: 90%|█████████ | 327/363 [04:49<00:25, 1.42it/s] Loading 0: 90%|█████████ | 328/363 [04:51<00:30, 1.16it/s] Loading 0: 90%|█████████ | 328/363 [04:51<00:30, 1.16it/s] Loading 0: 91%|█████████ | 329/363 [04:53<00:35, 1.04s/it] Loading 0: 91%|█████████ | 329/363 [04:53<00:35, 1.04s/it] Loading 0: 92%|█████████▏| 335/363 [04:56<00:21, 1.33it/s] Loading 0: 92%|█████████▏| 335/363 [04:56<00:21, 1.33it/s] Loading 0: 93%|█████████▎| 336/363 [04:59<00:24, 1.08it/s] Loading 0: 93%|█████████▎| 336/363 [04:59<00:24, 1.08it/s] Loading 0: 94%|█████████▍| 341/363 [05:00<00:13, 1.63it/s] Loading 0: 94%|█████████▍| 341/363 [05:00<00:13, 1.63it/s] Loading 0: 94%|█████████▍| 343/363 [05:02<00:14, 1.41it/s] Loading 0: 94%|█████████▍| 343/363 [05:02<00:14, 1.41it/s] Loading 0: 95%|█████████▌| 346/363 [05:04<00:12, 1.40it/s] Loading 0: 95%|█████████▌| 346/363 [05:04<00:12, 1.40it/s] Loading 0: 96%|█████████▌| 347/363 [05:06<00:14, 1.12it/s] Loading 0: 96%|█████████▌| 347/363 [05:06<00:14, 1.12it/s] Loading 0: 96%|█████████▌| 348/363 [05:08<00:16, 1.10s/it] Loading 0: 96%|█████████▌| 348/363 [05:08<00:16, 1.10s/it] Loading 0: 98%|█████████▊| 355/363 [05:11<00:05, 1.45it/s] Loading 0: 98%|█████████▊| 355/363 [05:11<00:05, 1.45it/s] Loading 0: 98%|█████████▊| 356/363 [05:14<00:05, 1.18it/s] Loading 0: 98%|█████████▊| 356/363 [05:14<00:05, 1.18it/s] Loading 0: 98%|█████████▊| 357/363 [05:16<00:06, 1.04s/it] Loading 0: 98%|█████████▊| 357/363 [05:16<00:06, 1.04s/it] Loading 0: 100%|██████████| 363/363 [05:17<00:00, 1.79it/s] Loading 0: 100%|██████████| 363/363 [05:17<00:00, 1.79it/s] Loading 0: 100%|██████████| 363/363 [05:17<00:00, 1.14it/s]
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: The tokenizer you are loading from '/tmp/tmpvfx5g9ci' 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-v2-cosine-21546-v4-mkmlizer: quantized model in 323.937s
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: Processed model ChaiML/kimid-v2_cosine-lr2e6g32 in 371.148s
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia/config.json
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia/special_tokens_map.json
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia/tokenizer_config.json
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia/tokenizer.json
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia/flywheel_model.1.safetensors
chaiml-kimid-v2-cosine-21546-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v2-cosine-21546-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-kimid-v2-cosine-21546-v4-mkmlizer completed after 440.18s with status: succeeded
Stopping job with name chaiml-kimid-v2-cosine-21546-v4-mkmlizer
Pipeline stage MKMLizer completed in 440.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v2-cosine-21546-v4
Waiting for inference service chaiml-kimid-v2-cosine-21546-v4 to be ready
Inference service chaiml-kimid-v2-cosine-21546-v4 ready after 191.2148642539978s
Pipeline stage MKMLDeployer completed in 191.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2127561569213867s
Received healthy response to inference request in 2.287874698638916s
Received healthy response to inference request in 2.3818840980529785s
Received healthy response to inference request in 3.111346960067749s
Received healthy response to inference request in 2.9296329021453857s
5 requests
0 failed requests
5th percentile: 2.2277798652648926
10th percentile: 2.2428035736083984
20th percentile: 2.27285099029541
30th percentile: 2.3066765785217287
40th percentile: 2.3442803382873536
50th percentile: 2.3818840980529785
60th percentile: 2.6009836196899414
70th percentile: 2.8200831413269043
80th percentile: 2.9659757137298586
90th percentile: 3.038661336898804
95th percentile: 3.075004148483276
99th percentile: 3.1040783977508544
mean time: 2.584698963165283
Pipeline stage StressChecker completed in 15.55s
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 0.91s
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 0.65s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-_21546_v4 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-kimid-v2-cosine-21546-v4-profiler
Waiting for inference service chaiml-kimid-v2-cosine-21546-v4-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 2527.79s
Shutdown handler de-registered
chaiml-kimid-v2-cosine-_21546_v4 status is now inactive due to auto deactivation removed underperforming models