developer_uid: zonemercy
submission_id: chaiml-cai-synth-v4-cos_67883_v2
model_name: test
model_group: ChaiML/cai-synth-v4_cosi
status: inactive
timestamp: 2025-12-05T06:17:07+00:00
num_battles: 10770
num_wins: 5706
celo_rating: 1255.85
family_friendly_score: 0.5468
family_friendly_standard_error: 0.00704002499995561
submission_type: basic
model_repo: ChaiML/cai-synth-v4_cosine-lr2e6g32
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 128
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2702462800718463, 'latency_mean': 3.700253477096558, 'latency_p50': 3.7061166763305664, 'latency_p90': 3.904570293426514}, {'batch_size': 2, 'throughput': 0.43948583967454924, 'latency_mean': 4.5443624186515805, 'latency_p50': 4.544786334037781, 'latency_p90': 4.756682872772217}, {'batch_size': 3, 'throughput': 0.5615189609047118, 'latency_mean': 5.327515890598297, 'latency_p50': 5.314216136932373, 'latency_p90': 5.625502324104309}, {'batch_size': 5, 'throughput': 0.713334552649039, 'latency_mean': 6.997023286819458, 'latency_p50': 7.016498446464539, 'latency_p90': 7.706334710121155}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/cai-synth-v4_cosine-lr2e6g32
model_size: 24B
ranking_group: single
us_pacific_date: 2025-12-04
win_ratio: 0.5298050139275766
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>', 'You:', 'User:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 128}
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-cos-67883-v2-mkmlizer
Waiting for job on chaiml-cai-synth-v4-cos-67883-v2-mkmlizer to finish
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: bash: no job control in this shell
chaiml-cai-synth-v4-cos-67883-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-cos-67883-v2-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ belonging to: ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ║ ║
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: Downloaded to shared memory in 45.906s
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: Checking if ChaiML/cai-synth-v4_cosine-lr2e6g32 already exists in ChaiML
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmplyd05zuq, device:0
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-synth-v4-cos-67883-v2-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<07:08, 1.19s/it] Loading 0: 1%| | 4.00/363 [00:04<07:08, 1.19s/it] Loading 0: 1%|▏ | 5.00/363 [00:06<09:09, 1.53s/it] Loading 0: 1%|▏ | 5.00/363 [00:06<09:09, 1.53s/it] Loading 0: 3%|▎ | 12.0/363 [00:09<04:03, 1.44it/s] Loading 0: 3%|▎ | 12.0/363 [00:09<04:03, 1.44it/s] Loading 0: 4%|▎ | 13.0/363 [00:11<05:11, 1.12it/s] Loading 0: 4%|▎ | 13.0/363 [00:11<05:11, 1.12it/s] Loading 0: 4%|▍ | 14.0/363 [00:14<06:27, 1.11s/it] Loading 0: 4%|▍ | 14.0/363 [00:14<06:27, 1.11s/it] Loading 0: 6%|▌ | 21.0/363 [00:16<03:54, 1.46it/s] Loading 0: 6%|▌ | 21.0/363 [00:16<03:54, 1.46it/s] Loading 0: 6%|▌ | 22.0/363 [00:19<04:49, 1.18it/s] Loading 0: 6%|▌ | 22.0/363 [00:19<04:49, 1.18it/s] Loading 0: 6%|▋ | 23.0/363 [00:21<05:54, 1.04s/it] Loading 0: 6%|▋ | 23.0/363 [00:21<05:54, 1.04s/it] Loading 0: 8%|▊ | 30.0/363 [00:22<02:56, 1.89it/s] Loading 0: 8%|▊ | 30.0/363 [00:22<02:56, 1.89it/s] Loading 0: 9%|▉ | 34.0/363 [00:25<03:12, 1.71it/s] Loading 0: 9%|▉ | 34.0/363 [00:25<03:12, 1.71it/s] Loading 0: 10%|▉ | 35.0/363 [00:27<04:04, 1.34it/s] Loading 0: 10%|▉ | 35.0/363 [00:27<04:04, 1.34it/s] Loading 0: 10%|▉ | 36.0/363 [00:29<05:05, 1.07it/s] Loading 0: 10%|▉ | 36.0/363 [00:29<05:05, 1.07it/s] Loading 0: 11%|█ | 39.0/363 [00:31<04:37, 1.17it/s] Loading 0: 11%|█ | 39.0/363 [00:31<04:37, 1.17it/s] Loading 0: 11%|█ | 40.0/363 [00:33<05:36, 1.04s/it] Loading 0: 11%|█ | 40.0/363 [00:33<05:36, 1.04s/it] Loading 0: 11%|█▏ | 41.0/363 [00:36<06:43, 1.25s/it] Loading 0: 11%|█▏ | 41.0/363 [00:36<06:43, 1.25s/it] Loading 0: 13%|█▎ | 48.0/363 [00:39<03:48, 1.38it/s] Loading 0: 13%|█▎ | 48.0/363 [00:39<03:48, 1.38it/s] Loading 0: 13%|█▎ | 49.0/363 [00:41<04:38, 1.13it/s] Loading 0: 13%|█▎ | 49.0/363 [00:41<04:38, 1.13it/s] Loading 0: 14%|█▍ | 50.0/363 [00:43<05:38, 1.08s/it] Loading 0: 14%|█▍ | 50.0/363 [00:43<05:38, 1.08s/it] Loading 0: 16%|█▌ | 57.0/363 [00:46<03:31, 1.44it/s] Loading 0: 16%|█▌ | 57.0/363 [00:46<03:31, 1.44it/s] Loading 0: 16%|█▌ | 58.0/363 [00:48<04:18, 1.18it/s] Loading 0: 16%|█▌ | 58.0/363 [00:48<04:18, 1.18it/s] Loading 0: 16%|█▋ | 59.0/363 [00:50<05:14, 1.03s/it] Loading 0: 16%|█▋ | 59.0/363 [00:50<05:14, 1.03s/it] Loading 0: 18%|█▊ | 65.0/363 [00:53<03:41, 1.35it/s] Loading 0: 18%|█▊ | 65.0/363 [00:53<03:41, 1.35it/s] Loading 0: 20%|█▉ | 71.0/363 [00:56<03:08, 1.55it/s] Loading 0: 20%|█▉ | 71.0/363 [00:56<03:08, 1.55it/s] Loading 0: 20%|█▉ | 72.0/363 [00:59<03:48, 1.27it/s] Loading 0: 20%|█▉ | 72.0/363 [00:59<03:48, 1.27it/s] Loading 0: 20%|██ | 73.0/363 [01:01<04:37, 1.04it/s] Loading 0: 20%|██ | 73.0/363 [01:01<04:37, 1.04it/s] Loading 0: 22%|██▏ | 79.0/363 [01:04<03:24, 1.39it/s] Loading 0: 22%|██▏ | 79.0/363 [01:04<03:24, 1.39it/s] Loading 0: 22%|██▏ | 80.0/363 [01:06<04:10, 1.13it/s] Loading 0: 22%|██▏ | 80.0/363 [01:06<04:10, 1.13it/s] Loading 0: 24%|██▎ | 86.0/363 [01:09<03:12, 1.44it/s] Loading 0: 24%|██▎ | 86.0/363 [01:09<03:12, 1.44it/s] Loading 0: 24%|██▍ | 87.0/363 [01:11<03:55, 1.17it/s] Loading 0: 24%|██▍ | 87.0/363 [01:11<03:55, 1.17it/s] Loading 0: 25%|██▍ | 90.0/363 [01:13<03:41, 1.23it/s] Loading 0: 25%|██▍ | 90.0/363 [01:13<03:41, 1.23it/s] Loading 0: 25%|██▌ | 91.0/363 [01:15<04:26, 1.02it/s] Loading 0: 25%|██▌ | 91.0/363 [01:15<04:26, 1.02it/s] Loading 0: 25%|██▌ | 92.0/363 [01:18<05:18, 1.18s/it] Loading 0: 25%|██▌ | 92.0/363 [01:18<05:18, 1.18s/it] Loading 0: 27%|██▋ | 99.0/363 [01:21<03:09, 1.39it/s] Loading 0: 27%|██▋ | 99.0/363 [01:21<03:09, 1.39it/s] Loading 0: 28%|██▊ | 100/363 [01:23<03:49, 1.15it/s] Loading 0: 28%|██▊ | 100/363 [01:23<03:49, 1.15it/s] Loading 0: 28%|██▊ | 101/363 [01:25<04:38, 1.06s/it] Loading 0: 28%|██▊ | 101/363 [01:25<04:38, 1.06s/it] Loading 0: 30%|██▉ | 108/363 [01:28<02:59, 1.42it/s] Loading 0: 30%|██▉ | 108/363 [01:28<02:59, 1.42it/s] Loading 0: 31%|███ | 111/363 [01:30<02:58, 1.41it/s] Loading 0: 31%|███ | 111/363 [01:30<02:58, 1.41it/s] Loading 0: 31%|███ | 112/363 [01:32<03:37, 1.16it/s] Loading 0: 31%|███ | 112/363 [01:32<03:37, 1.16it/s] Loading 0: 31%|███ | 113/363 [01:35<04:24, 1.06s/it] Loading 0: 31%|███ | 113/363 [01:35<04:24, 1.06s/it] Loading 0: 33%|███▎ | 120/363 [01:38<02:46, 1.46it/s] Loading 0: 33%|███▎ | 120/363 [01:38<02:46, 1.46it/s] Loading 0: 33%|███▎ | 121/363 [01:40<03:22, 1.19it/s] Loading 0: 33%|███▎ | 121/363 [01:40<03:22, 1.19it/s] Loading 0: 34%|███▎ | 122/363 [01:42<04:07, 1.03s/it] Loading 0: 34%|███▎ | 122/363 [01:42<04:07, 1.03s/it] Loading 0: 36%|███▌ | 129/363 [01:45<02:39, 1.47it/s] Loading 0: 36%|███▌ | 129/363 [01:45<02:39, 1.47it/s] Loading 0: 36%|███▌ | 130/363 [01:47<03:14, 1.20it/s] Loading 0: 36%|███▌ | 130/363 [01:47<03:14, 1.20it/s] Loading 0: 36%|███▌ | 131/363 [01:49<03:56, 1.02s/it] Loading 0: 36%|███▌ | 131/363 [01:49<03:56, 1.02s/it] Loading 0: 38%|███▊ | 138/363 [01:52<02:32, 1.47it/s] Loading 0: 38%|███▊ | 138/363 [01:52<02:32, 1.47it/s] Loading 0: 38%|███▊ | 139/363 [01:54<03:05, 1.20it/s] Loading 0: 38%|███▊ | 139/363 [01:54<03:05, 1.20it/s] Loading 0: 39%|███▊ | 140/363 [01:57<03:46, 1.02s/it] Loading 0: 39%|███▊ | 140/363 [01:57<03:46, 1.02s/it] Loading 0: 40%|████ | 147/363 [01:58<01:54, 1.88it/s] Loading 0: 40%|████ | 147/363 [01:58<01:54, 1.88it/s] Loading 0: 42%|████▏ | 151/363 [02:00<02:03, 1.72it/s] Loading 0: 42%|████▏ | 151/363 [02:00<02:03, 1.72it/s] Loading 0: 42%|████▏ | 152/363 [02:03<02:36, 1.35it/s] Loading 0: 42%|████▏ | 152/363 [02:03<02:36, 1.35it/s] Loading 0: 42%|████▏ | 153/363 [02:05<03:16, 1.07it/s] Loading 0: 42%|████▏ | 153/363 [02:05<03:16, 1.07it/s] Loading 0: 43%|████▎ | 156/363 [02:07<02:58, 1.16it/s] Loading 0: 43%|████▎ | 156/363 [02:07<02:58, 1.16it/s] Loading 0: 43%|████▎ | 157/363 [02:09<03:35, 1.05s/it] Loading 0: 43%|████▎ | 157/363 [02:09<03:35, 1.05s/it] Loading 0: 44%|████▎ | 158/363 [02:12<04:21, 1.27s/it] Loading 0: 44%|████▎ | 158/363 [02:12<04:21, 1.27s/it] Loading 0: 45%|████▌ | 165/363 [02:15<02:25, 1.36it/s] Loading 0: 45%|████▌ | 165/363 [02:15<02:25, 1.36it/s] Loading 0: 46%|████▌ | 166/363 [02:17<02:56, 1.12it/s] Loading 0: 46%|████▌ | 166/363 [02:17<02:56, 1.12it/s] Loading 0: 46%|████▌ | 167/363 [02:19<03:32, 1.09s/it] Loading 0: 46%|████▌ | 167/363 [02:19<03:32, 1.09s/it] Loading 0: 48%|████▊ | 174/363 [02:22<02:11, 1.44it/s] Loading 0: 48%|████▊ | 174/363 [02:22<02:11, 1.44it/s] Loading 0: 48%|████▊ | 175/363 [02:24<02:39, 1.18it/s] Loading 0: 48%|████▊ | 175/363 [02:24<02:39, 1.18it/s] Loading 0: 48%|████▊ | 176/363 [02:26<03:13, 1.03s/it] Loading 0: 48%|████▊ | 176/363 [02:26<03:13, 1.03s/it] Loading 0: 50%|█████ | 182/363 [02:29<02:13, 1.35it/s] Loading 0: 50%|█████ | 182/363 [02:29<02:13, 1.35it/s] Loading 0: 52%|█████▏ | 188/363 [02:32<01:52, 1.56it/s] Loading 0: 52%|█████▏ | 188/363 [02:32<01:52, 1.56it/s] Loading 0: 52%|█████▏ | 189/363 [02:34<02:17, 1.26it/s] Loading 0: 52%|█████▏ | 189/363 [02:34<02:17, 1.26it/s] Loading 0: 53%|█████▎ | 192/363 [02:37<02:11, 1.30it/s] Loading 0: 53%|█████▎ | 192/363 [02:37<02:11, 1.30it/s] Loading 0: 53%|█████▎ | 193/363 [02:39<02:38, 1.07it/s] Loading 0: 53%|█████▎ | 193/363 [02:39<02:38, 1.07it/s] Loading 0: 53%|█████▎ | 194/363 [02:41<03:10, 1.13s/it] Loading 0: 53%|█████▎ | 194/363 [02:41<03:10, 1.13s/it] Loading 0: 55%|█████▌ | 201/363 [02:44<01:54, 1.42it/s] Loading 0: 55%|█████▌ | 201/363 [02:44<01:54, 1.42it/s] Loading 0: 56%|█████▌ | 202/363 [02:46<02:18, 1.16it/s] Loading 0: 56%|█████▌ | 202/363 [02:46<02:18, 1.16it/s] Loading 0: 56%|█████▌ | 203/363 [02:48<02:47, 1.05s/it] Loading 0: 56%|█████▌ | 203/363 [02:48<02:47, 1.05s/it] Loading 0: 58%|█████▊ | 210/363 [02:51<01:45, 1.46it/s] Loading 0: 58%|█████▊ | 210/363 [02:51<01:45, 1.46it/s] Loading 0: 58%|█████▊ | 211/363 [02:53<02:07, 1.19it/s] Loading 0: 58%|█████▊ | 211/363 [02:53<02:07, 1.19it/s] Loading 0: 58%|█████▊ | 212/363 [02:56<02:34, 1.02s/it] Loading 0: 58%|█████▊ | 212/363 [02:56<02:34, 1.02s/it] Loading 0: 60%|██████ | 218/363 [02:58<01:46, 1.36it/s] Loading 0: 60%|██████ | 218/363 [02:58<01:46, 1.36it/s] Loading 0: 60%|██████ | 219/363 [03:01<02:10, 1.10it/s] Loading 0: 60%|██████ | 219/363 [03:01<02:10, 1.10it/s] Loading 0: 62%|██████▏ | 225/363 [03:04<01:38, 1.40it/s] Loading 0: 62%|██████▏ | 225/363 [03:04<01:38, 1.40it/s] Loading 0: 63%|██████▎ | 228/363 [03:06<01:36, 1.40it/s] Loading 0: 63%|██████▎ | 228/363 [03:06<01:36, 1.40it/s] Loading 0: 63%|██████▎ | 229/363 [03:08<01:56, 1.15it/s] Loading 0: 63%|██████▎ | 229/363 [03:08<01:56, 1.15it/s] Loading 0: 63%|██████▎ | 230/363 [03:10<02:21, 1.06s/it] Loading 0: 63%|██████▎ | 230/363 [03:10<02:21, 1.06s/it] Loading 0: 65%|██████▌ | 237/363 [03:13<01:26, 1.45it/s] Loading 0: 65%|██████▌ | 237/363 [03:13<01:26, 1.45it/s] Loading 0: 66%|██████▌ | 238/363 [03:15<01:44, 1.19it/s] Loading 0: 66%|██████▌ | 238/363 [03:15<01:44, 1.19it/s] Loading 0: 66%|██████▌ | 239/363 [03:18<02:07, 1.03s/it] Loading 0: 66%|██████▌ | 239/363 [03:18<02:07, 1.03s/it] Loading 0: 68%|██████▊ | 246/363 [03:21<01:19, 1.47it/s] Loading 0: 68%|██████▊ | 246/363 [03:21<01:19, 1.47it/s] Loading 0: 68%|██████▊ | 247/363 [03:23<01:36, 1.20it/s] Loading 0: 68%|██████▊ | 247/363 [03:23<01:36, 1.20it/s] Loading 0: 68%|██████▊ | 248/363 [03:25<01:56, 1.01s/it] Loading 0: 68%|██████▊ | 248/363 [03:25<01:56, 1.01s/it] Loading 0: 70%|███████ | 255/363 [03:28<01:13, 1.48it/s] Loading 0: 70%|███████ | 255/363 [03:28<01:13, 1.48it/s] Loading 0: 71%|███████ | 256/363 [03:30<01:28, 1.21it/s] Loading 0: 71%|███████ | 256/363 [03:30<01:28, 1.21it/s] Loading 0: 71%|███████ | 257/363 [03:32<01:47, 1.01s/it] Loading 0: 71%|███████ | 257/363 [03:32<01:47, 1.01s/it] Loading 0: 73%|███████▎ | 264/363 [03:33<00:52, 1.89it/s] Loading 0: 73%|███████▎ | 264/363 [03:33<00:52, 1.89it/s] Loading 0: 74%|███████▍ | 268/363 [03:36<00:55, 1.73it/s] Loading 0: 74%|███████▍ | 268/363 [03:36<00:55, 1.73it/s] Loading 0: 74%|███████▍ | 269/363 [03:38<01:09, 1.36it/s] Loading 0: 74%|███████▍ | 269/363 [03:38<01:09, 1.36it/s] Loading 0: 74%|███████▍ | 270/363 [03:40<01:26, 1.08it/s] Loading 0: 74%|███████▍ | 270/363 [03:40<01:26, 1.08it/s] Loading 0: 75%|███████▌ | 273/363 [03:57<03:48, 2.54s/it] Loading 0: 75%|███████▌ | 273/363 [03:57<03:48, 2.54s/it] Loading 0: 75%|███████▌ | 274/363 [03:59<03:40, 2.48s/it] Loading 0: 75%|███████▌ | 274/363 [03:59<03:40, 2.48s/it] Loading 0: 76%|███████▌ | 275/363 [04:01<03:34, 2.44s/it] Loading 0: 76%|███████▌ | 275/363 [04:01<03:34, 2.44s/it] Loading 0: 78%|███████▊ | 282/363 [04:04<01:34, 1.17s/it] Loading 0: 78%|███████▊ | 282/363 [04:04<01:34, 1.17s/it] Loading 0: 78%|███████▊ | 283/363 [04:06<01:42, 1.28s/it] Loading 0: 78%|███████▊ | 283/363 [04:06<01:42, 1.28s/it] Loading 0: 78%|███████▊ | 284/363 [04:09<01:52, 1.42s/it] Loading 0: 78%|███████▊ | 284/363 [04:09<01:52, 1.42s/it] Loading 0: 80%|████████ | 291/363 [04:12<01:00, 1.19it/s] Loading 0: 80%|████████ | 291/363 [04:12<01:00, 1.19it/s] Loading 0: 80%|████████ | 292/363 [04:14<01:09, 1.02it/s] Loading 0: 80%|████████ | 292/363 [04:14<01:09, 1.02it/s] Loading 0: 81%|████████ | 293/363 [04:16<01:21, 1.16s/it] Loading 0: 81%|████████ | 293/363 [04:16<01:21, 1.16s/it] Loading 0: 82%|████████▏ | 299/363 [04:19<00:51, 1.24it/s] Loading 0: 82%|████████▏ | 299/363 [04:19<00:51, 1.24it/s] Loading 0: 84%|████████▍ | 305/363 [04:22<00:39, 1.47it/s] Loading 0: 84%|████████▍ | 305/363 [04:22<00:39, 1.47it/s] Loading 0: 84%|████████▍ | 306/363 [04:25<00:47, 1.20it/s] Loading 0: 84%|████████▍ | 306/363 [04:25<00:47, 1.20it/s] Loading 0: 85%|████████▌ | 309/363 [04:27<00:43, 1.24it/s] Loading 0: 85%|████████▌ | 309/363 [04:27<00:43, 1.24it/s] Loading 0: 85%|████████▌ | 310/363 [04:29<00:51, 1.02it/s] Loading 0: 85%|████████▌ | 310/363 [04:29<00:51, 1.02it/s] Loading 0: 86%|████████▌ | 311/363 [04:31<01:01, 1.17s/it] Loading 0: 86%|████████▌ | 311/363 [04:31<01:01, 1.17s/it] Loading 0: 88%|████████▊ | 318/363 [04:34<00:32, 1.37it/s] Loading 0: 88%|████████▊ | 318/363 [04:34<00:32, 1.37it/s] Loading 0: 88%|████████▊ | 319/363 [04:37<00:39, 1.12it/s] Loading 0: 88%|████████▊ | 319/363 [04:37<00:39, 1.12it/s] Loading 0: 88%|████████▊ | 320/363 [04:39<00:46, 1.09s/it] Loading 0: 88%|████████▊ | 320/363 [04:39<00:46, 1.09s/it] Loading 0: 90%|█████████ | 327/363 [04:42<00:25, 1.42it/s] Loading 0: 90%|█████████ | 327/363 [04:42<00:25, 1.42it/s] Loading 0: 90%|█████████ | 328/363 [04:44<00:30, 1.15it/s] Loading 0: 90%|█████████ | 328/363 [04:44<00:30, 1.15it/s] Loading 0: 91%|█████████ | 329/363 [04:46<00:35, 1.05s/it] Loading 0: 91%|█████████ | 329/363 [04:46<00:35, 1.05s/it] Loading 0: 92%|█████████▏| 335/363 [04:49<00:21, 1.33it/s] Loading 0: 92%|█████████▏| 335/363 [04:49<00:21, 1.33it/s] Loading 0: 93%|█████████▎| 336/363 [04:52<00:24, 1.09it/s] Loading 0: 93%|█████████▎| 336/363 [04:52<00:24, 1.09it/s] Loading 0: 94%|█████████▍| 341/363 [04:53<00:13, 1.64it/s] Loading 0: 94%|█████████▍| 341/363 [04:53<00:13, 1.64it/s] Loading 0: 94%|█████████▍| 343/363 [04:55<00:14, 1.42it/s] Loading 0: 94%|█████████▍| 343/363 [04:55<00:14, 1.42it/s] Loading 0: 95%|█████████▌| 346/363 [04:57<00:12, 1.41it/s] Loading 0: 95%|█████████▌| 346/363 [04:57<00:12, 1.41it/s] Loading 0: 96%|█████████▌| 347/363 [04:59<00:14, 1.13it/s] Loading 0: 96%|█████████▌| 347/363 [04:59<00:14, 1.13it/s] Loading 0: 96%|█████████▌| 348/363 [05:01<00:16, 1.10s/it] Loading 0: 96%|█████████▌| 348/363 [05:01<00:16, 1.10s/it] Loading 0: 98%|█████████▊| 355/363 [05:04<00:05, 1.46it/s] Loading 0: 98%|█████████▊| 355/363 [05:04<00:05, 1.46it/s] Loading 0: 98%|█████████▊| 356/363 [05:06<00:05, 1.18it/s] Loading 0: 98%|█████████▊| 356/363 [05:06<00:05, 1.18it/s] Loading 0: 98%|█████████▊| 357/363 [05:09<00:06, 1.04s/it] Loading 0: 98%|█████████▊| 357/363 [05:09<00:06, 1.04s/it] Loading 0: 100%|██████████| 363/363 [05:10<00:00, 1.81it/s] Loading 0: 100%|██████████| 363/363 [05:10<00:00, 1.81it/s] Loading 0: 100%|██████████| 363/363 [05:10<00:00, 1.17it/s]
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: The tokenizer you are loading from '/tmp/tmplyd05zuq' 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-cos-67883-v2-mkmlizer: quantized model in 316.686s
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: Processed model ChaiML/cai-synth-v4_cosine-lr2e6g32 in 362.592s
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia/config.json
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia/special_tokens_map.json
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia/tokenizer_config.json
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia/tokenizer.json
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia/flywheel_model.1.safetensors
chaiml-cai-synth-v4-cos-67883-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cos-67883-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-synth-v4-cos-67883-v2-mkmlizer completed after 408.05s with status: succeeded
Stopping job with name chaiml-cai-synth-v4-cos-67883-v2-mkmlizer
Pipeline stage MKMLizer completed in 408.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 2.39s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-synth-v4-cos-67883-v2
Waiting for inference service chaiml-cai-synth-v4-cos-67883-v2 to be ready
Inference service chaiml-cai-synth-v4-cos-67883-v2 ready after 181.22025990486145s
Pipeline stage MKMLDeployer completed in 181.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7568750381469727s
Received healthy response to inference request in 3.6323907375335693s
Received healthy response to inference request in 3.645596742630005s
Received healthy response to inference request in 3.404758930206299s
Received healthy response to inference request in 3.8625330924987793s
5 requests
0 failed requests
5th percentile: 3.450285291671753
10th percentile: 3.495811653137207
20th percentile: 3.586864376068115
30th percentile: 3.6350319385528564
40th percentile: 3.6403143405914307
50th percentile: 3.645596742630005
60th percentile: 3.690108060836792
70th percentile: 3.734619379043579
80th percentile: 3.778006649017334
90th percentile: 3.8202698707580565
95th percentile: 3.841401481628418
99th percentile: 3.858306770324707
mean time: 3.660430908203125
Pipeline stage StressChecker completed in 20.03s
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 0.65s
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 0.64s
Shutdown handler de-registered
chaiml-cai-synth-v4-cos_67883_v2 status is now deployed due to DeploymentManager action
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 3201.71s
Shutdown handler de-registered
chaiml-cai-synth-v4-cos_67883_v2 status is now inactive due to auto deactivation removed underperforming models