developer_uid: zonemercy
submission_id: chaiml-cai-synth-v4-cosine_v7
model_name: test
model_group: ChaiML/cai-synth-v4_cosi
status: torndown
timestamp: 2025-12-12T18:27:15+00:00
num_battles: 6716
num_wins: 3283
celo_rating: 1290.76
family_friendly_score: 0.612
family_friendly_standard_error: 0.00689138592737339
submission_type: basic
model_repo: ChaiML/cai-synth-v4_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': 0.4246782921354852, 'latency_mean': 2.3546607446670533, 'latency_p50': 2.343759775161743, 'latency_p90': 2.5647691011428835}, {'batch_size': 2, 'throughput': 0.6340961934785091, 'latency_mean': 3.143557416200638, 'latency_p50': 3.145500659942627, 'latency_p90': 3.3880438804626465}, {'batch_size': 3, 'throughput': 0.7732488211628512, 'latency_mean': 3.8636794912815096, 'latency_p50': 3.862901449203491, 'latency_p90': 4.189360165596008}, {'batch_size': 4, 'throughput': 0.869293212369608, 'latency_mean': 4.5837082922458645, 'latency_p50': 4.608420729637146, 'latency_p90': 5.213284826278686}, {'batch_size': 5, 'throughput': 0.9263155436085855, 'latency_mean': 5.366456598043442, 'latency_p50': 5.385817646980286, 'latency_p90': 6.063836050033569}]
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
model_size: 24B
ranking_group: single
throughput_3p7s: 0.75
us_pacific_date: 2025-12-05
win_ratio: 0.4888326384752829
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-cosine-v7-mkmlizer
Waiting for job on chaiml-cai-synth-v4-cosine-v7-mkmlizer to finish
chaiml-cai-synth-v4-cosine-v7-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-cai-synth-v4-cosine-v7-mkmlizer: bash: no job control in this shell
chaiml-cai-synth-v4-cosine-v7-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-cosine-v7-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ belonging to: ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-synth-v4-cosine-v7-mkmlizer: Downloaded to shared memory in 47.334s
chaiml-cai-synth-v4-cosine-v7-mkmlizer: Checking if ChaiML/cai-synth-v4_cosine already exists in ChaiML
chaiml-cai-synth-v4-cosine-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpd0cnfio2, device:0
chaiml-cai-synth-v4-cosine-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-synth-v4-cosine-v7-mkmlizer: Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s] Loading 0: 1%| | 3.00/363 [00:02<04:24, 1.36it/s] Loading 0: 1%| | 3.00/363 [00:02<04:24, 1.36it/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<09:12, 1.54s/it] Loading 0: 1%|▏ | 5.00/363 [00:06<09:12, 1.54s/it] Loading 0: 3%|▎ | 12.0/363 [00:09<04:04, 1.43it/s] Loading 0: 3%|▎ | 12.0/363 [00:09<04:04, 1.43it/s] Loading 0: 4%|▎ | 13.0/363 [00:11<05:12, 1.12it/s] Loading 0: 4%|▎ | 13.0/363 [00:11<05:12, 1.12it/s] Loading 0: 4%|▍ | 14.0/363 [00:14<06:30, 1.12s/it] Loading 0: 4%|▍ | 14.0/363 [00:14<06:30, 1.12s/it] Loading 0: 6%|▌ | 21.0/363 [00:17<03:55, 1.45it/s] Loading 0: 6%|▌ | 21.0/363 [00:17<03:55, 1.45it/s] Loading 0: 6%|▌ | 22.0/363 [00:19<04:51, 1.17it/s] Loading 0: 6%|▌ | 22.0/363 [00:19<04:51, 1.17it/s] Loading 0: 6%|▋ | 23.0/363 [00:21<05:56, 1.05s/it] Loading 0: 6%|▋ | 23.0/363 [00:21<05:56, 1.05s/it] Loading 0: 8%|▊ | 30.0/363 [00:22<02:55, 1.89it/s] Loading 0: 8%|▊ | 30.0/363 [00:22<02:55, 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<04:05, 1.34it/s] Loading 0: 10%|▉ | 35.0/363 [00:27<04:05, 1.34it/s] Loading 0: 10%|▉ | 36.0/363 [00:29<05:09, 1.06it/s] Loading 0: 10%|▉ | 36.0/363 [00:29<05:09, 1.06it/s] Loading 0: 11%|█ | 39.0/363 [00:31<04:40, 1.15it/s] Loading 0: 11%|█ | 39.0/363 [00:31<04:40, 1.15it/s] Loading 0: 11%|█ | 40.0/363 [00:34<05:39, 1.05s/it] Loading 0: 11%|█ | 40.0/363 [00:34<05:39, 1.05s/it] Loading 0: 11%|█▏ | 41.0/363 [00:36<06:46, 1.26s/it] Loading 0: 11%|█▏ | 41.0/363 [00:36<06:46, 1.26s/it] Loading 0: 13%|█▎ | 48.0/363 [00:39<03:49, 1.37it/s] Loading 0: 13%|█▎ | 48.0/363 [00:39<03:49, 1.37it/s] Loading 0: 13%|█▎ | 49.0/363 [00:41<04:40, 1.12it/s] Loading 0: 13%|█▎ | 49.0/363 [00:41<04:40, 1.12it/s] Loading 0: 14%|█▍ | 50.0/363 [00:43<05:41, 1.09s/it] Loading 0: 14%|█▍ | 50.0/363 [00:43<05:41, 1.09s/it] Loading 0: 16%|█▌ | 57.0/363 [00:46<03:34, 1.43it/s] Loading 0: 16%|█▌ | 57.0/363 [00:46<03:34, 1.43it/s] Loading 0: 16%|█▌ | 58.0/363 [00:48<04:20, 1.17it/s] Loading 0: 16%|█▌ | 58.0/363 [00:48<04:20, 1.17it/s] Loading 0: 16%|█▋ | 59.0/363 [00:51<05:17, 1.05s/it] Loading 0: 16%|█▋ | 59.0/363 [00:51<05:17, 1.05s/it] Loading 0: 18%|█▊ | 65.0/363 [00:54<03:42, 1.34it/s] Loading 0: 18%|█▊ | 65.0/363 [00:54<03:42, 1.34it/s] Loading 0: 20%|█▉ | 71.0/363 [00:57<03:10, 1.53it/s] Loading 0: 20%|█▉ | 71.0/363 [00:57<03:10, 1.53it/s] Loading 0: 20%|█▉ | 72.0/363 [00:59<03:50, 1.26it/s] Loading 0: 20%|█▉ | 72.0/363 [00:59<03:50, 1.26it/s] Loading 0: 20%|██ | 73.0/363 [01:01<04:40, 1.03it/s] Loading 0: 20%|██ | 73.0/363 [01:01<04:40, 1.03it/s] Loading 0: 22%|██▏ | 79.0/363 [01:04<03:26, 1.37it/s] Loading 0: 22%|██▏ | 79.0/363 [01:04<03:26, 1.37it/s] Loading 0: 22%|██▏ | 80.0/363 [01:06<04:12, 1.12it/s] Loading 0: 22%|██▏ | 80.0/363 [01:06<04:12, 1.12it/s] Loading 0: 24%|██▎ | 86.0/363 [01:09<03:14, 1.42it/s] Loading 0: 24%|██▎ | 86.0/363 [01:09<03:14, 1.42it/s] Loading 0: 24%|██▍ | 87.0/363 [01:12<03:58, 1.16it/s] Loading 0: 24%|██▍ | 87.0/363 [01:12<03:58, 1.16it/s] Loading 0: 25%|██▍ | 90.0/363 [01:14<03:44, 1.22it/s] Loading 0: 25%|██▍ | 90.0/363 [01:14<03:44, 1.22it/s] Loading 0: 25%|██▌ | 91.0/363 [01:16<04:29, 1.01it/s] Loading 0: 25%|██▌ | 91.0/363 [01:16<04:29, 1.01it/s] Loading 0: 25%|██▌ | 92.0/363 [01:18<05:22, 1.19s/it] Loading 0: 25%|██▌ | 92.0/363 [01:18<05:22, 1.19s/it] Loading 0: 27%|██▋ | 99.0/363 [01:21<03:10, 1.39it/s] Loading 0: 27%|██▋ | 99.0/363 [01:21<03:10, 1.39it/s] Loading 0: 28%|██▊ | 100/363 [01:23<03:51, 1.14it/s] Loading 0: 28%|██▊ | 100/363 [01:23<03:51, 1.14it/s] Loading 0: 28%|██▊ | 101/363 [01:26<04:40, 1.07s/it] Loading 0: 28%|██▊ | 101/363 [01:26<04:40, 1.07s/it] Loading 0: 30%|██▉ | 108/363 [01:29<03:01, 1.40it/s] Loading 0: 30%|██▉ | 108/363 [01:29<03:01, 1.40it/s] Loading 0: 31%|███ | 111/363 [01:31<03:00, 1.40it/s] Loading 0: 31%|███ | 111/363 [01:31<03:00, 1.40it/s] Loading 0: 31%|███ | 112/363 [01:33<03:39, 1.14it/s] Loading 0: 31%|███ | 112/363 [01:33<03:39, 1.14it/s] Loading 0: 31%|███ | 113/363 [01:35<04:27, 1.07s/it] Loading 0: 31%|███ | 113/363 [01:35<04:27, 1.07s/it] Loading 0: 33%|███▎ | 120/363 [01:38<02:49, 1.44it/s] Loading 0: 33%|███▎ | 120/363 [01:38<02:49, 1.44it/s] Loading 0: 33%|███▎ | 121/363 [01:41<03:25, 1.18it/s] Loading 0: 33%|███▎ | 121/363 [01:41<03:25, 1.18it/s] Loading 0: 34%|███▎ | 122/363 [01:43<04:10, 1.04s/it] Loading 0: 34%|███▎ | 122/363 [01:43<04:10, 1.04s/it] Loading 0: 36%|███▌ | 129/363 [01:46<02:41, 1.45it/s] Loading 0: 36%|███▌ | 129/363 [01:46<02:41, 1.45it/s] Loading 0: 36%|███▌ | 130/363 [01:48<03:16, 1.19it/s] Loading 0: 36%|███▌ | 130/363 [01:48<03:16, 1.19it/s] Loading 0: 36%|███▌ | 131/363 [01:50<03:58, 1.03s/it] Loading 0: 36%|███▌ | 131/363 [01:50<03:58, 1.03s/it] Loading 0: 38%|███▊ | 138/363 [01:53<02:34, 1.46it/s] Loading 0: 38%|███▊ | 138/363 [01:53<02:34, 1.46it/s] Loading 0: 38%|███▊ | 139/363 [01:55<03:07, 1.19it/s] Loading 0: 38%|███▊ | 139/363 [01:55<03:07, 1.19it/s] Loading 0: 39%|███▊ | 140/363 [01:58<03:48, 1.02s/it] Loading 0: 39%|███▊ | 140/363 [01:58<03:48, 1.02s/it] Loading 0: 40%|████ | 147/363 [01:59<01:56, 1.85it/s] Loading 0: 40%|████ | 147/363 [01:59<01:56, 1.85it/s] Loading 0: 42%|████▏ | 151/363 [02:02<02:05, 1.69it/s] Loading 0: 42%|████▏ | 151/363 [02:02<02:05, 1.69it/s] Loading 0: 42%|████▏ | 152/363 [02:04<02:38, 1.33it/s] Loading 0: 42%|████▏ | 152/363 [02:04<02:38, 1.33it/s] Loading 0: 42%|████▏ | 153/363 [02:06<03:18, 1.06it/s] Loading 0: 42%|████▏ | 153/363 [02:06<03:18, 1.06it/s] Loading 0: 43%|████▎ | 156/363 [02:08<02:59, 1.15it/s] Loading 0: 43%|████▎ | 156/363 [02:08<02:59, 1.15it/s] Loading 0: 43%|████▎ | 157/363 [02:10<03:37, 1.05s/it] Loading 0: 43%|████▎ | 157/363 [02:10<03:37, 1.05s/it] Loading 0: 44%|████▎ | 158/363 [02:13<04:19, 1.27s/it] Loading 0: 44%|████▎ | 158/363 [02:13<04:19, 1.27s/it] Loading 0: 45%|████▌ | 165/363 [02:16<02:25, 1.37it/s] Loading 0: 45%|████▌ | 165/363 [02:16<02:25, 1.37it/s] Loading 0: 46%|████▌ | 166/363 [02:18<02:56, 1.12it/s] Loading 0: 46%|████▌ | 166/363 [02:18<02:56, 1.12it/s] Loading 0: 46%|████▌ | 167/363 [02:20<03:33, 1.09s/it] Loading 0: 46%|████▌ | 167/363 [02:20<03:33, 1.09s/it] Loading 0: 48%|████▊ | 174/363 [02:23<02:11, 1.44it/s] Loading 0: 48%|████▊ | 174/363 [02:23<02:11, 1.44it/s] Loading 0: 48%|████▊ | 175/363 [02:25<02:40, 1.17it/s] Loading 0: 48%|████▊ | 175/363 [02:25<02:40, 1.17it/s] Loading 0: 48%|████▊ | 176/363 [02:27<03:14, 1.04s/it] Loading 0: 48%|████▊ | 176/363 [02:27<03:14, 1.04s/it] Loading 0: 50%|█████ | 182/363 [02:30<02:15, 1.34it/s] Loading 0: 50%|█████ | 182/363 [02:30<02:15, 1.34it/s] Loading 0: 52%|█████▏ | 188/363 [02:34<01:54, 1.53it/s] Loading 0: 52%|█████▏ | 188/363 [02:34<01:54, 1.53it/s] Loading 0: 52%|█████▏ | 189/363 [02:36<02:19, 1.25it/s] Loading 0: 52%|█████▏ | 189/363 [02:36<02:19, 1.25it/s] Loading 0: 53%|█████▎ | 192/363 [02:38<02:13, 1.28it/s] Loading 0: 53%|█████▎ | 192/363 [02:38<02:13, 1.28it/s] Loading 0: 53%|█████▎ | 193/363 [02:40<02:40, 1.06it/s] Loading 0: 53%|█████▎ | 193/363 [02:40<02:40, 1.06it/s] Loading 0: 53%|█████▎ | 194/363 [02:42<03:12, 1.14s/it] Loading 0: 53%|█████▎ | 194/363 [02:42<03:12, 1.14s/it] Loading 0: 55%|█████▌ | 201/363 [02:45<01:55, 1.41it/s] Loading 0: 55%|█████▌ | 201/363 [02:45<01:55, 1.41it/s] Loading 0: 56%|█████▌ | 202/363 [02:47<02:19, 1.15it/s] Loading 0: 56%|█████▌ | 202/363 [02:47<02:19, 1.15it/s] Loading 0: 56%|█████▌ | 203/363 [02:50<02:49, 1.06s/it] Loading 0: 56%|█████▌ | 203/363 [02:50<02:49, 1.06s/it] Loading 0: 58%|█████▊ | 210/363 [02:53<01:45, 1.44it/s] Loading 0: 58%|█████▊ | 210/363 [02:53<01:45, 1.44it/s] Loading 0: 58%|█████▊ | 211/363 [02:55<02:08, 1.18it/s] Loading 0: 58%|█████▊ | 211/363 [02:55<02:08, 1.18it/s] Loading 0: 58%|█████▊ | 212/363 [02:57<02:36, 1.03s/it] Loading 0: 58%|█████▊ | 212/363 [02:57<02:36, 1.03s/it] Loading 0: 60%|██████ | 218/363 [03:00<01:48, 1.34it/s] Loading 0: 60%|██████ | 218/363 [03:00<01:48, 1.34it/s] Loading 0: 60%|██████ | 219/363 [03:02<02:12, 1.09it/s] Loading 0: 60%|██████ | 219/363 [03:02<02:12, 1.09it/s] Loading 0: 62%|██████▏ | 225/363 [03:06<01:39, 1.38it/s] Loading 0: 62%|██████▏ | 225/363 [03:06<01:39, 1.38it/s] Loading 0: 63%|██████▎ | 228/363 [03:08<01:37, 1.38it/s] Loading 0: 63%|██████▎ | 228/363 [03:08<01:37, 1.38it/s] Loading 0: 63%|██████▎ | 229/363 [03:10<01:58, 1.13it/s] Loading 0: 63%|██████▎ | 229/363 [03:10<01:58, 1.13it/s] Loading 0: 63%|██████▎ | 230/363 [03:12<02:22, 1.07s/it] Loading 0: 63%|██████▎ | 230/363 [03:12<02:22, 1.07s/it] Loading 0: 65%|██████▌ | 237/363 [03:15<01:27, 1.44it/s] Loading 0: 65%|██████▌ | 237/363 [03:15<01:27, 1.44it/s] Loading 0: 66%|██████▌ | 238/363 [03:17<01:46, 1.18it/s] Loading 0: 66%|██████▌ | 238/363 [03:17<01:46, 1.18it/s] Loading 0: 66%|██████▌ | 239/363 [03:19<02:08, 1.03s/it] Loading 0: 66%|██████▌ | 239/363 [03:19<02:08, 1.03s/it] Loading 0: 68%|██████▊ | 246/363 [03:22<01:20, 1.46it/s] Loading 0: 68%|██████▊ | 246/363 [03:22<01:20, 1.46it/s] Loading 0: 68%|██████▊ | 247/363 [03:25<01:37, 1.19it/s] Loading 0: 68%|██████▊ | 247/363 [03:25<01:37, 1.19it/s] Loading 0: 68%|██████▊ | 248/363 [03:27<01:57, 1.02s/it] Loading 0: 68%|██████▊ | 248/363 [03:27<01:57, 1.02s/it] Loading 0: 70%|██████▉ | 253/363 [03:28<01:15, 1.46it/s] Loading 0: 70%|██████▉ | 253/363 [03:28<01:15, 1.46it/s] Loading 0: 70%|███████ | 255/363 [03:31<01:26, 1.25it/s] Loading 0: 70%|███████ | 255/363 [03:31<01:26, 1.25it/s] Loading 0: 71%|███████ | 256/363 [03:33<01:44, 1.02it/s] Loading 0: 71%|███████ | 256/363 [03:33<01:44, 1.02it/s] Loading 0: 71%|███████ | 257/363 [03:35<02:05, 1.19s/it] Loading 0: 71%|███████ | 257/363 [03:35<02:05, 1.19s/it] Loading 0: 73%|███████▎ | 264/363 [03:36<00:54, 1.82it/s] Loading 0: 73%|███████▎ | 264/363 [03:36<00:54, 1.82it/s] Loading 0: 74%|███████▍ | 268/363 [03:39<00:56, 1.67it/s] Loading 0: 74%|███████▍ | 268/363 [03:39<00:56, 1.67it/s] Loading 0: 74%|███████▍ | 269/363 [03:41<01:11, 1.31it/s] Loading 0: 74%|███████▍ | 269/363 [03:41<01:11, 1.31it/s] Loading 0: 74%|███████▍ | 270/363 [03:44<01:29, 1.04it/s] Loading 0: 74%|███████▍ | 270/363 [03:44<01:29, 1.04it/s] Loading 0: 75%|███████▌ | 273/363 [04:00<03:54, 2.61s/it] Loading 0: 75%|███████▌ | 273/363 [04:00<03:54, 2.61s/it] Loading 0: 75%|███████▌ | 274/363 [04:02<03:46, 2.54s/it] Loading 0: 75%|███████▌ | 274/363 [04:02<03:46, 2.54s/it] Loading 0: 76%|███████▌ | 275/363 [04:05<03:40, 2.50s/it] Loading 0: 76%|███████▌ | 275/363 [04:05<03:40, 2.50s/it] Loading 0: 78%|███████▊ | 282/363 [04:07<01:35, 1.18s/it] Loading 0: 78%|███████▊ | 282/363 [04:07<01:35, 1.18s/it] Loading 0: 78%|███████▊ | 283/363 [04:10<01:43, 1.29s/it] Loading 0: 78%|███████▊ | 283/363 [04:10<01:43, 1.29s/it] Loading 0: 78%|███████▊ | 284/363 [04:12<01:52, 1.43s/it] Loading 0: 78%|███████▊ | 284/363 [04:12<01:52, 1.43s/it] Loading 0: 80%|████████ | 291/363 [04:15<01:00, 1.20it/s] Loading 0: 80%|████████ | 291/363 [04:15<01:00, 1.20it/s] Loading 0: 80%|████████ | 292/363 [04:17<01:09, 1.03it/s] Loading 0: 80%|████████ | 292/363 [04:17<01:09, 1.03it/s] Loading 0: 81%|████████ | 293/363 [04:19<01:20, 1.15s/it] Loading 0: 81%|████████ | 293/363 [04:19<01:20, 1.15s/it] Loading 0: 82%|████████▏ | 299/363 [04:22<00:50, 1.26it/s] Loading 0: 82%|████████▏ | 299/363 [04:22<00:50, 1.26it/s] Loading 0: 84%|████████▍ | 305/363 [04:25<00:38, 1.49it/s] Loading 0: 84%|████████▍ | 305/363 [04:25<00:38, 1.49it/s] Loading 0: 84%|████████▍ | 306/363 [04:27<00:46, 1.22it/s] Loading 0: 84%|████████▍ | 306/363 [04:27<00:46, 1.22it/s] Loading 0: 85%|████████▌ | 309/363 [04:30<00:42, 1.26it/s] Loading 0: 85%|████████▌ | 309/363 [04:30<00:42, 1.26it/s] Loading 0: 85%|████████▌ | 310/363 [04:32<00:50, 1.05it/s] Loading 0: 85%|████████▌ | 310/363 [04:32<00:50, 1.05it/s] Loading 0: 86%|████████▌ | 311/363 [04:34<00:59, 1.14s/it] Loading 0: 86%|████████▌ | 311/363 [04:34<00:59, 1.14s/it] Loading 0: 88%|████████▊ | 318/363 [04:37<00:32, 1.40it/s] Loading 0: 88%|████████▊ | 318/363 [04:37<00:32, 1.40it/s] Loading 0: 88%|████████▊ | 319/363 [04:39<00:38, 1.15it/s] Loading 0: 88%|████████▊ | 319/363 [04:39<00:38, 1.15it/s] Loading 0: 88%|████████▊ | 320/363 [04:41<00:45, 1.06s/it] Loading 0: 88%|████████▊ | 320/363 [04:41<00:45, 1.06s/it] Loading 0: 90%|█████████ | 327/363 [04:44<00:24, 1.45it/s] Loading 0: 90%|█████████ | 327/363 [04:44<00:24, 1.45it/s] Loading 0: 90%|█████████ | 328/363 [04:46<00:29, 1.19it/s] Loading 0: 90%|█████████ | 328/363 [04:46<00:29, 1.19it/s] Loading 0: 91%|█████████ | 329/363 [04:49<00:34, 1.03s/it] Loading 0: 91%|█████████ | 329/363 [04:49<00:34, 1.03s/it] Loading 0: 92%|█████████▏| 335/363 [04:52<00:20, 1.35it/s] Loading 0: 92%|█████████▏| 335/363 [04:52<00:20, 1.35it/s] Loading 0: 93%|█████████▎| 336/363 [04:54<00:24, 1.09it/s] Loading 0: 93%|█████████▎| 336/363 [04:54<00:24, 1.09it/s] Loading 0: 94%|█████████▍| 341/363 [04:55<00:13, 1.65it/s] Loading 0: 94%|█████████▍| 341/363 [04:55<00:13, 1.65it/s] Loading 0: 94%|█████████▍| 343/363 [04:57<00:14, 1.42it/s] Loading 0: 94%|█████████▍| 343/363 [04:57<00:14, 1.42it/s] Loading 0: 95%|█████████▌| 346/363 [04:59<00:12, 1.41it/s] Loading 0: 95%|█████████▌| 346/363 [04:59<00:12, 1.41it/s] Loading 0: 96%|█████████▌| 347/363 [05:02<00:14, 1.12it/s] Loading 0: 96%|█████████▌| 347/363 [05:02<00:14, 1.12it/s] Loading 0: 96%|█████████▌| 348/363 [05:04<00:16, 1.10s/it] Loading 0: 96%|█████████▌| 348/363 [05:04<00:16, 1.10s/it] Loading 0: 98%|█████████▊| 355/363 [05:07<00:05, 1.44it/s] Loading 0: 98%|█████████▊| 355/363 [05:07<00:05, 1.44it/s] Loading 0: 98%|█████████▊| 356/363 [05:09<00:05, 1.17it/s] Loading 0: 98%|█████████▊| 356/363 [05:09<00:05, 1.17it/s] Loading 0: 98%|█████████▊| 357/363 [05:11<00:06, 1.05s/it] Loading 0: 98%|█████████▊| 357/363 [05:11<00:06, 1.05s/it] Loading 0: 100%|██████████| 363/363 [05:12<00:00, 1.79it/s] Loading 0: 100%|██████████| 363/363 [05:12<00:00, 1.79it/s] Loading 0: 100%|██████████| 363/363 [05:12<00:00, 1.16it/s]
chaiml-cai-synth-v4-cosine-v7-mkmlizer: The tokenizer you are loading from '/tmp/tmpd0cnfio2' 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-cosine-v7-mkmlizer: quantized model in 320.237s
chaiml-cai-synth-v4-cosine-v7-mkmlizer: Processed model ChaiML/cai-synth-v4_cosine in 367.572s
chaiml-cai-synth-v4-cosine-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-synth-v4-cosine-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-synth-v4-cosine-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia
chaiml-cai-synth-v4-cosine-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia/config.json
chaiml-cai-synth-v4-cosine-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia/special_tokens_map.json
chaiml-cai-synth-v4-cosine-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia/tokenizer_config.json
chaiml-cai-synth-v4-cosine-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia/tokenizer.json
chaiml-cai-synth-v4-cosine-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia/flywheel_model.1.safetensors
chaiml-cai-synth-v4-cosine-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v7/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-synth-v4-cosine-v7-mkmlizer completed after 460.05s with status: succeeded
Stopping job with name chaiml-cai-synth-v4-cosine-v7-mkmlizer
Pipeline stage MKMLizer completed in 460.55s
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-cosine-v7
Waiting for inference service chaiml-cai-synth-v4-cosine-v7 to be ready
Inference service chaiml-cai-synth-v4-cosine-v7 ready after 190.67786359786987s
Pipeline stage MKMLDeployer completed in 191.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9290757179260254s
Received healthy response to inference request in 2.426368236541748s
Received healthy response to inference request in 2.4806108474731445s
Received healthy response to inference request in 2.1266021728515625s
Received healthy response to inference request in 2.4013137817382812s
5 requests
0 failed requests
5th percentile: 2.1815444946289064
10th percentile: 2.23648681640625
20th percentile: 2.3463714599609373
30th percentile: 2.4063246726989744
40th percentile: 2.4163464546203612
50th percentile: 2.426368236541748
60th percentile: 2.4480652809143066
70th percentile: 2.4697623252868652
80th percentile: 2.5703038215637206
90th percentile: 2.7496897697448732
95th percentile: 2.8393827438354493
99th percentile: 2.91113712310791
mean time: 2.4727941513061524
Pipeline stage StressChecker completed in 13.87s
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 0.64s
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 0.67s
Shutdown handler de-registered
chaiml-cai-synth-v4-cosine_v7 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 2562.10s
Shutdown handler de-registered
chaiml-cai-synth-v4-cosine_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-cai-synth-v4-cosine_v7 status is now torndown due to DeploymentManager action