developer_uid: zonemercy
submission_id: chaiml-cai-synth-v4-cosine_v4
model_name: test
model_group: ChaiML/cai-synth-v4_cosi
status: torndown
timestamp: 2025-12-12T18:27:14+00:00
num_battles: 6935
num_wins: 3391
celo_rating: 1280.98
family_friendly_score: 0.617
family_friendly_standard_error: 0.006874750904578289
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': 0.4296746120844871, 'latency_mean': 2.327273988723755, 'latency_p50': 2.3308310508728027, 'latency_p90': 2.5263940334320067}, {'batch_size': 2, 'throughput': 0.6342815941996881, 'latency_mean': 3.146076465845108, 'latency_p50': 3.1469175815582275, 'latency_p90': 3.3915982246398926}, {'batch_size': 3, 'throughput': 0.7814607263557897, 'latency_mean': 3.826641861200333, 'latency_p50': 3.8190890550613403, 'latency_p90': 4.116933584213257}, {'batch_size': 4, 'throughput': 0.8799385092179828, 'latency_mean': 4.529958839416504, 'latency_p50': 4.555975794792175, 'latency_p90': 5.032128119468688}, {'batch_size': 5, 'throughput': 0.9413079394578682, 'latency_mean': 5.282944140434265, 'latency_p50': 5.2585355043411255, 'latency_p90': 6.067508363723755}]
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: 0.76
us_pacific_date: 2025-12-05
win_ratio: 0.4889689978370584
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', '</s>', 'You:'], '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-v4-mkmlizer
Waiting for job on chaiml-cai-synth-v4-cosine-v4-mkmlizer to finish
chaiml-cai-synth-v4-cosine-v4-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-cai-synth-v4-cosine-v4-mkmlizer: bash: no job control in this shell
chaiml-cai-synth-v4-cosine-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-cai-synth-v4-cosine-v4-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ belonging to: ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ║ ║
chaiml-cai-synth-v4-cosine-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-synth-v4-cosine-v4-mkmlizer: Downloaded to shared memory in 44.445s
chaiml-cai-synth-v4-cosine-v4-mkmlizer: Checking if ChaiML/cai-synth-v4_cosine already exists in ChaiML
chaiml-cai-synth-v4-cosine-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpvycvqte6, device:0
chaiml-cai-synth-v4-cosine-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-synth-v4-cosine-v4-mkmlizer: Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s] Loading 0: 1%| | 3.00/363 [00:01<03:48, 1.57it/s] Loading 0: 1%| | 3.00/363 [00:01<03:48, 1.57it/s] Loading 0: 1%| | 4.00/363 [00:03<06:11, 1.03s/it] Loading 0: 1%| | 4.00/363 [00:03<06:11, 1.03s/it] Loading 0: 1%|▏ | 5.00/363 [00:05<07:59, 1.34s/it] Loading 0: 1%|▏ | 5.00/363 [00:05<07:59, 1.34s/it] Loading 0: 3%|▎ | 12.0/363 [00:08<03:32, 1.65it/s] Loading 0: 3%|▎ | 12.0/363 [00:08<03:32, 1.65it/s] Loading 0: 4%|▎ | 13.0/363 [00:10<04:31, 1.29it/s] Loading 0: 4%|▎ | 13.0/363 [00:10<04:31, 1.29it/s] Loading 0: 4%|▍ | 14.0/363 [00:12<05:38, 1.03it/s] Loading 0: 4%|▍ | 14.0/363 [00:12<05:38, 1.03it/s] Loading 0: 6%|▌ | 21.0/363 [00:14<03:24, 1.67it/s] Loading 0: 6%|▌ | 21.0/363 [00:14<03:24, 1.67it/s] Loading 0: 6%|▌ | 22.0/363 [00:16<04:13, 1.35it/s] Loading 0: 6%|▌ | 22.0/363 [00:16<04:13, 1.35it/s] Loading 0: 6%|▋ | 23.0/363 [00:18<05:11, 1.09it/s] Loading 0: 6%|▋ | 23.0/363 [00:18<05:11, 1.09it/s] Loading 0: 9%|▊ | 31.0/363 [00:19<02:28, 2.24it/s] Loading 0: 9%|▊ | 31.0/363 [00:19<02:28, 2.24it/s] Loading 0: 9%|▉ | 34.0/363 [00:22<02:50, 1.93it/s] Loading 0: 9%|▉ | 34.0/363 [00:22<02:50, 1.93it/s] Loading 0: 10%|▉ | 35.0/363 [00:23<03:37, 1.51it/s] Loading 0: 10%|▉ | 35.0/363 [00:23<03:37, 1.51it/s] Loading 0: 10%|▉ | 36.0/363 [00:25<04:33, 1.20it/s] Loading 0: 10%|▉ | 36.0/363 [00:25<04:33, 1.20it/s] Loading 0: 11%|█ | 39.0/363 [00:27<04:06, 1.31it/s] Loading 0: 11%|█ | 39.0/363 [00:27<04:06, 1.31it/s] Loading 0: 11%|█ | 40.0/363 [00:29<05:00, 1.07it/s] Loading 0: 11%|█ | 40.0/363 [00:29<05:00, 1.07it/s] Loading 0: 11%|█▏ | 41.0/363 [00:31<05:58, 1.11s/it] Loading 0: 11%|█▏ | 41.0/363 [00:31<05:58, 1.11s/it] Loading 0: 13%|█▎ | 48.0/363 [00:34<03:21, 1.56it/s] Loading 0: 13%|█▎ | 48.0/363 [00:34<03:21, 1.56it/s] Loading 0: 13%|█▎ | 49.0/363 [00:36<04:05, 1.28it/s] Loading 0: 13%|█▎ | 49.0/363 [00:36<04:05, 1.28it/s] Loading 0: 14%|█▍ | 50.0/363 [00:38<04:57, 1.05it/s] Loading 0: 14%|█▍ | 50.0/363 [00:38<04:57, 1.05it/s] Loading 0: 16%|█▌ | 57.0/363 [00:40<03:05, 1.65it/s] Loading 0: 16%|█▌ | 57.0/363 [00:40<03:05, 1.65it/s] Loading 0: 16%|█▌ | 58.0/363 [00:42<03:46, 1.35it/s] Loading 0: 16%|█▌ | 58.0/363 [00:42<03:46, 1.35it/s] Loading 0: 16%|█▋ | 59.0/363 [00:44<04:36, 1.10it/s] Loading 0: 16%|█▋ | 59.0/363 [00:44<04:36, 1.10it/s] Loading 0: 18%|█▊ | 65.0/363 [00:47<03:13, 1.54it/s] Loading 0: 18%|█▊ | 65.0/363 [00:47<03:13, 1.54it/s] Loading 0: 20%|█▉ | 71.0/363 [00:49<02:44, 1.77it/s] Loading 0: 20%|█▉ | 71.0/363 [00:49<02:44, 1.77it/s] Loading 0: 20%|█▉ | 72.0/363 [00:51<03:19, 1.46it/s] Loading 0: 20%|█▉ | 72.0/363 [00:51<03:19, 1.46it/s] Loading 0: 20%|██ | 73.0/363 [00:53<04:03, 1.19it/s] Loading 0: 20%|██ | 73.0/363 [00:53<04:03, 1.19it/s] Loading 0: 22%|██▏ | 79.0/363 [00:56<02:58, 1.59it/s] Loading 0: 22%|██▏ | 79.0/363 [00:56<02:58, 1.59it/s] Loading 0: 22%|██▏ | 80.0/363 [00:58<03:38, 1.29it/s] Loading 0: 22%|██▏ | 80.0/363 [00:58<03:38, 1.29it/s] Loading 0: 24%|██▎ | 86.0/363 [01:00<02:48, 1.65it/s] Loading 0: 24%|██▎ | 86.0/363 [01:00<02:48, 1.65it/s] Loading 0: 24%|██▍ | 87.0/363 [01:02<03:26, 1.34it/s] Loading 0: 24%|██▍ | 87.0/363 [01:02<03:26, 1.34it/s] Loading 0: 25%|██▍ | 90.0/363 [01:04<03:13, 1.41it/s] Loading 0: 25%|██▍ | 90.0/363 [01:04<03:13, 1.41it/s] Loading 0: 25%|██▌ | 91.0/363 [01:06<03:53, 1.17it/s] Loading 0: 25%|██▌ | 91.0/363 [01:06<03:53, 1.17it/s] Loading 0: 25%|██▌ | 92.0/363 [01:08<04:39, 1.03s/it] Loading 0: 25%|██▌ | 92.0/363 [01:08<04:39, 1.03s/it] Loading 0: 27%|██▋ | 99.0/363 [01:11<02:45, 1.60it/s] Loading 0: 27%|██▋ | 99.0/363 [01:11<02:45, 1.60it/s] Loading 0: 28%|██▊ | 100/363 [01:12<03:20, 1.31it/s] Loading 0: 28%|██▊ | 100/363 [01:12<03:20, 1.31it/s] Loading 0: 28%|██▊ | 101/363 [01:14<04:03, 1.08it/s] Loading 0: 28%|██▊ | 101/363 [01:14<04:03, 1.08it/s] Loading 0: 30%|██▉ | 108/363 [01:17<02:36, 1.63it/s] Loading 0: 30%|██▉ | 108/363 [01:17<02:36, 1.63it/s] Loading 0: 31%|███ | 111/363 [01:19<02:35, 1.62it/s] Loading 0: 31%|███ | 111/363 [01:19<02:35, 1.62it/s] Loading 0: 31%|███ | 112/363 [01:21<03:10, 1.32it/s] Loading 0: 31%|███ | 112/363 [01:21<03:10, 1.32it/s] Loading 0: 31%|███ | 113/363 [01:23<03:51, 1.08it/s] Loading 0: 31%|███ | 113/363 [01:23<03:51, 1.08it/s] Loading 0: 33%|███▎ | 120/363 [01:25<02:26, 1.66it/s] Loading 0: 33%|███▎ | 120/363 [01:25<02:26, 1.66it/s] Loading 0: 33%|███▎ | 121/363 [01:27<02:58, 1.36it/s] Loading 0: 33%|███▎ | 121/363 [01:27<02:58, 1.36it/s] Loading 0: 34%|███▎ | 122/363 [01:29<03:37, 1.11it/s] Loading 0: 34%|███▎ | 122/363 [01:29<03:37, 1.11it/s] Loading 0: 36%|███▌ | 129/363 [01:32<02:19, 1.68it/s] Loading 0: 36%|███▌ | 129/363 [01:32<02:19, 1.68it/s] Loading 0: 36%|███▌ | 130/363 [01:34<02:49, 1.37it/s] Loading 0: 36%|███▌ | 130/363 [01:34<02:49, 1.37it/s] Loading 0: 36%|███▌ | 131/363 [01:36<03:26, 1.12it/s] Loading 0: 36%|███▌ | 131/363 [01:36<03:26, 1.12it/s] Loading 0: 38%|███▊ | 138/363 [01:38<02:14, 1.68it/s] Loading 0: 38%|███▊ | 138/363 [01:38<02:14, 1.68it/s] Loading 0: 38%|███▊ | 139/363 [01:40<02:43, 1.37it/s] Loading 0: 38%|███▊ | 139/363 [01:40<02:43, 1.37it/s] Loading 0: 39%|███▊ | 140/363 [01:42<03:18, 1.12it/s] Loading 0: 39%|███▊ | 140/363 [01:42<03:18, 1.12it/s] Loading 0: 41%|████ | 148/363 [01:43<01:36, 2.23it/s] Loading 0: 41%|████ | 148/363 [01:43<01:36, 2.23it/s] Loading 0: 42%|████▏ | 151/363 [01:45<01:49, 1.93it/s] Loading 0: 42%|████▏ | 151/363 [01:45<01:49, 1.93it/s] Loading 0: 42%|████▏ | 152/363 [01:47<02:19, 1.52it/s] Loading 0: 42%|████▏ | 152/363 [01:47<02:19, 1.52it/s] Loading 0: 42%|████▏ | 153/363 [01:49<02:56, 1.19it/s] Loading 0: 42%|████▏ | 153/363 [01:49<02:56, 1.19it/s] Loading 0: 43%|████▎ | 156/363 [01:51<02:40, 1.29it/s] Loading 0: 43%|████▎ | 156/363 [01:51<02:40, 1.29it/s] Loading 0: 43%|████▎ | 157/363 [01:53<03:14, 1.06it/s] Loading 0: 43%|████▎ | 157/363 [01:53<03:14, 1.06it/s] Loading 0: 44%|████▎ | 158/363 [01:55<03:51, 1.13s/it] Loading 0: 44%|████▎ | 158/363 [01:55<03:51, 1.13s/it] Loading 0: 45%|████▌ | 165/363 [01:58<02:09, 1.53it/s] Loading 0: 45%|████▌ | 165/363 [01:58<02:09, 1.53it/s] Loading 0: 46%|████▌ | 166/363 [02:00<02:37, 1.25it/s] Loading 0: 46%|████▌ | 166/363 [02:00<02:37, 1.25it/s] Loading 0: 46%|████▌ | 167/363 [02:02<03:11, 1.03it/s] Loading 0: 46%|████▌ | 167/363 [02:02<03:11, 1.03it/s] Loading 0: 48%|████▊ | 174/363 [02:05<01:57, 1.61it/s] Loading 0: 48%|████▊ | 174/363 [02:05<01:57, 1.61it/s] Loading 0: 48%|████▊ | 175/363 [02:07<02:23, 1.31it/s] Loading 0: 48%|████▊ | 175/363 [02:07<02:23, 1.31it/s] Loading 0: 48%|████▊ | 176/363 [02:09<02:54, 1.07it/s] Loading 0: 48%|████▊ | 176/363 [02:09<02:54, 1.07it/s] Loading 0: 50%|█████ | 182/363 [02:11<02:01, 1.49it/s] Loading 0: 50%|█████ | 182/363 [02:11<02:01, 1.49it/s] Loading 0: 52%|█████▏ | 188/363 [02:14<01:42, 1.71it/s] Loading 0: 52%|█████▏ | 188/363 [02:14<01:42, 1.71it/s] Loading 0: 52%|█████▏ | 189/363 [02:16<02:05, 1.39it/s] Loading 0: 52%|█████▏ | 189/363 [02:16<02:05, 1.39it/s] Loading 0: 53%|█████▎ | 192/363 [02:18<01:59, 1.43it/s] Loading 0: 53%|█████▎ | 192/363 [02:18<01:59, 1.43it/s] Loading 0: 53%|█████▎ | 193/363 [02:20<02:24, 1.18it/s] Loading 0: 53%|█████▎ | 193/363 [02:20<02:24, 1.18it/s] Loading 0: 53%|█████▎ | 194/363 [02:22<02:53, 1.03s/it] Loading 0: 53%|█████▎ | 194/363 [02:22<02:53, 1.03s/it] Loading 0: 55%|█████▌ | 201/363 [02:25<01:44, 1.55it/s] Loading 0: 55%|█████▌ | 201/363 [02:25<01:44, 1.55it/s] Loading 0: 56%|█████▌ | 202/363 [02:27<02:06, 1.27it/s] Loading 0: 56%|█████▌ | 202/363 [02:27<02:06, 1.27it/s] Loading 0: 56%|█████▌ | 203/363 [02:29<02:32, 1.05it/s] Loading 0: 56%|█████▌ | 203/363 [02:29<02:32, 1.05it/s] Loading 0: 58%|█████▊ | 210/363 [02:31<01:35, 1.60it/s] Loading 0: 58%|█████▊ | 210/363 [02:31<01:35, 1.60it/s] Loading 0: 58%|█████▊ | 211/363 [02:33<01:55, 1.32it/s] Loading 0: 58%|█████▊ | 211/363 [02:33<01:55, 1.32it/s] Loading 0: 58%|█████▊ | 212/363 [02:35<02:19, 1.08it/s] Loading 0: 58%|█████▊ | 212/363 [02:35<02:19, 1.08it/s] Loading 0: 60%|██████ | 218/363 [02:38<01:37, 1.49it/s] Loading 0: 60%|██████ | 218/363 [02:38<01:37, 1.49it/s] Loading 0: 60%|██████ | 219/363 [02:40<01:58, 1.22it/s] Loading 0: 60%|██████ | 219/363 [02:40<01:58, 1.22it/s] Loading 0: 62%|██████▏ | 225/363 [02:43<01:28, 1.55it/s] Loading 0: 62%|██████▏ | 225/363 [02:43<01:28, 1.55it/s] Loading 0: 63%|██████▎ | 228/363 [02:45<01:26, 1.55it/s] Loading 0: 63%|██████▎ | 228/363 [02:45<01:26, 1.55it/s] Loading 0: 63%|██████▎ | 229/363 [02:47<01:45, 1.27it/s] Loading 0: 63%|██████▎ | 229/363 [02:47<01:45, 1.27it/s] Loading 0: 63%|██████▎ | 230/363 [02:49<02:07, 1.05it/s] Loading 0: 63%|██████▎ | 230/363 [02:49<02:07, 1.05it/s] Loading 0: 65%|██████▌ | 237/363 [02:51<01:18, 1.62it/s] Loading 0: 65%|██████▌ | 237/363 [02:51<01:18, 1.62it/s] Loading 0: 66%|██████▌ | 238/363 [02:53<01:34, 1.32it/s] Loading 0: 66%|██████▌ | 238/363 [02:53<01:34, 1.32it/s] Loading 0: 66%|██████▌ | 239/363 [02:55<01:54, 1.08it/s] Loading 0: 66%|██████▌ | 239/363 [02:55<01:54, 1.08it/s] Loading 0: 68%|██████▊ | 246/363 [02:58<01:11, 1.63it/s] Loading 0: 68%|██████▊ | 246/363 [02:58<01:11, 1.63it/s] Loading 0: 68%|██████▊ | 247/363 [03:00<01:27, 1.33it/s] Loading 0: 68%|██████▊ | 247/363 [03:00<01:27, 1.33it/s] Loading 0: 68%|██████▊ | 248/363 [03:02<01:45, 1.09it/s] Loading 0: 68%|██████▊ | 248/363 [03:02<01:45, 1.09it/s] Loading 0: 70%|███████ | 255/363 [03:04<01:06, 1.64it/s] Loading 0: 70%|███████ | 255/363 [03:04<01:06, 1.64it/s] Loading 0: 71%|███████ | 256/363 [03:06<01:20, 1.34it/s] Loading 0: 71%|███████ | 256/363 [03:06<01:20, 1.34it/s] Loading 0: 71%|███████ | 257/363 [03:08<01:36, 1.09it/s] Loading 0: 71%|███████ | 257/363 [03:08<01:36, 1.09it/s] Loading 0: 73%|███████▎ | 265/363 [03:10<00:45, 2.17it/s] Loading 0: 73%|███████▎ | 265/363 [03:10<00:45, 2.17it/s] Loading 0: 74%|███████▍ | 268/363 [03:12<00:50, 1.88it/s] Loading 0: 74%|███████▍ | 268/363 [03:12<00:50, 1.88it/s] Loading 0: 74%|███████▍ | 269/363 [03:14<01:03, 1.48it/s] Loading 0: 74%|███████▍ | 269/363 [03:14<01:03, 1.48it/s] Loading 0: 74%|███████▍ | 270/363 [03:16<01:18, 1.18it/s] Loading 0: 74%|███████▍ | 270/363 [03:16<01:18, 1.18it/s] Loading 0: 75%|███████▌ | 273/363 [03:31<03:34, 2.38s/it] Loading 0: 75%|███████▌ | 273/363 [03:31<03:34, 2.38s/it] Loading 0: 75%|███████▌ | 274/363 [03:33<03:26, 2.31s/it] Loading 0: 75%|███████▌ | 274/363 [03:33<03:26, 2.31s/it] Loading 0: 76%|███████▌ | 275/363 [03:35<03:20, 2.28s/it] Loading 0: 76%|███████▌ | 275/363 [03:35<03:20, 2.28s/it] Loading 0: 78%|███████▊ | 282/363 [03:38<01:26, 1.07s/it] Loading 0: 78%|███████▊ | 282/363 [03:38<01:26, 1.07s/it] Loading 0: 78%|███████▊ | 283/363 [03:40<01:33, 1.17s/it] Loading 0: 78%|███████▊ | 283/363 [03:40<01:33, 1.17s/it] Loading 0: 78%|███████▊ | 284/363 [03:42<01:42, 1.29s/it] Loading 0: 78%|███████▊ | 284/363 [03:42<01:42, 1.29s/it] Loading 0: 80%|████████ | 291/363 [03:44<00:54, 1.33it/s] Loading 0: 80%|████████ | 291/363 [03:44<00:54, 1.33it/s] Loading 0: 80%|████████ | 292/363 [03:46<01:02, 1.14it/s] Loading 0: 80%|████████ | 292/363 [03:46<01:02, 1.14it/s] Loading 0: 81%|████████ | 293/363 [03:48<01:11, 1.03s/it] Loading 0: 81%|████████ | 293/363 [03:48<01:11, 1.03s/it] Loading 0: 82%|████████▏ | 299/363 [03:51<00:45, 1.41it/s] Loading 0: 82%|████████▏ | 299/363 [03:51<00:45, 1.41it/s] Loading 0: 84%|████████▍ | 305/363 [03:54<00:34, 1.67it/s] Loading 0: 84%|████████▍ | 305/363 [03:54<00:34, 1.67it/s] Loading 0: 84%|████████▍ | 306/363 [03:56<00:41, 1.37it/s] Loading 0: 84%|████████▍ | 306/363 [03:56<00:41, 1.37it/s] Loading 0: 85%|████████▌ | 309/363 [03:58<00:38, 1.42it/s] Loading 0: 85%|████████▌ | 309/363 [03:58<00:38, 1.42it/s] Loading 0: 85%|████████▌ | 310/363 [04:00<00:45, 1.17it/s] Loading 0: 85%|████████▌ | 310/363 [04:00<00:45, 1.17it/s] Loading 0: 86%|████████▌ | 311/363 [04:02<00:53, 1.03s/it] Loading 0: 86%|████████▌ | 311/363 [04:02<00:53, 1.03s/it] Loading 0: 88%|████████▊ | 318/363 [04:04<00:28, 1.58it/s] Loading 0: 88%|████████▊ | 318/363 [04:04<00:28, 1.58it/s] Loading 0: 88%|████████▊ | 319/363 [04:06<00:34, 1.29it/s] Loading 0: 88%|████████▊ | 319/363 [04:06<00:34, 1.29it/s] Loading 0: 88%|████████▊ | 320/363 [04:08<00:40, 1.06it/s] Loading 0: 88%|████████▊ | 320/363 [04:08<00:40, 1.06it/s] Loading 0: 90%|█████████ | 327/363 [04:11<00:22, 1.63it/s] Loading 0: 90%|█████████ | 327/363 [04:11<00:22, 1.63it/s] Loading 0: 90%|█████████ | 328/363 [04:13<00:26, 1.33it/s] Loading 0: 90%|█████████ | 328/363 [04:13<00:26, 1.33it/s] Loading 0: 91%|█████████ | 329/363 [04:15<00:31, 1.09it/s] Loading 0: 91%|█████████ | 329/363 [04:15<00:31, 1.09it/s] Loading 0: 92%|█████████▏| 335/363 [04:17<00:18, 1.52it/s] Loading 0: 92%|█████████▏| 335/363 [04:17<00:18, 1.52it/s] Loading 0: 93%|█████████▎| 336/363 [04:19<00:21, 1.23it/s] Loading 0: 93%|█████████▎| 336/363 [04:19<00:21, 1.23it/s] Loading 0: 94%|█████████▍| 343/363 [04:22<00:11, 1.67it/s] Loading 0: 94%|█████████▍| 343/363 [04:22<00:11, 1.67it/s] Loading 0: 95%|█████████▌| 346/363 [04:24<00:10, 1.64it/s] Loading 0: 95%|█████████▌| 346/363 [04:24<00:10, 1.64it/s] Loading 0: 96%|█████████▌| 347/363 [04:26<00:11, 1.34it/s] Loading 0: 96%|█████████▌| 347/363 [04:26<00:11, 1.34it/s] Loading 0: 96%|█████████▌| 348/363 [04:28<00:13, 1.09it/s] Loading 0: 96%|█████████▌| 348/363 [04:28<00:13, 1.09it/s] Loading 0: 98%|█████████▊| 355/363 [04:31<00:04, 1.64it/s] Loading 0: 98%|█████████▊| 355/363 [04:31<00:04, 1.64it/s] Loading 0: 98%|█████████▊| 356/363 [04:33<00:05, 1.34it/s] Loading 0: 98%|█████████▊| 356/363 [04:33<00:05, 1.34it/s] Loading 0: 98%|█████████▊| 357/363 [04:35<00:05, 1.10it/s] Loading 0: 98%|█████████▊| 357/363 [04:35<00:05, 1.10it/s] Loading 0: 100%|██████████| 363/363 [04:35<00:00, 2.02it/s] Loading 0: 100%|██████████| 363/363 [04:35<00:00, 2.02it/s] Loading 0: 100%|██████████| 363/363 [04:35<00:00, 1.32it/s]
chaiml-cai-synth-v4-cosine-v4-mkmlizer: The tokenizer you are loading from '/tmp/tmpvycvqte6' 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-v4-mkmlizer: quantized model in 282.367s
chaiml-cai-synth-v4-cosine-v4-mkmlizer: Processed model ChaiML/cai-synth-v4_cosine in 326.812s
chaiml-cai-synth-v4-cosine-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-synth-v4-cosine-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia
chaiml-cai-synth-v4-cosine-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia/config.json
chaiml-cai-synth-v4-cosine-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia/special_tokens_map.json
chaiml-cai-synth-v4-cosine-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia/tokenizer_config.json
chaiml-cai-synth-v4-cosine-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia/tokenizer.json
chaiml-cai-synth-v4-cosine-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia/flywheel_model.1.safetensors
chaiml-cai-synth-v4-cosine-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-synth-v4-cosine-v4-mkmlizer completed after 378.32s with status: succeeded
Stopping job with name chaiml-cai-synth-v4-cosine-v4-mkmlizer
Pipeline stage MKMLizer completed in 378.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-synth-v4-cosine-v4
Waiting for inference service chaiml-cai-synth-v4-cosine-v4 to be ready
Inference service chaiml-cai-synth-v4-cosine-v4 ready after 190.71226286888123s
Pipeline stage MKMLDeployer completed in 191.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2611982822418213s
Received healthy response to inference request in 2.551464080810547s
Received healthy response to inference request in 2.273496389389038s
Received healthy response to inference request in 2.2285122871398926s
Received healthy response to inference request in 1.9504601955413818s
5 requests
0 failed requests
5th percentile: 2.006070613861084
10th percentile: 2.061681032180786
20th percentile: 2.1729018688201904
30th percentile: 2.2350494861602783
40th percentile: 2.24812388420105
50th percentile: 2.2611982822418213
60th percentile: 2.266117525100708
70th percentile: 2.2710367679595946
80th percentile: 2.32908992767334
90th percentile: 2.4402770042419433
95th percentile: 2.495870542526245
99th percentile: 2.5403453731536865
mean time: 2.253026247024536
Pipeline stage StressChecker completed in 12.66s
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 0.96s
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-cosine_v4 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 2490.91s
Shutdown handler de-registered
chaiml-cai-synth-v4-cosine_v4 status is now torndown due to DeploymentManager action