developer_uid: zonemercy
submission_id: chaiml-cai-synth-v4-cosine_v2
model_name: test
model_group: ChaiML/cai-synth-v4_cosi
status: inactive
timestamp: 2025-12-05T06:17:07+00:00
num_battles: 11035
num_wins: 5798
celo_rating: 1255.85
family_friendly_score: 0.5684
family_friendly_standard_error: 0.007004590494811242
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: 128
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.268576572233111, 'latency_mean': 3.7232523381710054, 'latency_p50': 3.737007737159729, 'latency_p90': 3.911538505554199}, {'batch_size': 2, 'throughput': 0.4415391928522609, 'latency_mean': 4.5217377066612245, 'latency_p50': 4.504798531532288, 'latency_p90': 4.769924211502075}, {'batch_size': 3, 'throughput': 0.5595836338311903, 'latency_mean': 5.340840090513229, 'latency_p50': 5.331928849220276, 'latency_p90': 5.783322238922119}, {'batch_size': 5, 'throughput': 0.7068239822602129, 'latency_mean': 7.049081385135651, 'latency_p50': 7.0508506298065186, 'latency_p90': 7.643860459327698}]
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
us_pacific_date: 2025-12-04
win_ratio: 0.5254191209787041
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': 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-cosine-v2-mkmlizer
Waiting for job on chaiml-cai-synth-v4-cosine-v2-mkmlizer to finish
chaiml-cai-synth-v4-cosine-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-cai-synth-v4-cosine-v2-mkmlizer: bash: no job control in this shell
chaiml-cai-synth-v4-cosine-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-cosine-v2-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ║                                                                     ║
chaiml-cai-synth-v4-cosine-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-synth-v4-cosine-v2-mkmlizer: Downloaded to shared memory in 46.111s
chaiml-cai-synth-v4-cosine-v2-mkmlizer: Checking if ChaiML/cai-synth-v4_cosine already exists in ChaiML
chaiml-cai-synth-v4-cosine-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpop9m50a0, device:0
chaiml-cai-synth-v4-cosine-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-synth-v4-cosine-v2-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:21, 1.37it/s]
Loading 0:   1%|          | 3.00/363 [00:02<04:21, 1.37it/s]
Loading 0:   1%|          | 4.00/363 [00:04<07:02, 1.18s/it]
Loading 0:   1%|          | 4.00/363 [00:04<07:02, 1.18s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<09:04, 1.52s/it]
Loading 0:   1%|▏         | 5.00/363 [00:06<09:04, 1.52s/it]
Loading 0:   3%|▎         | 12.0/363 [00:09<04:01, 1.45it/s]
Loading 0:   3%|▎         | 12.0/363 [00:09<04:01, 1.45it/s]
Loading 0:   4%|▎         | 13.0/363 [00:11<05:08, 1.14it/s]
Loading 0:   4%|▎         | 13.0/363 [00:11<05:08, 1.14it/s]
Loading 0:   4%|▍         | 14.0/363 [00:13<06:23, 1.10s/it]
Loading 0:   4%|▍         | 14.0/363 [00:13<06:23, 1.10s/it]
Loading 0:   6%|▌         | 21.0/363 [00:16<03:51, 1.48it/s]
Loading 0:   6%|▌         | 21.0/363 [00:16<03:51, 1.48it/s]
Loading 0:   6%|▌         | 22.0/363 [00:18<04:46, 1.19it/s]
Loading 0:   6%|▌         | 22.0/363 [00:18<04:46, 1.19it/s]
Loading 0:   6%|▋         | 23.0/363 [00:21<05:51, 1.03s/it]
Loading 0:   6%|▋         | 23.0/363 [00:21<05:51, 1.03s/it]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:54, 1.91it/s]
Loading 0:   8%|▊         | 30.0/363 [00:22<02:54, 1.91it/s]
Loading 0:   9%|▉         | 34.0/363 [00:25<03:10, 1.73it/s]
Loading 0:   9%|▉         | 34.0/363 [00:25<03:10, 1.73it/s]
Loading 0:  10%|▉         | 35.0/363 [00:27<04:01, 1.36it/s]
Loading 0:  10%|▉         | 35.0/363 [00:27<04:01, 1.36it/s]
Loading 0:  10%|▉         | 36.0/363 [00:29<05:04, 1.07it/s]
Loading 0:  10%|▉         | 36.0/363 [00:29<05:04, 1.07it/s]
Loading 0:  11%|█         | 39.0/363 [00:31<04:36, 1.17it/s]
Loading 0:  11%|█         | 39.0/363 [00:31<04:36, 1.17it/s]
Loading 0:  11%|█         | 40.0/363 [00:33<05:35, 1.04s/it]
Loading 0:  11%|█         | 40.0/363 [00:33<05:35, 1.04s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:35<06:42, 1.25s/it]
Loading 0:  11%|█▏        | 41.0/363 [00:35<06:42, 1.25s/it]
Loading 0:  13%|█▎        | 48.0/363 [00:38<03:47, 1.39it/s]
Loading 0:  13%|█▎        | 48.0/363 [00:38<03:47, 1.39it/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<03:30, 1.45it/s]
Loading 0:  16%|█▌        | 57.0/363 [00:46<03:30, 1.45it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:48<04:17, 1.19it/s]
Loading 0:  16%|█▌        | 58.0/363 [00:48<04:17, 1.19it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:50<05:12, 1.03s/it]
Loading 0:  16%|█▋        | 59.0/363 [00:50<05:12, 1.03s/it]
Loading 0:  18%|█▊        | 65.0/363 [00:53<03:40, 1.35it/s]
Loading 0:  18%|█▊        | 65.0/363 [00:53<03:40, 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 [00:58<03:48, 1.28it/s]
Loading 0:  20%|█▉        | 72.0/363 [00:58<03:48, 1.28it/s]
Loading 0:  20%|██        | 73.0/363 [01:00<04:37, 1.05it/s]
Loading 0:  20%|██        | 73.0/363 [01:00<04:37, 1.05it/s]
Loading 0:  22%|██▏       | 79.0/363 [01:03<03:23, 1.39it/s]
Loading 0:  22%|██▏       | 79.0/363 [01:03<03:23, 1.39it/s]
Loading 0:  22%|██▏       | 80.0/363 [01:06<04:08, 1.14it/s]
Loading 0:  22%|██▏       | 80.0/363 [01:06<04:08, 1.14it/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<03:56, 1.17it/s]
Loading 0:  24%|██▍       | 87.0/363 [01:11<03:56, 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 [01:17<05:17, 1.17s/it]
Loading 0:  25%|██▌       | 92.0/363 [01:17<05:17, 1.17s/it]
Loading 0:  27%|██▋       | 99.0/363 [01:20<03:08, 1.40it/s]
Loading 0:  27%|██▋       | 99.0/363 [01:20<03:08, 1.40it/s]
Loading 0:  28%|██▊       | 100/363 [01:22<03:48, 1.15it/s] 
Loading 0:  28%|██▊       | 100/363 [01:22<03:48, 1.15it/s]
Loading 0:  28%|██▊       | 101/363 [01:25<04:37, 1.06s/it]
Loading 0:  28%|██▊       | 101/363 [01:25<04:37, 1.06s/it]
Loading 0:  30%|██▉       | 108/363 [01:28<03:00, 1.42it/s]
Loading 0:  30%|██▉       | 108/363 [01:28<03:00, 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<03:36, 1.16it/s]
Loading 0:  31%|███       | 112/363 [01:32<03:36, 1.16it/s]
Loading 0:  31%|███       | 113/363 [01:34<04:23, 1.05s/it]
Loading 0:  31%|███       | 113/363 [01:34<04:23, 1.05s/it]
Loading 0:  33%|███▎      | 120/363 [01:37<02:46, 1.46it/s]
Loading 0:  33%|███▎      | 120/363 [01:37<02:46, 1.46it/s]
Loading 0:  33%|███▎      | 121/363 [01:39<03:22, 1.19it/s]
Loading 0:  33%|███▎      | 121/363 [01:39<03:22, 1.19it/s]
Loading 0:  34%|███▎      | 122/363 [01:42<04:06, 1.02s/it]
Loading 0:  34%|███▎      | 122/363 [01:42<04:06, 1.02s/it]
Loading 0:  36%|███▌      | 129/363 [01:44<02:38, 1.48it/s]
Loading 0:  36%|███▌      | 129/363 [01:44<02:38, 1.48it/s]
Loading 0:  36%|███▌      | 130/363 [01:47<03:12, 1.21it/s]
Loading 0:  36%|███▌      | 130/363 [01:47<03:12, 1.21it/s]
Loading 0:  36%|███▌      | 131/363 [01:49<03:53, 1.01s/it]
Loading 0:  36%|███▌      | 131/363 [01:49<03:53, 1.01s/it]
Loading 0:  38%|███▊      | 138/363 [01:52<02:31, 1.49it/s]
Loading 0:  38%|███▊      | 138/363 [01:52<02:31, 1.49it/s]
Loading 0:  38%|███▊      | 139/363 [01:54<03:04, 1.22it/s]
Loading 0:  38%|███▊      | 139/363 [01:54<03:04, 1.22it/s]
Loading 0:  39%|███▊      | 140/363 [01:56<03:44, 1.01s/it]
Loading 0:  39%|███▊      | 140/363 [01:56<03:44, 1.01s/it]
Loading 0:  40%|████      | 147/363 [01:57<01:53, 1.90it/s]
Loading 0:  40%|████      | 147/363 [01:57<01:53, 1.90it/s]
Loading 0:  42%|████▏     | 151/363 [02:00<02:02, 1.74it/s]
Loading 0:  42%|████▏     | 151/363 [02:00<02:02, 1.74it/s]
Loading 0:  42%|████▏     | 152/363 [02:02<02:34, 1.36it/s]
Loading 0:  42%|████▏     | 152/363 [02:02<02:34, 1.36it/s]
Loading 0:  42%|████▏     | 153/363 [02:04<03:14, 1.08it/s]
Loading 0:  42%|████▏     | 153/363 [02:04<03:14, 1.08it/s]
Loading 0:  43%|████▎     | 156/363 [02:06<02:55, 1.18it/s]
Loading 0:  43%|████▎     | 156/363 [02:06<02:55, 1.18it/s]
Loading 0:  43%|████▎     | 157/363 [02:08<03:32, 1.03s/it]
Loading 0:  43%|████▎     | 157/363 [02:08<03:32, 1.03s/it]
Loading 0:  44%|████▎     | 158/363 [02:11<04:15, 1.24s/it]
Loading 0:  44%|████▎     | 158/363 [02:11<04:15, 1.24s/it]
Loading 0:  45%|████▌     | 165/363 [02:14<02:22, 1.39it/s]
Loading 0:  45%|████▌     | 165/363 [02:14<02:22, 1.39it/s]
Loading 0:  46%|████▌     | 166/363 [02:16<02:53, 1.14it/s]
Loading 0:  46%|████▌     | 166/363 [02:16<02:53, 1.14it/s]
Loading 0:  46%|████▌     | 167/363 [02:18<03:30, 1.07s/it]
Loading 0:  46%|████▌     | 167/363 [02:18<03:30, 1.07s/it]
Loading 0:  48%|████▊     | 174/363 [02:21<02:09, 1.46it/s]
Loading 0:  48%|████▊     | 174/363 [02:21<02:09, 1.46it/s]
Loading 0:  48%|████▊     | 175/363 [02:23<02:37, 1.19it/s]
Loading 0:  48%|████▊     | 175/363 [02:23<02:37, 1.19it/s]
Loading 0:  48%|████▊     | 176/363 [02:25<03:11, 1.03s/it]
Loading 0:  48%|████▊     | 176/363 [02:25<03:11, 1.03s/it]
Loading 0:  50%|█████     | 182/363 [02:28<02:13, 1.35it/s]
Loading 0:  50%|█████     | 182/363 [02:28<02:13, 1.35it/s]
Loading 0:  52%|█████▏    | 188/363 [02:31<01:53, 1.54it/s]
Loading 0:  52%|█████▏    | 188/363 [02:31<01:53, 1.54it/s]
Loading 0:  52%|█████▏    | 189/363 [02:34<02:18, 1.26it/s]
Loading 0:  52%|█████▏    | 189/363 [02:34<02:18, 1.26it/s]
Loading 0:  53%|█████▎    | 192/363 [02:36<02:11, 1.30it/s]
Loading 0:  53%|█████▎    | 192/363 [02:36<02:11, 1.30it/s]
Loading 0:  53%|█████▎    | 193/363 [02:38<02:38, 1.07it/s]
Loading 0:  53%|█████▎    | 193/363 [02:38<02:38, 1.07it/s]
Loading 0:  53%|█████▎    | 194/363 [02:40<03:12, 1.14s/it]
Loading 0:  53%|█████▎    | 194/363 [02:40<03:12, 1.14s/it]
Loading 0:  55%|█████▌    | 201/363 [02:43<01:54, 1.42it/s]
Loading 0:  55%|█████▌    | 201/363 [02:43<01:54, 1.42it/s]
Loading 0:  56%|█████▌    | 202/363 [02:45<02:18, 1.17it/s]
Loading 0:  56%|█████▌    | 202/363 [02:45<02:18, 1.17it/s]
Loading 0:  56%|█████▌    | 203/363 [02:47<02:46, 1.04s/it]
Loading 0:  56%|█████▌    | 203/363 [02:47<02:46, 1.04s/it]
Loading 0:  58%|█████▊    | 210/363 [02:50<01:43, 1.47it/s]
Loading 0:  58%|█████▊    | 210/363 [02:50<01:43, 1.47it/s]
Loading 0:  58%|█████▊    | 211/363 [02:52<02:06, 1.21it/s]
Loading 0:  58%|█████▊    | 211/363 [02:52<02:06, 1.21it/s]
Loading 0:  58%|█████▊    | 212/363 [02:55<02:33, 1.01s/it]
Loading 0:  58%|█████▊    | 212/363 [02:55<02:33, 1.01s/it]
Loading 0:  60%|██████    | 218/363 [02:57<01:46, 1.37it/s]
Loading 0:  60%|██████    | 218/363 [02:57<01:46, 1.37it/s]
Loading 0:  60%|██████    | 219/363 [03:00<02:09, 1.11it/s]
Loading 0:  60%|██████    | 219/363 [03:00<02:09, 1.11it/s]
Loading 0:  62%|██████▏   | 225/363 [03:03<01:38, 1.41it/s]
Loading 0:  62%|██████▏   | 225/363 [03:03<01:38, 1.41it/s]
Loading 0:  63%|██████▎   | 228/363 [03:05<01:35, 1.41it/s]
Loading 0:  63%|██████▎   | 228/363 [03:05<01:35, 1.41it/s]
Loading 0:  63%|██████▎   | 229/363 [03:07<01:55, 1.16it/s]
Loading 0:  63%|██████▎   | 229/363 [03:07<01:55, 1.16it/s]
Loading 0:  63%|██████▎   | 230/363 [03:09<02:19, 1.05s/it]
Loading 0:  63%|██████▎   | 230/363 [03:09<02:19, 1.05s/it]
Loading 0:  65%|██████▌   | 237/363 [03:12<01:26, 1.46it/s]
Loading 0:  65%|██████▌   | 237/363 [03:12<01:26, 1.46it/s]
Loading 0:  66%|██████▌   | 238/363 [03:14<01:44, 1.20it/s]
Loading 0:  66%|██████▌   | 238/363 [03:14<01:44, 1.20it/s]
Loading 0:  66%|██████▌   | 239/363 [03:17<02:05, 1.02s/it]
Loading 0:  66%|██████▌   | 239/363 [03:17<02:05, 1.02s/it]
Loading 0:  68%|██████▊   | 246/363 [03:19<01:18, 1.49it/s]
Loading 0:  68%|██████▊   | 246/363 [03:19<01:18, 1.49it/s]
Loading 0:  68%|██████▊   | 247/363 [03:21<01:35, 1.22it/s]
Loading 0:  68%|██████▊   | 247/363 [03:21<01:35, 1.22it/s]
Loading 0:  68%|██████▊   | 248/363 [03:24<01:55, 1.00s/it]
Loading 0:  68%|██████▊   | 248/363 [03:24<01:55, 1.00s/it]
Loading 0:  70%|███████   | 255/363 [03:27<01:12, 1.49it/s]
Loading 0:  70%|███████   | 255/363 [03:27<01:12, 1.49it/s]
Loading 0:  71%|███████   | 256/363 [03:29<01:27, 1.22it/s]
Loading 0:  71%|███████   | 256/363 [03:29<01:27, 1.22it/s]
Loading 0:  71%|███████   | 257/363 [03:31<01:46, 1.00s/it]
Loading 0:  71%|███████   | 257/363 [03:31<01:46, 1.00s/it]
Loading 0:  73%|███████▎  | 264/363 [03:32<00:52, 1.89it/s]
Loading 0:  73%|███████▎  | 264/363 [03:32<00:52, 1.89it/s]
Loading 0:  74%|███████▍  | 268/363 [03:35<00:54, 1.73it/s]
Loading 0:  74%|███████▍  | 268/363 [03:35<00:54, 1.73it/s]
Loading 0:  74%|███████▍  | 269/363 [03:37<01:08, 1.36it/s]
Loading 0:  74%|███████▍  | 269/363 [03:37<01:08, 1.36it/s]
Loading 0:  74%|███████▍  | 270/363 [03:39<01:25, 1.08it/s]
Loading 0:  74%|███████▍  | 270/363 [03:39<01:25, 1.08it/s]
Loading 0:  75%|███████▌  | 273/363 [03:56<03:47, 2.53s/it]
Loading 0:  75%|███████▌  | 273/363 [03:56<03:47, 2.53s/it]
Loading 0:  75%|███████▌  | 274/363 [03:58<03:39, 2.47s/it]
Loading 0:  75%|███████▌  | 274/363 [03:58<03:39, 2.47s/it]
Loading 0:  76%|███████▌  | 275/363 [04:00<03:34, 2.43s/it]
Loading 0:  76%|███████▌  | 275/363 [04:00<03:34, 2.43s/it]
Loading 0:  78%|███████▊  | 282/363 [04:03<01:35, 1.18s/it]
Loading 0:  78%|███████▊  | 282/363 [04:03<01:35, 1.18s/it]
Loading 0:  78%|███████▊  | 283/363 [04:05<01:42, 1.28s/it]
Loading 0:  78%|███████▊  | 283/363 [04:05<01:42, 1.28s/it]
Loading 0:  78%|███████▊  | 284/363 [04:07<01:51, 1.42s/it]
Loading 0:  78%|███████▊  | 284/363 [04:07<01:51, 1.42s/it]
Loading 0:  80%|████████  | 291/363 [04:10<00:58, 1.23it/s]
Loading 0:  80%|████████  | 291/363 [04:10<00:58, 1.23it/s]
Loading 0:  80%|████████  | 292/363 [04:12<01:07, 1.05it/s]
Loading 0:  80%|████████  | 292/363 [04:12<01:07, 1.05it/s]
Loading 0:  81%|████████  | 293/363 [04:15<01:18, 1.12s/it]
Loading 0:  81%|████████  | 293/363 [04:15<01:18, 1.12s/it]
Loading 0:  82%|████████▏ | 299/363 [04:17<00:49, 1.30it/s]
Loading 0:  82%|████████▏ | 299/363 [04:17<00:49, 1.30it/s]
Loading 0:  84%|████████▍ | 305/363 [04:20<00:37, 1.53it/s]
Loading 0:  84%|████████▍ | 305/363 [04:20<00:37, 1.53it/s]
Loading 0:  84%|████████▍ | 306/363 [04:23<00:45, 1.25it/s]
Loading 0:  84%|████████▍ | 306/363 [04:23<00:45, 1.25it/s]
Loading 0:  85%|████████▌ | 309/363 [04:25<00:41, 1.29it/s]
Loading 0:  85%|████████▌ | 309/363 [04:25<00:41, 1.29it/s]
Loading 0:  85%|████████▌ | 310/363 [04:27<00:49, 1.07it/s]
Loading 0:  85%|████████▌ | 310/363 [04:27<00:49, 1.07it/s]
Loading 0:  86%|████████▌ | 311/363 [04:29<00:58, 1.13s/it]
Loading 0:  86%|████████▌ | 311/363 [04:29<00:58, 1.13s/it]
Loading 0:  87%|████████▋ | 316/363 [04:30<00:30, 1.52it/s]
Loading 0:  87%|████████▋ | 316/363 [04:30<00:30, 1.52it/s]
Loading 0:  88%|████████▊ | 318/363 [04:32<00:33, 1.33it/s]
Loading 0:  88%|████████▊ | 318/363 [04:32<00:33, 1.33it/s]
Loading 0:  88%|████████▊ | 319/363 [04:34<00:41, 1.06it/s]
Loading 0:  88%|████████▊ | 319/363 [04:34<00:41, 1.06it/s]
Loading 0:  88%|████████▊ | 320/363 [04:37<00:49, 1.16s/it]
Loading 0:  88%|████████▊ | 320/363 [04:37<00:49, 1.16s/it]
Loading 0:  90%|█████████ | 327/363 [04:39<00:24, 1.47it/s]
Loading 0:  90%|█████████ | 327/363 [04:39<00:24, 1.47it/s]
Loading 0:  90%|█████████ | 328/363 [04:41<00:29, 1.19it/s]
Loading 0:  90%|█████████ | 328/363 [04:41<00:29, 1.19it/s]
Loading 0:  91%|█████████ | 329/363 [04:44<00:35, 1.04s/it]
Loading 0:  91%|█████████ | 329/363 [04:44<00:35, 1.04s/it]
Loading 0:  92%|█████████▏| 335/363 [04:47<00:20, 1.35it/s]
Loading 0:  92%|█████████▏| 335/363 [04:47<00:20, 1.35it/s]
Loading 0:  93%|█████████▎| 336/363 [04:49<00:25, 1.08it/s]
Loading 0:  93%|█████████▎| 336/363 [04:49<00:25, 1.08it/s]
Loading 0:  94%|█████████▍| 341/363 [04:50<00:13, 1.65it/s]
Loading 0:  94%|█████████▍| 341/363 [04:50<00:13, 1.65it/s]
Loading 0:  94%|█████████▍| 343/363 [04:52<00:14, 1.41it/s]
Loading 0:  94%|█████████▍| 343/363 [04:52<00:14, 1.41it/s]
Loading 0:  95%|█████████▌| 346/363 [04:55<00:12, 1.39it/s]
Loading 0:  95%|█████████▌| 346/363 [04:55<00:12, 1.39it/s]
Loading 0:  96%|█████████▌| 347/363 [04:57<00:14, 1.10it/s]
Loading 0:  96%|█████████▌| 347/363 [04:57<00:14, 1.10it/s]
Loading 0:  96%|█████████▌| 348/363 [04:59<00:16, 1.13s/it]
Loading 0:  96%|█████████▌| 348/363 [04:59<00:16, 1.13s/it]
Loading 0:  98%|█████████▊| 355/363 [05:02<00:05, 1.42it/s]
Loading 0:  98%|█████████▊| 355/363 [05:02<00:05, 1.42it/s]
Loading 0:  98%|█████████▊| 356/363 [05:04<00:06, 1.15it/s]
Loading 0:  98%|█████████▊| 356/363 [05:04<00:06, 1.15it/s]
Loading 0:  98%|█████████▊| 357/363 [05:07<00:06, 1.07s/it]
Loading 0:  98%|█████████▊| 357/363 [05:07<00:06, 1.07s/it]
Loading 0: 100%|██████████| 363/363 [05:07<00:00, 1.76it/s]
Loading 0: 100%|██████████| 363/363 [05:07<00:00, 1.76it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [05:07<00:00, 1.18it/s]
chaiml-cai-synth-v4-cosine-v2-mkmlizer: The tokenizer you are loading from '/tmp/tmpop9m50a0' 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-v2-mkmlizer: quantized model in 315.583s
chaiml-cai-synth-v4-cosine-v2-mkmlizer: Processed model ChaiML/cai-synth-v4_cosine in 361.695s
chaiml-cai-synth-v4-cosine-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-synth-v4-cosine-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-synth-v4-cosine-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia
chaiml-cai-synth-v4-cosine-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia/config.json
chaiml-cai-synth-v4-cosine-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia/special_tokens_map.json
chaiml-cai-synth-v4-cosine-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia/tokenizer_config.json
chaiml-cai-synth-v4-cosine-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia/tokenizer.json
chaiml-cai-synth-v4-cosine-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia/flywheel_model.1.safetensors
chaiml-cai-synth-v4-cosine-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-synth-v4-cosine-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-cai-synth-v4-cosine-v2-mkmlizer completed after 438.09s with status: succeeded
Stopping job with name chaiml-cai-synth-v4-cosine-v2-mkmlizer
Pipeline stage MKMLizer completed in 438.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-synth-v4-cosine-v2
Waiting for inference service chaiml-cai-synth-v4-cosine-v2 to be ready
Inference service chaiml-cai-synth-v4-cosine-v2 ready after 190.80899810791016s
Pipeline stage MKMLDeployer completed in 191.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.660792827606201s
Received healthy response to inference request in 3.9731199741363525s
Received healthy response to inference request in 3.2786731719970703s
Received healthy response to inference request in 3.4913671016693115s
Received healthy response to inference request in 3.863978147506714s
5 requests
0 failed requests
5th percentile: 3.3212119579315185
10th percentile: 3.3637507438659666
20th percentile: 3.4488283157348634
30th percentile: 3.5252522468566894
40th percentile: 3.5930225372314455
50th percentile: 3.660792827606201
60th percentile: 3.7420669555664063
70th percentile: 3.8233410835266115
80th percentile: 3.885806512832642
90th percentile: 3.929463243484497
95th percentile: 3.9512916088104246
99th percentile: 3.968754301071167
mean time: 3.65358624458313
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 0.63s
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 0.69s
Shutdown handler de-registered
chaiml-cai-synth-v4-cosine_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 3228.87s
Shutdown handler de-registered
chaiml-cai-synth-v4-cosine_v2 status is now inactive due to auto deactivation removed underperforming models