chaiml-cai-real-v3-cosine

developer_uid: zonemercy
submission_id: chaiml-cai-real-v3-cosine_v3
model_name: test
model_group: ChaiML/cai-real-v3_cosin
status: torndown
timestamp: 2025-11-23T02:51:19+00:00
num_battles: 5599
num_wins: 3380
celo_rating: 1363.6
family_friendly_score: 0.48419999999999996
family_friendly_standard_error: 0.007067536487348332
submission_type: basic
model_repo: ChaiML/cai-real-v3_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': 0.2764045824799399, 'latency_mean': 3.617763124704361, 'latency_p50': 3.6261990070343018, 'latency_p90': 3.8206523180007936}, {'batch_size': 2, 'throughput': 0.45595803460741446, 'latency_mean': 4.384487063884735, 'latency_p50': 4.359643816947937, 'latency_p90': 4.658225631713867}, {'batch_size': 3, 'throughput': 0.5849820042298386, 'latency_mean': 5.127179476022721, 'latency_p50': 5.120498418807983, 'latency_p90': 5.417477869987488}, {'batch_size': 5, 'throughput': 0.7368453834077212, 'latency_mean': 6.7631301653385165, 'latency_p50': 6.765219211578369, 'latency_p90': 7.336359715461731}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/cai-real-v3_cosine
model_size: 24B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-11-19
win_ratio: 0.6036792284336489
generation_params: {'temperature': 0.3, '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': 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-real-v3-cosine-v3-mkmlizer
Waiting for job on chaiml-cai-real-v3-cosine-v3-mkmlizer to finish
chaiml-cai-real-v3-cosine-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-real-v3-cosine-v3-mkmlizer: Downloaded to shared memory in 64.122s
chaiml-cai-real-v3-cosine-v3-mkmlizer: Checking if ChaiML/cai-real-v3_cosine already exists in ChaiML
chaiml-cai-real-v3-cosine-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp60_rek78, device:0
chaiml-cai-real-v3-cosine-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
chaiml-cai-real-v3-cosine-v3-mkmlizer: quantized model in 312.531s
chaiml-cai-real-v3-cosine-v3-mkmlizer: Processed model ChaiML/cai-real-v3_cosine in 376.654s
chaiml-cai-real-v3-cosine-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-real-v3-cosine-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-real-v3-cosine-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia
chaiml-cai-real-v3-cosine-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia/config.json
chaiml-cai-real-v3-cosine-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia/special_tokens_map.json
chaiml-cai-real-v3-cosine-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia/tokenizer_config.json
chaiml-cai-real-v3-cosine-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia/tokenizer.json
chaiml-cai-real-v3-cosine-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia/flywheel_model.1.safetensors
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-cai-real-v3-cosine-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v3/nvidia/flywheel_model.0.safetensors
chaiml-cai-real-v3-cosine-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:02<04:21,  1.38it/s]
Loading 0:   1%|          | 4/363 [00:04<07:05,  1.18s/it]
Loading 0:   1%|▏         | 5/363 [00:06<09:02,  1.52s/it]
Loading 0:   2%|▏         | 8/363 [00:06<04:12,  1.41it/s]
Loading 0:   2%|▏         | 9/363 [00:07<03:41,  1.60it/s]
Loading 0:   3%|▎         | 10/363 [00:07<02:59,  1.96it/s]
Loading 0:   3%|▎         | 12/363 [00:09<04:18,  1.36it/s]
Loading 0:   4%|▎         | 13/363 [00:11<06:07,  1.05s/it]
Loading 0:   4%|▍         | 14/363 [00:13<07:45,  1.33s/it]
Loading 0:   5%|▍         | 17/363 [00:14<04:06,  1.40it/s]
Loading 0:   5%|▍         | 18/363 [00:14<03:36,  1.59it/s]
Loading 0:   5%|▌         | 19/363 [00:14<02:58,  1.93it/s]
Loading 0:   6%|▌         | 21/363 [00:16<04:10,  1.36it/s]
Loading 0:   6%|▌         | 22/363 [00:18<05:53,  1.04s/it]
Loading 0:   6%|▋         | 23/363 [00:21<07:27,  1.32s/it]
Loading 0:   7%|▋         | 26/363 [00:21<03:59,  1.40it/s]
Loading 0:   7%|▋         | 27/363 [00:21<03:30,  1.59it/s]
Loading 0:   8%|▊         | 28/363 [00:21<02:53,  1.93it/s]
Loading 0:   8%|▊         | 30/363 [00:22<02:08,  2.60it/s]
Loading 0:   9%|▊         | 31/363 [00:22<01:59,  2.77it/s]
Loading 0:   9%|▉         | 32/363 [00:22<01:42,  3.22it/s]
Loading 0:   9%|▉         | 33/363 [00:22<01:28,  3.72it/s]
Loading 0:   9%|▉         | 34/363 [00:24<04:11,  1.31it/s]
Loading 0:  10%|▉         | 35/363 [00:27<06:14,  1.14s/it]
Loading 0:  10%|▉         | 36/363 [00:29<07:53,  1.45s/it]
Loading 0:  11%|█         | 39/363 [00:31<05:39,  1.05s/it]
Loading 0:  11%|█         | 40/363 [00:33<06:52,  1.28s/it]
Loading 0:  11%|█▏        | 41/363 [00:35<08:01,  1.49s/it]
Loading 0:  12%|█▏        | 44/363 [00:36<04:19,  1.23it/s]
Loading 0:  12%|█▏        | 45/363 [00:36<03:45,  1.41it/s]
Loading 0:  13%|█▎        | 46/363 [00:36<03:06,  1.70it/s]
Loading 0:  13%|█▎        | 48/363 [00:38<04:03,  1.30it/s]
Loading 0:  13%|█▎        | 49/363 [00:40<05:34,  1.06s/it]
Loading 0:  14%|█▍        | 50/363 [00:43<06:57,  1.34s/it]
Loading 0:  15%|█▍        | 53/363 [00:43<03:44,  1.38it/s]
Loading 0:  15%|█▍        | 54/363 [00:43<03:16,  1.57it/s]
Loading 0:  15%|█▌        | 55/363 [00:43<02:42,  1.90it/s]
Loading 0:  16%|█▌        | 57/363 [00:45<03:45,  1.36it/s]
Loading 0:  16%|█▌        | 58/363 [00:48<05:16,  1.04s/it]
Loading 0:  16%|█▋        | 59/363 [00:50<06:39,  1.32s/it]
Loading 0:  17%|█▋        | 62/363 [00:50<03:33,  1.41it/s]
Loading 0:  17%|█▋        | 63/363 [00:50<03:07,  1.60it/s]
Loading 0:  18%|█▊        | 64/363 [00:51<02:34,  1.93it/s]
Loading 0:  18%|█▊        | 65/363 [00:53<04:28,  1.11it/s]
Loading 0:  18%|█▊        | 67/363 [00:53<02:58,  1.65it/s]
Loading 0:  19%|█▊        | 68/363 [00:53<02:36,  1.89it/s]
Loading 0:  19%|█▉        | 69/363 [00:53<02:08,  2.30it/s]
Loading 0:  19%|█▉        | 70/363 [00:54<01:45,  2.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:56<04:04,  1.19it/s]
Loading 0:  20%|█▉        | 72/363 [00:58<05:49,  1.20s/it]
Loading 0:  20%|██        | 73/363 [01:00<07:12,  1.49s/it]
Loading 0:  21%|██        | 76/363 [01:00<03:30,  1.36it/s]
Loading 0:  21%|██        | 77/363 [01:01<03:02,  1.57it/s]
Loading 0:  21%|██▏       | 78/363 [01:01<02:29,  1.90it/s]
Loading 0:  22%|██▏       | 79/363 [01:03<04:22,  1.08it/s]
Loading 0:  22%|██▏       | 80/363 [01:05<05:57,  1.26s/it]
Loading 0:  23%|██▎       | 82/363 [01:06<03:43,  1.26it/s]
Loading 0:  23%|██▎       | 83/363 [01:06<03:08,  1.49it/s]
Loading 0:  23%|██▎       | 84/363 [01:06<02:31,  1.85it/s]
Loading 0:  24%|██▎       | 86/363 [01:08<03:32,  1.30it/s]
Loading 0:  24%|██▍       | 87/363 [01:10<05:03,  1.10s/it]
Loading 0:  25%|██▍       | 90/363 [01:13<04:08,  1.10it/s]
Loading 0:  25%|██▌       | 91/363 [01:15<05:11,  1.15s/it]
Loading 0:  25%|██▌       | 92/363 [01:17<06:13,  1.38s/it]
Loading 0:  26%|██▌       | 95/363 [01:17<03:26,  1.30it/s]
Loading 0:  26%|██▋       | 96/363 [01:17<03:00,  1.48it/s]
Loading 0:  27%|██▋       | 97/363 [01:18<02:31,  1.75it/s]
Loading 0:  27%|██▋       | 99/363 [01:20<03:24,  1.29it/s]
Loading 0:  28%|██▊       | 100/363 [01:22<04:39,  1.06s/it]
Loading 0:  28%|██▊       | 101/363 [01:24<05:49,  1.34s/it]
Loading 0:  29%|██▊       | 104/363 [01:25<03:07,  1.38it/s]
Loading 0:  29%|██▉       | 105/363 [01:25<02:44,  1.57it/s]
Loading 0:  29%|██▉       | 106/363 [01:25<02:15,  1.89it/s]
Loading 0:  29%|██▉       | 107/363 [01:25<01:52,  2.28it/s]
Loading 0:  30%|██▉       | 108/363 [01:27<03:41,  1.15it/s]
Loading 0:  31%|███       | 111/363 [01:29<03:19,  1.26it/s]
Loading 0:  31%|███       | 112/363 [01:32<04:26,  1.06s/it]
Loading 0:  31%|███       | 113/363 [01:34<05:29,  1.32s/it]
Loading 0:  32%|███▏      | 116/363 [01:34<03:00,  1.37it/s]
Loading 0:  32%|███▏      | 117/363 [01:34<02:38,  1.55it/s]
Loading 0:  33%|███▎      | 118/363 [01:35<02:11,  1.86it/s]
Loading 0:  33%|███▎      | 120/363 [01:37<03:00,  1.35it/s]
Loading 0:  33%|███▎      | 121/363 [01:39<04:12,  1.04s/it]
Loading 0:  34%|███▎      | 122/363 [01:41<05:17,  1.32s/it]
Loading 0:  34%|███▍      | 125/363 [01:41<02:50,  1.40it/s]
Loading 0:  35%|███▍      | 126/363 [01:42<02:29,  1.59it/s]
Loading 0:  35%|███▍      | 127/363 [01:42<02:03,  1.91it/s]
Loading 0:  36%|███▌      | 129/363 [01:44<02:52,  1.36it/s]
Loading 0:  36%|███▌      | 130/363 [01:46<04:02,  1.04s/it]
Loading 0:  36%|███▌      | 131/363 [01:48<05:06,  1.32s/it]
Loading 0:  37%|███▋      | 134/363 [01:49<02:43,  1.40it/s]
Loading 0:  37%|███▋      | 135/363 [01:49<02:23,  1.59it/s]
Loading 0:  37%|███▋      | 136/363 [01:49<01:58,  1.91it/s]
Loading 0:  38%|███▊      | 138/363 [01:51<02:45,  1.36it/s]
Loading 0:  38%|███▊      | 139/363 [01:53<03:52,  1.04s/it]
Loading 0:  39%|███▊      | 140/363 [01:56<04:54,  1.32s/it]
Loading 0:  39%|███▉      | 143/363 [01:56<02:37,  1.40it/s]
Loading 0:  40%|███▉      | 144/363 [01:56<02:17,  1.59it/s]
Loading 0:  40%|███▉      | 145/363 [01:56<01:54,  1.91it/s]
Loading 0:  40%|████      | 147/363 [01:57<01:23,  2.58it/s]
Loading 0:  41%|████      | 148/363 [01:57<01:18,  2.75it/s]
Loading 0:  41%|████      | 149/363 [01:57<01:05,  3.24it/s]
Loading 0:  41%|████▏     | 150/363 [01:57<00:57,  3.67it/s]
Loading 0:  42%|████▏     | 151/363 [02:00<02:43,  1.30it/s]
Loading 0:  42%|████▏     | 152/363 [02:02<04:01,  1.15s/it]
Loading 0:  42%|████▏     | 153/363 [02:04<05:05,  1.45s/it]
Loading 0:  43%|████▎     | 156/363 [02:06<03:37,  1.05s/it]
Loading 0:  43%|████▎     | 157/363 [02:08<04:24,  1.28s/it]
Loading 0:  44%|████▎     | 158/363 [02:10<05:06,  1.50s/it]
Loading 0:  44%|████▍     | 161/363 [02:11<02:44,  1.23it/s]
Loading 0:  45%|████▍     | 162/363 [02:11<02:22,  1.41it/s]
Loading 0:  45%|████▍     | 163/363 [02:11<01:57,  1.71it/s]
Loading 0:  45%|████▌     | 165/363 [02:13<02:33,  1.29it/s]
Loading 0:  46%|████▌     | 166/363 [02:16<03:30,  1.07s/it]
Loading 0:  46%|████▌     | 167/363 [02:18<04:22,  1.34s/it]
Loading 0:  47%|████▋     | 170/363 [02:18<02:20,  1.38it/s]
Loading 0:  47%|████▋     | 171/363 [02:18<02:02,  1.57it/s]
Loading 0:  47%|████▋     | 172/363 [02:18<01:41,  1.88it/s]
Loading 0:  48%|████▊     | 174/363 [02:21<02:19,  1.35it/s]
Loading 0:  48%|████▊     | 175/363 [02:23<03:15,  1.04s/it]
Loading 0:  48%|████▊     | 176/363 [02:25<04:06,  1.32s/it]
Loading 0:  49%|████▉     | 179/363 [02:25<02:11,  1.40it/s]
Loading 0:  50%|████▉     | 180/363 [02:26<01:54,  1.59it/s]
Loading 0:  50%|████▉     | 181/363 [02:26<01:35,  1.91it/s]
Loading 0:  50%|█████     | 182/363 [02:28<02:44,  1.10it/s]
Loading 0:  51%|█████     | 184/363 [02:28<01:48,  1.65it/s]
Loading 0:  51%|█████     | 185/363 [02:28<01:34,  1.88it/s]
Loading 0:  51%|█████     | 186/363 [02:29<01:17,  2.29it/s]
Loading 0:  52%|█████▏    | 187/363 [02:29<01:04,  2.75it/s]
Loading 0:  52%|█████▏    | 188/363 [02:31<02:27,  1.19it/s]
Loading 0:  52%|█████▏    | 189/363 [02:33<03:33,  1.22s/it]
Loading 0:  53%|█████▎    | 192/363 [02:35<02:42,  1.06it/s]
Loading 0:  53%|█████▎    | 193/363 [02:37<03:23,  1.19s/it]
Loading 0:  53%|█████▎    | 194/363 [02:40<04:00,  1.42s/it]
Loading 0:  54%|█████▍    | 197/363 [02:40<02:09,  1.29it/s]
Loading 0:  55%|█████▍    | 198/363 [02:40<01:52,  1.47it/s]
Loading 0:  55%|█████▍    | 199/363 [02:40<01:33,  1.76it/s]
Loading 0:  55%|█████▌    | 201/363 [02:43<02:03,  1.31it/s]
Loading 0:  56%|█████▌    | 202/363 [02:45<02:49,  1.06s/it]
Loading 0:  56%|█████▌    | 203/363 [02:47<03:32,  1.33s/it]
Loading 0:  57%|█████▋    | 206/363 [02:47<01:52,  1.39it/s]
Loading 0:  57%|█████▋    | 207/363 [02:48<01:38,  1.58it/s]
Loading 0:  57%|█████▋    | 208/363 [02:48<01:21,  1.90it/s]
Loading 0:  58%|█████▊    | 210/363 [02:50<01:52,  1.36it/s]
Loading 0:  58%|█████▊    | 211/363 [02:52<02:37,  1.04s/it]
Loading 0:  58%|█████▊    | 212/363 [02:54<03:18,  1.32s/it]
Loading 0:  59%|█████▉    | 215/363 [02:55<01:45,  1.40it/s]
Loading 0:  60%|█████▉    | 216/363 [02:55<01:32,  1.59it/s]
Loading 0:  60%|█████▉    | 217/363 [02:55<01:16,  1.92it/s]
Loading 0:  60%|██████    | 218/363 [02:57<02:11,  1.11it/s]
Loading 0:  60%|██████    | 219/363 [02:59<02:57,  1.24s/it]
Loading 0:  61%|██████    | 221/363 [03:00<01:51,  1.27it/s]
Loading 0:  61%|██████    | 222/363 [03:00<01:34,  1.49it/s]
Loading 0:  61%|██████▏   | 223/363 [03:00<01:15,  1.86it/s]
Loading 0:  62%|██████▏   | 224/363 [03:00<01:00,  2.29it/s]
Loading 0:  62%|██████▏   | 225/363 [03:02<02:04,  1.11it/s]
Loading 0:  63%|██████▎   | 228/363 [03:04<01:48,  1.25it/s]
Loading 0:  63%|██████▎   | 229/363 [03:07<02:24,  1.07s/it]
Loading 0:  63%|██████▎   | 230/363 [03:09<02:57,  1.33s/it]
Loading 0:  64%|██████▍   | 233/363 [03:09<01:35,  1.37it/s]
Loading 0:  64%|██████▍   | 234/363 [03:09<01:23,  1.55it/s]
Loading 0:  65%|██████▍   | 235/363 [03:10<01:08,  1.87it/s]
Loading 0:  65%|██████▌   | 237/363 [03:12<01:33,  1.35it/s]
Loading 0:  66%|██████▌   | 238/363 [03:14<02:09,  1.04s/it]
Loading 0:  66%|██████▌   | 239/363 [03:16<02:43,  1.31s/it]
Loading 0:  67%|██████▋   | 242/363 [03:16<01:26,  1.40it/s]
Loading 0:  67%|██████▋   | 243/363 [03:17<01:15,  1.59it/s]
Loading 0:  67%|██████▋   | 244/363 [03:17<01:02,  1.91it/s]
Loading 0:  68%|██████▊   | 246/363 [03:19<01:25,  1.36it/s]
Loading 0:  68%|██████▊   | 247/363 [03:21<02:00,  1.04s/it]
Loading 0:  68%|██████▊   | 248/363 [03:23<02:31,  1.31s/it]
Loading 0:  69%|██████▉   | 251/363 [03:24<01:19,  1.41it/s]
Loading 0:  69%|██████▉   | 252/363 [03:24<01:09,  1.60it/s]
Loading 0:  70%|██████▉   | 253/363 [03:24<00:57,  1.92it/s]
Loading 0:  70%|███████   | 255/363 [03:26<01:19,  1.37it/s]
Loading 0:  71%|███████   | 256/363 [03:28<01:50,  1.03s/it]
Loading 0:  71%|███████   | 257/363 [03:31<02:19,  1.31s/it]
Loading 0:  72%|███████▏  | 260/363 [03:31<01:13,  1.41it/s]
Loading 0:  72%|███████▏  | 261/363 [03:31<01:03,  1.60it/s]
Loading 0:  72%|███████▏  | 262/363 [03:31<00:52,  1.93it/s]
Loading 0:  73%|███████▎  | 264/363 [03:32<00:38,  2.59it/s]
Loading 0:  73%|███████▎  | 265/363 [03:32<00:35,  2.77it/s]
Loading 0:  73%|███████▎  | 266/363 [03:32<00:29,  3.26it/s]
Loading 0:  74%|███████▎  | 267/363 [03:32<00:25,  3.73it/s]
Loading 0:  74%|███████▍  | 268/363 [03:34<01:12,  1.31it/s]
Loading 0:  74%|███████▍  | 269/363 [03:37<01:47,  1.14s/it]
Loading 0:  74%|███████▍  | 270/363 [03:39<02:13,  1.44s/it]
Loading 0:  75%|███████▌  | 273/363 [03:55<05:24,  3.61s/it]
Loading 0:  75%|███████▌  | 274/363 [03:57<04:54,  3.30s/it]
Loading 0:  76%|███████▌  | 275/363 [03:59<04:29,  3.06s/it]
Loading 0:  77%|███████▋  | 278/363 [04:00<02:16,  1.60s/it]
Loading 0:  77%|███████▋  | 279/363 [04:00<01:52,  1.34s/it]
Loading 0:  77%|███████▋  | 280/363 [04:00<01:29,  1.08s/it]
Loading 0:  78%|███████▊  | 282/363 [04:02<01:25,  1.06s/it]
Loading 0:  78%|███████▊  | 283/363 [04:04<01:41,  1.27s/it]
Loading 0:  78%|███████▊  | 284/363 [04:06<01:57,  1.49s/it]
Loading 0:  79%|███████▉  | 287/363 [04:07<01:00,  1.26it/s]
Loading 0:  79%|███████▉  | 288/363 [04:07<00:51,  1.46it/s]
Loading 0:  80%|███████▉  | 289/363 [04:07<00:41,  1.77it/s]
Loading 0:  80%|████████  | 291/363 [04:09<00:54,  1.32it/s]
Loading 0:  80%|████████  | 292/363 [04:11<01:14,  1.06s/it]
Loading 0:  81%|████████  | 293/363 [04:13<01:32,  1.33s/it]
Loading 0:  82%|████████▏ | 296/363 [04:14<00:47,  1.41it/s]
Loading 0:  82%|████████▏ | 297/363 [04:14<00:40,  1.61it/s]
Loading 0:  82%|████████▏ | 298/363 [04:14<00:33,  1.95it/s]
Loading 0:  82%|████████▏ | 299/363 [04:16<00:57,  1.11it/s]
Loading 0:  83%|████████▎ | 301/363 [04:17<00:37,  1.67it/s]
Loading 0:  83%|████████▎ | 302/363 [04:17<00:31,  1.92it/s]
Loading 0:  83%|████████▎ | 303/363 [04:17<00:25,  2.34it/s]
Loading 0:  84%|████████▎ | 304/363 [04:17<00:21,  2.81it/s]
Loading 0:  84%|████████▍ | 305/363 [04:19<00:48,  1.20it/s]
Loading 0:  84%|████████▍ | 306/363 [04:21<01:09,  1.22s/it]
Loading 0:  85%|████████▌ | 309/363 [04:24<00:51,  1.06it/s]
Loading 0:  85%|████████▌ | 310/363 [04:26<01:03,  1.19s/it]
Loading 0:  86%|████████▌ | 311/363 [04:28<01:13,  1.42s/it]
Loading 0:  87%|████████▋ | 314/363 [04:28<00:37,  1.30it/s]
Loading 0:  87%|████████▋ | 315/363 [04:29<00:32,  1.50it/s]
Loading 0:  87%|████████▋ | 316/363 [04:29<00:25,  1.81it/s]
Loading 0:  88%|████████▊ | 318/363 [04:31<00:33,  1.33it/s]
Loading 0:  88%|████████▊ | 319/363 [04:33<00:46,  1.05s/it]
Loading 0:  88%|████████▊ | 320/363 [04:35<00:56,  1.32s/it]
Loading 0:  89%|████████▉ | 323/363 [04:35<00:28,  1.41it/s]
Loading 0:  89%|████████▉ | 324/363 [04:36<00:24,  1.61it/s]
Loading 0:  90%|████████▉ | 325/363 [04:36<00:19,  1.95it/s]
Loading 0:  90%|█████████ | 327/363 [04:38<00:26,  1.37it/s]
Loading 0:  90%|█████████ | 328/363 [04:40<00:36,  1.03s/it]
Loading 0:  91%|█████████ | 329/363 [04:42<00:44,  1.31s/it]
Loading 0:  91%|█████████▏| 332/363 [04:43<00:21,  1.42it/s]
Loading 0:  92%|█████████▏| 333/363 [04:43<00:18,  1.62it/s]
Loading 0:  92%|█████████▏| 334/363 [04:43<00:14,  1.96it/s]
Loading 0:  92%|█████████▏| 335/363 [04:45<00:25,  1.12it/s]
Loading 0:  93%|█████████▎| 336/363 [04:47<00:33,  1.23s/it]
Loading 0:  93%|█████████▎| 338/363 [04:48<00:19,  1.29it/s]
Loading 0:  93%|█████████▎| 339/363 [04:48<00:15,  1.53it/s]
Loading 0:  94%|█████████▎| 340/363 [04:48<00:12,  1.88it/s]
Loading 0:  94%|█████████▍| 341/363 [04:49<00:11,  1.84it/s]
Loading 0:  94%|█████████▍| 343/363 [04:51<00:15,  1.30it/s]
Loading 0:  95%|█████████▌| 346/363 [04:53<00:12,  1.34it/s]
Loading 0:  96%|█████████▌| 347/363 [04:55<00:16,  1.00s/it]
Loading 0:  96%|█████████▌| 348/363 [04:57<00:18,  1.26s/it]
Loading 0:  97%|█████████▋| 351/363 [04:58<00:08,  1.40it/s]
Loading 0:  97%|█████████▋| 352/363 [04:58<00:06,  1.60it/s]
Loading 0:  97%|█████████▋| 353/363 [04:58<00:05,  1.91it/s]
Loading 0:  98%|█████████▊| 355/363 [05:00<00:05,  1.36it/s]
Loading 0:  98%|█████████▊| 356/363 [05:02<00:07,  1.03s/it]
Loading 0:  98%|█████████▊| 357/363 [05:05<00:07,  1.30s/it]
Loading 0:  99%|█████████▉| 360/363 [05:05<00:02,  1.42it/s]
Loading 0:  99%|█████████▉| 361/363 [05:05<00:01,  1.62it/s]
Loading 0: 100%|█████████▉| 362/363 [05:05<00:00,  1.95it/s]
                                                            
Job chaiml-cai-real-v3-cosine-v3-mkmlizer completed after 419.2s with status: succeeded
Stopping job with name chaiml-cai-real-v3-cosine-v3-mkmlizer
Pipeline stage MKMLizer completed in 420.29s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-real-v3-cosine-v3
Waiting for inference service chaiml-cai-real-v3-cosine-v3 to be ready
Inference service chaiml-cai-real-v3-cosine-v3 ready after 150.8524889945984s
Pipeline stage MKMLDeployer completed in 151.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5776896476745605s
Received healthy response to inference request in 3.3317205905914307s
Received healthy response to inference request in 3.6371169090270996s
Received healthy response to inference request in 3.298987865447998s
Received healthy response to inference request in 3.0749919414520264s
5 requests
0 failed requests
5th percentile: 3.119791126251221
10th percentile: 3.164590311050415
20th percentile: 3.2541886806488036
30th percentile: 3.3055344104766844
40th percentile: 3.3186275005340575
50th percentile: 3.3317205905914307
60th percentile: 3.4301082134246825
70th percentile: 3.5284958362579344
80th percentile: 3.589575099945068
90th percentile: 3.613346004486084
95th percentile: 3.625231456756592
99th percentile: 3.634739818572998
mean time: 3.384101390838623
Pipeline stage StressChecker completed in 18.61s
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 0.72s
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-real-v3-cosine_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cai-real-v3-cosine-v3-profiler
Waiting for inference service chaiml-cai-real-v3-cosine-v3-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3379.47s
Shutdown handler de-registered
chaiml-cai-real-v3-cosine_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-cai-real-v3-cosine_v3 status is now torndown due to DeploymentManager action