chaiml-cai-real-v3-cosine

developer_uid: zonemercy
submission_id: chaiml-cai-real-v3-cosine_v11
model_name: test
model_group: ChaiML/cai-real-v3_cosin
status: inactive
timestamp: 2025-11-28T08:40:41+00:00
num_battles: 6577
num_wins: 3910
celo_rating: 1356.16
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
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': 0.26861078930745663, 'latency_mean': 3.72273331284523, 'latency_p50': 3.7193400859832764, 'latency_p90': 3.9207305908203125}, {'batch_size': 2, 'throughput': 0.43525770418918197, 'latency_mean': 4.590703434944153, 'latency_p50': 4.580317139625549, 'latency_p90': 4.823595595359802}, {'batch_size': 3, 'throughput': 0.5536211465647871, 'latency_mean': 5.408346374034881, 'latency_p50': 5.376839995384216, 'latency_p90': 5.68040668964386}, {'batch_size': 5, 'throughput': 0.6935460013016158, 'latency_mean': 7.160032634735107, 'latency_p50': 7.130154967308044, 'latency_p90': 7.75631160736084}]
gpu_counts: {'NVIDIA L40S': 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
us_pacific_date: 2025-11-28
win_ratio: 0.5944959708073589
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': ['You:', 'User:', '</s>'], '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-v11-mkmlizer
Waiting for job on chaiml-cai-real-v3-cosine-v11-mkmlizer to finish
chaiml-cai-real-v3-cosine-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-real-v3-cosine-v11-mkmlizer: Downloaded to shared memory in 79.118s
chaiml-cai-real-v3-cosine-v11-mkmlizer: Checking if ChaiML/cai-real-v3_cosine already exists in ChaiML
chaiml-cai-real-v3-cosine-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmphe8fh8iy, device:0
chaiml-cai-real-v3-cosine-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-real-v3-cosine-v11-mkmlizer: quantized model in 282.385s
chaiml-cai-real-v3-cosine-v11-mkmlizer: Processed model ChaiML/cai-real-v3_cosine in 361.503s
chaiml-cai-real-v3-cosine-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-real-v3-cosine-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-real-v3-cosine-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia
chaiml-cai-real-v3-cosine-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia/config.json
chaiml-cai-real-v3-cosine-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia/special_tokens_map.json
chaiml-cai-real-v3-cosine-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia/tokenizer_config.json
chaiml-cai-real-v3-cosine-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia/tokenizer.json
chaiml-cai-real-v3-cosine-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia/flywheel_model.1.safetensors
chaiml-cai-real-v3-cosine-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v11/nvidia/flywheel_model.0.safetensors
chaiml-cai-real-v3-cosine-v11-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:01<03:55,  1.53it/s]
Loading 0:   1%|          | 4/363 [00:03<06:22,  1.07s/it]
Loading 0:   1%|▏         | 5/363 [00:05<08:09,  1.37s/it]
Loading 0:   2%|▏         | 8/363 [00:06<03:47,  1.56it/s]
Loading 0:   2%|▏         | 9/363 [00:06<03:19,  1.77it/s]
Loading 0:   3%|▎         | 10/363 [00:06<02:41,  2.18it/s]
Loading 0:   3%|▎         | 12/363 [00:08<03:52,  1.51it/s]
Loading 0:   4%|▎         | 13/363 [00:10<05:30,  1.06it/s]
Loading 0:   4%|▍         | 14/363 [00:12<06:58,  1.20s/it]
Loading 0:   5%|▍         | 17/363 [00:12<03:40,  1.57it/s]
Loading 0:   5%|▍         | 18/363 [00:13<03:13,  1.78it/s]
Loading 0:   5%|▌         | 19/363 [00:13<02:40,  2.14it/s]
Loading 0:   6%|▌         | 21/363 [00:15<03:45,  1.52it/s]
Loading 0:   6%|▌         | 22/363 [00:17<05:17,  1.07it/s]
Loading 0:   6%|▋         | 23/363 [00:19<06:42,  1.18s/it]
Loading 0:   7%|▋         | 26/363 [00:19<03:35,  1.56it/s]
Loading 0:   7%|▋         | 27/363 [00:19<03:09,  1.78it/s]
Loading 0:   8%|▊         | 28/363 [00:19<02:36,  2.14it/s]
Loading 0:   8%|▊         | 30/363 [00:19<01:55,  2.89it/s]
Loading 0:   9%|▊         | 31/363 [00:20<01:48,  3.07it/s]
Loading 0:   9%|▉         | 32/363 [00:20<01:32,  3.58it/s]
Loading 0:   9%|▉         | 33/363 [00:20<01:21,  4.03it/s]
Loading 0:   9%|▉         | 34/363 [00:22<03:48,  1.44it/s]
Loading 0:  10%|▉         | 35/363 [00:24<05:38,  1.03s/it]
Loading 0:  10%|▉         | 36/363 [00:26<07:07,  1.31s/it]
Loading 0:  11%|█         | 39/363 [00:28<05:06,  1.06it/s]
Loading 0:  11%|█         | 40/363 [00:30<06:11,  1.15s/it]
Loading 0:  11%|█▏        | 41/363 [00:32<07:13,  1.35s/it]
Loading 0:  12%|█▏        | 44/363 [00:32<03:53,  1.37it/s]
Loading 0:  12%|█▏        | 45/363 [00:32<03:23,  1.56it/s]
Loading 0:  13%|█▎        | 46/363 [00:32<02:47,  1.90it/s]
Loading 0:  13%|█▎        | 48/363 [00:34<03:38,  1.44it/s]
Loading 0:  13%|█▎        | 49/363 [00:36<05:00,  1.04it/s]
Loading 0:  14%|█▍        | 50/363 [00:38<06:15,  1.20s/it]
Loading 0:  15%|█▍        | 53/363 [00:39<03:21,  1.54it/s]
Loading 0:  15%|█▍        | 54/363 [00:39<02:56,  1.75it/s]
Loading 0:  15%|█▌        | 55/363 [00:39<02:26,  2.10it/s]
Loading 0:  16%|█▌        | 57/363 [00:41<03:22,  1.51it/s]
Loading 0:  16%|█▌        | 58/363 [00:43<04:45,  1.07it/s]
Loading 0:  16%|█▋        | 59/363 [00:45<06:01,  1.19s/it]
Loading 0:  17%|█▋        | 62/363 [00:45<03:12,  1.56it/s]
Loading 0:  17%|█▋        | 63/363 [00:45<02:49,  1.78it/s]
Loading 0:  18%|█▊        | 64/363 [00:46<02:19,  2.14it/s]
Loading 0:  18%|█▊        | 65/363 [00:47<04:01,  1.23it/s]
Loading 0:  18%|█▊        | 67/363 [00:48<02:41,  1.83it/s]
Loading 0:  19%|█▊        | 68/363 [00:48<02:20,  2.09it/s]
Loading 0:  19%|█▉        | 69/363 [00:48<01:55,  2.55it/s]
Loading 0:  19%|█▉        | 70/363 [00:48<01:34,  3.09it/s]
Loading 0:  20%|█▉        | 71/363 [00:50<03:47,  1.28it/s]
Loading 0:  20%|█▉        | 72/363 [00:52<05:19,  1.10s/it]
Loading 0:  20%|██        | 73/363 [00:54<06:33,  1.36s/it]
Loading 0:  21%|██        | 76/363 [00:54<03:11,  1.50it/s]
Loading 0:  21%|██        | 77/363 [00:55<02:45,  1.73it/s]
Loading 0:  21%|██▏       | 78/363 [00:55<02:15,  2.11it/s]
Loading 0:  22%|██▏       | 79/363 [00:57<03:56,  1.20it/s]
Loading 0:  22%|██▏       | 80/363 [00:59<05:21,  1.14s/it]
Loading 0:  23%|██▎       | 82/363 [00:59<03:21,  1.39it/s]
Loading 0:  23%|██▎       | 83/363 [00:59<02:49,  1.65it/s]
Loading 0:  23%|██▎       | 84/363 [00:59<02:15,  2.06it/s]
Loading 0:  24%|██▎       | 86/363 [01:01<03:10,  1.45it/s]
Loading 0:  24%|██▍       | 87/363 [01:03<04:33,  1.01it/s]
Loading 0:  25%|██▍       | 90/363 [01:05<03:43,  1.22it/s]
Loading 0:  25%|██▌       | 91/363 [01:07<04:40,  1.03s/it]
Loading 0:  25%|██▌       | 92/363 [01:09<05:35,  1.24s/it]
Loading 0:  26%|██▌       | 95/363 [01:10<03:06,  1.44it/s]
Loading 0:  26%|██▋       | 96/363 [01:10<02:43,  1.64it/s]
Loading 0:  27%|██▋       | 97/363 [01:10<02:15,  1.97it/s]
Loading 0:  27%|██▋       | 99/363 [01:12<02:59,  1.47it/s]
Loading 0:  28%|██▊       | 100/363 [01:14<04:08,  1.06it/s]
Loading 0:  28%|██▊       | 101/363 [01:16<05:12,  1.19s/it]
Loading 0:  29%|██▊       | 104/363 [01:16<02:48,  1.54it/s]
Loading 0:  29%|██▉       | 105/363 [01:16<02:27,  1.75it/s]
Loading 0:  29%|██▉       | 106/363 [01:17<02:02,  2.10it/s]
Loading 0:  29%|██▉       | 107/363 [01:17<01:41,  2.52it/s]
Loading 0:  30%|██▉       | 108/363 [01:19<03:19,  1.28it/s]
Loading 0:  31%|███       | 111/363 [01:21<02:59,  1.41it/s]
Loading 0:  31%|███       | 112/363 [01:22<03:59,  1.05it/s]
Loading 0:  31%|███       | 113/363 [01:24<04:57,  1.19s/it]
Loading 0:  32%|███▏      | 116/363 [01:25<02:43,  1.51it/s]
Loading 0:  32%|███▏      | 117/363 [01:25<02:23,  1.72it/s]
Loading 0:  33%|███▎      | 118/363 [01:25<01:58,  2.06it/s]
Loading 0:  33%|███▎      | 120/363 [01:27<02:42,  1.49it/s]
Loading 0:  33%|███▎      | 121/363 [01:29<03:47,  1.07it/s]
Loading 0:  34%|███▎      | 122/363 [01:31<04:45,  1.19s/it]
Loading 0:  34%|███▍      | 125/363 [01:31<02:33,  1.55it/s]
Loading 0:  35%|███▍      | 126/363 [01:32<02:14,  1.76it/s]
Loading 0:  35%|███▍      | 127/363 [01:32<01:51,  2.11it/s]
Loading 0:  36%|███▌      | 129/363 [01:34<02:35,  1.50it/s]
Loading 0:  36%|███▌      | 130/363 [01:36<03:38,  1.07it/s]
Loading 0:  36%|███▌      | 131/363 [01:38<04:36,  1.19s/it]
Loading 0:  37%|███▋      | 134/363 [01:38<02:27,  1.55it/s]
Loading 0:  37%|███▋      | 135/363 [01:38<02:09,  1.76it/s]
Loading 0:  37%|███▋      | 136/363 [01:38<01:47,  2.11it/s]
Loading 0:  38%|███▊      | 138/363 [01:40<02:29,  1.50it/s]
Loading 0:  38%|███▊      | 139/363 [01:42<03:30,  1.07it/s]
Loading 0:  39%|███▊      | 140/363 [01:44<04:24,  1.19s/it]
Loading 0:  39%|███▉      | 143/363 [01:45<02:21,  1.55it/s]
Loading 0:  40%|███▉      | 144/363 [01:45<02:04,  1.76it/s]
Loading 0:  40%|███▉      | 145/363 [01:45<01:43,  2.11it/s]
Loading 0:  40%|████      | 147/363 [01:45<01:15,  2.84it/s]
Loading 0:  41%|████      | 148/363 [01:45<01:10,  3.04it/s]
Loading 0:  41%|████      | 149/363 [01:46<01:00,  3.55it/s]
Loading 0:  41%|████▏     | 150/363 [01:46<00:52,  4.05it/s]
Loading 0:  42%|████▏     | 151/363 [01:48<02:27,  1.44it/s]
Loading 0:  42%|████▏     | 152/363 [01:50<03:38,  1.03s/it]
Loading 0:  42%|████▏     | 153/363 [01:52<04:34,  1.31s/it]
Loading 0:  43%|████▎     | 156/363 [01:54<03:15,  1.06it/s]
Loading 0:  43%|████▎     | 157/363 [01:55<03:57,  1.15s/it]
Loading 0:  44%|████▎     | 158/363 [01:57<04:35,  1.34s/it]
Loading 0:  44%|████▍     | 161/363 [01:58<02:27,  1.37it/s]
Loading 0:  45%|████▍     | 162/363 [01:58<02:08,  1.57it/s]
Loading 0:  45%|████▍     | 163/363 [01:58<01:46,  1.88it/s]
Loading 0:  45%|████▌     | 165/363 [02:00<02:18,  1.43it/s]
Loading 0:  46%|████▌     | 166/363 [02:02<03:09,  1.04it/s]
Loading 0:  46%|████▌     | 167/363 [02:04<03:56,  1.21s/it]
Loading 0:  47%|████▋     | 170/363 [02:04<02:06,  1.53it/s]
Loading 0:  47%|████▋     | 171/363 [02:05<01:50,  1.74it/s]
Loading 0:  47%|████▋     | 172/363 [02:05<01:31,  2.09it/s]
Loading 0:  48%|████▊     | 174/363 [02:07<02:05,  1.50it/s]
Loading 0:  48%|████▊     | 175/363 [02:09<02:56,  1.07it/s]
Loading 0:  48%|████▊     | 176/363 [02:11<03:42,  1.19s/it]
Loading 0:  49%|████▉     | 179/363 [02:11<01:58,  1.55it/s]
Loading 0:  50%|████▉     | 180/363 [02:11<01:43,  1.76it/s]
Loading 0:  50%|████▉     | 181/363 [02:11<01:25,  2.13it/s]
Loading 0:  50%|█████     | 182/363 [02:13<02:28,  1.22it/s]
Loading 0:  51%|█████     | 184/363 [02:14<01:38,  1.82it/s]
Loading 0:  51%|█████     | 185/363 [02:14<01:25,  2.08it/s]
Loading 0:  51%|█████     | 186/363 [02:14<01:10,  2.51it/s]
Loading 0:  52%|█████▏    | 187/363 [02:14<00:57,  3.04it/s]
Loading 0:  52%|█████▏    | 188/363 [02:16<02:13,  1.31it/s]
Loading 0:  52%|█████▏    | 189/363 [02:18<03:12,  1.11s/it]
Loading 0:  53%|█████▎    | 192/363 [02:20<02:26,  1.17it/s]
Loading 0:  53%|█████▎    | 193/363 [02:22<03:03,  1.08s/it]
Loading 0:  53%|█████▎    | 194/363 [02:24<03:37,  1.29s/it]
Loading 0:  54%|█████▍    | 197/363 [02:24<01:56,  1.42it/s]
Loading 0:  55%|█████▍    | 198/363 [02:24<01:41,  1.62it/s]
Loading 0:  55%|█████▍    | 199/363 [02:25<01:23,  1.96it/s]
Loading 0:  55%|█████▌    | 201/363 [02:26<01:51,  1.46it/s]
Loading 0:  56%|█████▌    | 202/363 [02:28<02:33,  1.05it/s]
Loading 0:  56%|█████▌    | 203/363 [02:30<03:12,  1.20s/it]
Loading 0:  57%|█████▋    | 206/363 [02:31<01:42,  1.54it/s]
Loading 0:  57%|█████▋    | 207/363 [02:31<01:29,  1.74it/s]
Loading 0:  57%|█████▋    | 208/363 [02:31<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 210/363 [02:33<01:41,  1.50it/s]
Loading 0:  58%|█████▊    | 211/363 [02:35<02:22,  1.07it/s]
Loading 0:  58%|█████▊    | 212/363 [02:37<02:59,  1.19s/it]
Loading 0:  59%|█████▉    | 215/363 [02:37<01:35,  1.55it/s]
Loading 0:  60%|█████▉    | 216/363 [02:38<01:23,  1.76it/s]
Loading 0:  60%|█████▉    | 217/363 [02:38<01:08,  2.12it/s]
Loading 0:  60%|██████    | 218/363 [02:40<01:58,  1.22it/s]
Loading 0:  60%|██████    | 219/363 [02:42<02:40,  1.12s/it]
Loading 0:  61%|██████    | 221/363 [02:42<01:41,  1.40it/s]
Loading 0:  61%|██████    | 222/363 [02:42<01:25,  1.65it/s]
Loading 0:  61%|██████▏   | 223/363 [02:42<01:08,  2.04it/s]
Loading 0:  62%|██████▏   | 224/363 [02:42<00:55,  2.51it/s]
Loading 0:  62%|██████▏   | 225/363 [02:44<01:52,  1.22it/s]
Loading 0:  63%|██████▎   | 228/363 [02:46<01:37,  1.38it/s]
Loading 0:  63%|██████▎   | 229/363 [02:48<02:09,  1.03it/s]
Loading 0:  63%|██████▎   | 230/363 [02:50<02:39,  1.20s/it]
Loading 0:  64%|██████▍   | 233/363 [02:51<01:25,  1.51it/s]
Loading 0:  64%|██████▍   | 234/363 [02:51<01:15,  1.72it/s]
Loading 0:  65%|██████▍   | 235/363 [02:51<01:01,  2.07it/s]
Loading 0:  65%|██████▌   | 237/363 [02:53<01:24,  1.50it/s]
Loading 0:  66%|██████▌   | 238/363 [02:55<01:57,  1.07it/s]
Loading 0:  66%|██████▌   | 239/363 [02:57<02:27,  1.19s/it]
Loading 0:  67%|██████▋   | 242/363 [02:57<01:18,  1.55it/s]
Loading 0:  67%|██████▋   | 243/363 [02:57<01:08,  1.76it/s]
Loading 0:  67%|██████▋   | 244/363 [02:57<00:56,  2.11it/s]
Loading 0:  68%|██████▊   | 246/363 [02:59<01:17,  1.51it/s]
Loading 0:  68%|██████▊   | 247/363 [03:01<01:48,  1.07it/s]
Loading 0:  68%|██████▊   | 248/363 [03:03<02:16,  1.18s/it]
Loading 0:  69%|██████▉   | 251/363 [03:04<01:11,  1.56it/s]
Loading 0:  69%|██████▉   | 252/363 [03:04<01:02,  1.77it/s]
Loading 0:  70%|██████▉   | 253/363 [03:04<00:51,  2.13it/s]
Loading 0:  70%|███████   | 255/363 [03:06<01:11,  1.52it/s]
Loading 0:  71%|███████   | 256/363 [03:08<01:39,  1.07it/s]
Loading 0:  71%|███████   | 257/363 [03:10<02:05,  1.19s/it]
Loading 0:  72%|███████▏  | 260/363 [03:10<01:06,  1.55it/s]
Loading 0:  72%|███████▏  | 261/363 [03:10<00:57,  1.77it/s]
Loading 0:  72%|███████▏  | 262/363 [03:11<00:47,  2.12it/s]
Loading 0:  73%|███████▎  | 264/363 [03:11<00:34,  2.85it/s]
Loading 0:  73%|███████▎  | 265/363 [03:11<00:32,  3.05it/s]
Loading 0:  73%|███████▎  | 266/363 [03:11<00:27,  3.56it/s]
Loading 0:  74%|███████▎  | 267/363 [03:11<00:23,  4.08it/s]
Loading 0:  74%|███████▍  | 268/363 [03:13<01:05,  1.45it/s]
Loading 0:  74%|███████▍  | 269/363 [03:15<01:36,  1.03s/it]
Loading 0:  74%|███████▍  | 270/363 [03:17<02:01,  1.30s/it]
Loading 0:  75%|███████▌  | 273/363 [03:32<04:58,  3.32s/it]
Loading 0:  75%|███████▌  | 274/363 [03:34<04:29,  3.03s/it]
Loading 0:  76%|███████▌  | 275/363 [03:36<04:07,  2.82s/it]
Loading 0:  77%|███████▋  | 278/363 [03:37<02:05,  1.48s/it]
Loading 0:  77%|███████▋  | 279/363 [03:37<01:43,  1.24s/it]
Loading 0:  77%|███████▋  | 280/363 [03:37<01:22,  1.00it/s]
Loading 0:  78%|███████▊  | 282/363 [03:39<01:20,  1.01it/s]
Loading 0:  78%|███████▊  | 283/363 [03:41<01:35,  1.19s/it]
Loading 0:  78%|███████▊  | 284/363 [03:43<01:48,  1.38s/it]
Loading 0:  79%|███████▉  | 287/363 [03:43<00:55,  1.36it/s]
Loading 0:  79%|███████▉  | 288/363 [03:43<00:47,  1.58it/s]
Loading 0:  80%|███████▉  | 289/363 [03:43<00:38,  1.91it/s]
Loading 0:  80%|████████  | 291/363 [03:45<00:49,  1.44it/s]
Loading 0:  80%|████████  | 292/363 [03:47<01:07,  1.04it/s]
Loading 0:  81%|████████  | 293/363 [03:49<01:24,  1.20s/it]
Loading 0:  82%|████████▏ | 296/363 [03:50<00:43,  1.55it/s]
Loading 0:  82%|████████▏ | 297/363 [03:50<00:37,  1.78it/s]
Loading 0:  82%|████████▏ | 298/363 [03:50<00:30,  2.14it/s]
Loading 0:  82%|████████▏ | 299/363 [03:52<00:51,  1.23it/s]
Loading 0:  83%|████████▎ | 301/363 [03:52<00:33,  1.85it/s]
Loading 0:  83%|████████▎ | 302/363 [03:52<00:28,  2.14it/s]
Loading 0:  83%|████████▎ | 303/363 [03:52<00:23,  2.60it/s]
Loading 0:  84%|████████▎ | 304/363 [03:53<00:18,  3.12it/s]
Loading 0:  84%|████████▍ | 305/363 [03:54<00:43,  1.33it/s]
Loading 0:  84%|████████▍ | 306/363 [03:56<01:02,  1.10s/it]
Loading 0:  85%|████████▌ | 309/363 [03:58<00:45,  1.20it/s]
Loading 0:  85%|████████▌ | 310/363 [04:00<00:56,  1.06s/it]
Loading 0:  86%|████████▌ | 311/363 [04:02<01:06,  1.27s/it]
Loading 0:  87%|████████▋ | 314/363 [04:03<00:33,  1.45it/s]
Loading 0:  87%|████████▋ | 315/363 [04:03<00:28,  1.66it/s]
Loading 0:  87%|████████▋ | 316/363 [04:03<00:23,  2.00it/s]
Loading 0:  88%|████████▊ | 318/363 [04:05<00:30,  1.47it/s]
Loading 0:  88%|████████▊ | 319/363 [04:07<00:41,  1.06it/s]
Loading 0:  88%|████████▊ | 320/363 [04:09<00:51,  1.19s/it]
Loading 0:  89%|████████▉ | 323/363 [04:09<00:25,  1.55it/s]
Loading 0:  89%|████████▉ | 324/363 [04:09<00:21,  1.78it/s]
Loading 0:  90%|████████▉ | 325/363 [04:09<00:17,  2.15it/s]
Loading 0:  90%|█████████ | 327/363 [04:11<00:23,  1.52it/s]
Loading 0:  90%|█████████ | 328/363 [04:13<00:32,  1.08it/s]
Loading 0:  91%|█████████ | 329/363 [04:15<00:40,  1.18s/it]
Loading 0:  91%|█████████▏| 332/363 [04:16<00:19,  1.57it/s]
Loading 0:  92%|█████████▏| 333/363 [04:16<00:16,  1.79it/s]
Loading 0:  92%|█████████▏| 334/363 [04:16<00:13,  2.15it/s]
Loading 0:  92%|█████████▏| 335/363 [04:18<00:22,  1.23it/s]
Loading 0:  93%|█████████▎| 336/363 [04:20<00:29,  1.11s/it]
Loading 0:  93%|█████████▎| 338/363 [04:20<00:17,  1.42it/s]
Loading 0:  93%|█████████▎| 339/363 [04:20<00:14,  1.69it/s]
Loading 0:  94%|█████████▎| 340/363 [04:20<00:10,  2.10it/s]
Loading 0:  94%|█████████▍| 341/363 [04:21<00:09,  2.34it/s]
Loading 0:  94%|█████████▍| 343/363 [04:23<00:13,  1.52it/s]
Loading 0:  95%|█████████▌| 346/363 [04:25<00:11,  1.53it/s]
Loading 0:  96%|█████████▌| 347/363 [04:27<00:14,  1.12it/s]
Loading 0:  96%|█████████▌| 348/363 [04:29<00:16,  1.12s/it]
Loading 0:  97%|█████████▋| 351/363 [04:29<00:07,  1.58it/s]
Loading 0:  97%|█████████▋| 352/363 [04:29<00:06,  1.79it/s]
Loading 0:  97%|█████████▋| 353/363 [04:29<00:04,  2.15it/s]
Loading 0:  98%|█████████▊| 355/363 [04:31<00:05,  1.51it/s]
Loading 0:  98%|█████████▊| 356/363 [04:33<00:06,  1.08it/s]
Loading 0:  98%|█████████▊| 357/363 [04:35<00:07,  1.18s/it]
Loading 0:  99%|█████████▉| 360/363 [04:35<00:01,  1.57it/s]
Loading 0:  99%|█████████▉| 361/363 [04:36<00:01,  1.79it/s]
Loading 0: 100%|█████████▉| 362/363 [04:36<00:00,  2.16it/s]
                                                            
Job chaiml-cai-real-v3-cosine-v11-mkmlizer completed after 421.58s with status: succeeded
Stopping job with name chaiml-cai-real-v3-cosine-v11-mkmlizer
Pipeline stage MKMLizer completed in 422.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-real-v3-cosine-v11
Waiting for inference service chaiml-cai-real-v3-cosine-v11 to be ready
Failed to get response for submission blend_jotik_2025-11-05: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-4d70-fd43-linear-w01_v8/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n  Field required [type=missing, input_value={\'detail\': \'[Errno 104] Connection reset by peer\'}, input_type=dict]\\n    For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
Inference service chaiml-cai-real-v3-cosine-v11 ready after 170.99530243873596s
Pipeline stage MKMLDeployer completed in 171.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7608847618103027s
Received healthy response to inference request in 3.4466984272003174s
Received healthy response to inference request in 3.372378349304199s
Received healthy response to inference request in 3.154090642929077s
Received healthy response to inference request in 3.3426129817962646s
5 requests
0 failed requests
5th percentile: 3.1917951107025146
10th percentile: 3.229499578475952
20th percentile: 3.304908514022827
30th percentile: 3.3485660552978516
40th percentile: 3.3604722023010254
50th percentile: 3.372378349304199
60th percentile: 3.4021063804626466
70th percentile: 3.431834411621094
80th percentile: 3.5095356941223144
90th percentile: 3.6352102279663088
95th percentile: 3.6980474948883058
99th percentile: 3.748317308425903
mean time: 3.4153330326080322
Pipeline stage StressChecker completed in 18.68s
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 0.70s
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 0.63s
Shutdown handler de-registered
chaiml-cai-real-v3-cosine_v11 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-v11-profiler
Waiting for inference service chaiml-cai-real-v3-cosine-v11-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 3428.97s
Shutdown handler de-registered