chaiml-cai-real-v3-cosine

developer_uid: zonemercy
submission_id: chaiml-cai-real-v3-cosine_v12
model_name: test
model_group: ChaiML/cai-real-v3_cosin
status: inactive
timestamp: 2025-11-28T09:53:00+00:00
num_battles: 6312
num_wins: 3678
celo_rating: 1359.02
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': 0.2678839891626809, 'latency_mean': 3.732858736515045, 'latency_p50': 3.7270935773849487, 'latency_p90': 3.9299235343933105}, {'batch_size': 2, 'throughput': 0.43303053010065823, 'latency_mean': 4.616902520656586, 'latency_p50': 4.61560332775116, 'latency_p90': 4.8566405296325685}, {'batch_size': 3, 'throughput': 0.5516254462819932, 'latency_mean': 5.421086431741714, 'latency_p50': 5.440860986709595, 'latency_p90': 5.687744235992431}, {'batch_size': 5, 'throughput': 0.6931653989892292, 'latency_mean': 7.172264249324798, 'latency_p50': 7.181718587875366, 'latency_p90': 7.487970685958862}]
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: 0.5826996197718631
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:', '</s>', 'User:'], '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-v12-mkmlizer
Waiting for job on chaiml-cai-real-v3-cosine-v12-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-cai-real-v3-cosine-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ║                                                                     ║
chaiml-cai-real-v3-cosine-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-real-v3-cosine-v12-mkmlizer: Downloaded to shared memory in 59.269s
chaiml-cai-real-v3-cosine-v12-mkmlizer: Checking if ChaiML/cai-real-v3_cosine already exists in ChaiML
chaiml-cai-real-v3-cosine-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpopzmdzb9, device:0
chaiml-cai-real-v3-cosine-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-real-v3-cosine-v12-mkmlizer: quantized model in 321.173s
chaiml-cai-real-v3-cosine-v12-mkmlizer: Processed model ChaiML/cai-real-v3_cosine in 380.443s
chaiml-cai-real-v3-cosine-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-real-v3-cosine-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-real-v3-cosine-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia
chaiml-cai-real-v3-cosine-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia/config.json
chaiml-cai-real-v3-cosine-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia/special_tokens_map.json
chaiml-cai-real-v3-cosine-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia/tokenizer_config.json
chaiml-cai-real-v3-cosine-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia/tokenizer.json
chaiml-cai-real-v3-cosine-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia/flywheel_model.1.safetensors
chaiml-cai-real-v3-cosine-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-real-v3-cosine-v12/nvidia/flywheel_model.0.safetensors
chaiml-cai-real-v3-cosine-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:02<04:22,  1.37it/s]
Loading 0:   1%|          | 4/363 [00:04<07:06,  1.19s/it]
Loading 0:   1%|▏         | 5/363 [00:06<09:04,  1.52s/it]
Loading 0:   2%|▏         | 8/363 [00:06<04:13,  1.40it/s]
Loading 0:   2%|▏         | 9/363 [00:07<03:42,  1.59it/s]
Loading 0:   3%|▎         | 10/363 [00:07<03:00,  1.96it/s]
Loading 0:   3%|▎         | 12/363 [00:09<04:19,  1.35it/s]
Loading 0:   4%|▎         | 13/363 [00:11<06:08,  1.05s/it]
Loading 0:   4%|▍         | 14/363 [00:13<07:46,  1.34s/it]
Loading 0:   5%|▍         | 17/363 [00:14<04:07,  1.40it/s]
Loading 0:   5%|▍         | 18/363 [00:14<03:37,  1.59it/s]
Loading 0:   5%|▌         | 19/363 [00:14<02:59,  1.92it/s]
Loading 0:   6%|▌         | 21/363 [00:16<04:11,  1.36it/s]
Loading 0:   6%|▌         | 22/363 [00:18<05:54,  1.04s/it]
Loading 0:   6%|▋         | 23/363 [00:21<07:29,  1.32s/it]
Loading 0:   7%|▋         | 26/363 [00:21<04:00,  1.40it/s]
Loading 0:   7%|▋         | 27/363 [00:21<03:31,  1.59it/s]
Loading 0:   8%|▊         | 28/363 [00:21<02:54,  1.92it/s]
Loading 0:   8%|▊         | 30/363 [00:22<02:08,  2.59it/s]
Loading 0:   9%|▊         | 31/363 [00:22<02:00,  2.76it/s]
Loading 0:   9%|▉         | 32/363 [00:22<01:41,  3.25it/s]
Loading 0:   9%|▉         | 33/363 [00:22<01:29,  3.68it/s]
Loading 0:   9%|▉         | 34/363 [00:24<04:12,  1.30it/s]
Loading 0:  10%|▉         | 35/363 [00:27<06:17,  1.15s/it]
Loading 0:  10%|▉         | 36/363 [00:29<07:55,  1.45s/it]
Loading 0:  11%|█         | 39/363 [00:31<05:41,  1.05s/it]
Loading 0:  11%|█         | 40/363 [00:33<06:53,  1.28s/it]
Loading 0:  11%|█▏        | 41/363 [00:35<08:02,  1.50s/it]
Loading 0:  12%|█▏        | 44/363 [00:36<04:18,  1.23it/s]
Loading 0:  12%|█▏        | 45/363 [00:36<03:44,  1.42it/s]
Loading 0:  13%|█▎        | 46/363 [00:36<03:04,  1.72it/s]
Loading 0:  13%|█▎        | 48/363 [00:38<04:02,  1.30it/s]
Loading 0:  13%|█▎        | 49/363 [00:40<05:34,  1.06s/it]
Loading 0:  14%|█▍        | 50/363 [00:43<06:58,  1.34s/it]
Loading 0:  15%|█▍        | 53/363 [00:43<03:44,  1.38it/s]
Loading 0:  15%|█▍        | 54/363 [00:43<03:17,  1.57it/s]
Loading 0:  15%|█▌        | 55/363 [00:43<02:42,  1.89it/s]
Loading 0:  16%|█▌        | 57/363 [00:46<03:46,  1.35it/s]
Loading 0:  16%|█▌        | 58/363 [00:48<05:17,  1.04s/it]
Loading 0:  16%|█▋        | 59/363 [00:50<06:41,  1.32s/it]
Loading 0:  17%|█▋        | 62/363 [00:50<03:34,  1.40it/s]
Loading 0:  17%|█▋        | 63/363 [00:51<03:08,  1.59it/s]
Loading 0:  18%|█▊        | 64/363 [00:51<02:35,  1.92it/s]
Loading 0:  18%|█▊        | 65/363 [00:53<04:29,  1.11it/s]
Loading 0:  18%|█▊        | 67/363 [00:53<02:59,  1.64it/s]
Loading 0:  19%|█▊        | 68/363 [00:53<02:37,  1.88it/s]
Loading 0:  19%|█▉        | 69/363 [00:54<02:09,  2.28it/s]
Loading 0:  19%|█▉        | 70/363 [00:54<01:46,  2.74it/s]
Loading 0:  20%|█▉        | 71/363 [00:56<04:06,  1.18it/s]
Loading 0:  20%|█▉        | 72/363 [00:58<05:51,  1.21s/it]
Loading 0:  20%|██        | 73/363 [01:00<07:15,  1.50s/it]
Loading 0:  21%|██        | 76/363 [01:01<03:32,  1.35it/s]
Loading 0:  21%|██        | 77/363 [01:01<03:04,  1.55it/s]
Loading 0:  21%|██▏       | 78/363 [01:01<02:30,  1.90it/s]
Loading 0:  22%|██▏       | 79/363 [01:03<04:24,  1.08it/s]
Loading 0:  22%|██▏       | 80/363 [01:05<05:59,  1.27s/it]
Loading 0:  23%|██▎       | 82/363 [01:06<03:45,  1.25it/s]
Loading 0:  23%|██▎       | 83/363 [01:06<03:09,  1.47it/s]
Loading 0:  23%|██▎       | 84/363 [01:06<02:31,  1.84it/s]
Loading 0:  24%|██▎       | 86/363 [01:08<03:33,  1.30it/s]
Loading 0:  24%|██▍       | 87/363 [01:11<05:06,  1.11s/it]
Loading 0:  25%|██▍       | 90/363 [01:13<04:10,  1.09it/s]
Loading 0:  25%|██▌       | 91/363 [01:15<05:13,  1.15s/it]
Loading 0:  25%|██▌       | 92/363 [01:17<06:15,  1.39s/it]
Loading 0:  26%|██▌       | 95/363 [01:18<03:28,  1.29it/s]
Loading 0:  26%|██▋       | 96/363 [01:18<03:02,  1.46it/s]
Loading 0:  27%|██▋       | 97/363 [01:18<02:31,  1.76it/s]
Loading 0:  27%|██▋       | 99/363 [01:20<03:21,  1.31it/s]
Loading 0:  28%|██▊       | 100/363 [01:22<04:38,  1.06s/it]
Loading 0:  28%|██▊       | 101/363 [01:25<05:50,  1.34s/it]
Loading 0:  29%|██▊       | 104/363 [01:25<03:08,  1.37it/s]
Loading 0:  29%|██▉       | 105/363 [01:25<02:45,  1.56it/s]
Loading 0:  29%|██▉       | 106/363 [01:25<02:17,  1.87it/s]
Loading 0:  29%|██▉       | 107/363 [01:25<01:54,  2.24it/s]
Loading 0:  30%|██▉       | 108/363 [01:28<03:48,  1.12it/s]
Loading 0:  31%|███       | 111/363 [01:30<03:28,  1.21it/s]
Loading 0:  31%|███       | 112/363 [01:32<04:38,  1.11s/it]
Loading 0:  31%|███       | 113/363 [01:35<05:44,  1.38s/it]
Loading 0:  32%|███▏      | 116/363 [01:35<03:08,  1.31it/s]
Loading 0:  32%|███▏      | 117/363 [01:35<02:45,  1.48it/s]
Loading 0:  33%|███▎      | 118/363 [01:35<02:17,  1.78it/s]
Loading 0:  33%|███▎      | 120/363 [01:38<03:08,  1.29it/s]
Loading 0:  33%|███▎      | 121/363 [01:40<04:22,  1.09s/it]
Loading 0:  34%|███▎      | 122/363 [01:42<05:30,  1.37s/it]
Loading 0:  34%|███▍      | 125/363 [01:43<02:57,  1.34it/s]
Loading 0:  35%|███▍      | 126/363 [01:43<02:35,  1.52it/s]
Loading 0:  35%|███▍      | 127/363 [01:43<02:08,  1.84it/s]
Loading 0:  36%|███▌      | 129/363 [01:45<02:59,  1.30it/s]
Loading 0:  36%|███▌      | 130/363 [01:47<04:12,  1.08s/it]
Loading 0:  36%|███▌      | 131/363 [01:50<05:18,  1.37s/it]
Loading 0:  37%|███▋      | 134/363 [01:50<02:50,  1.34it/s]
Loading 0:  37%|███▋      | 135/363 [01:50<02:29,  1.52it/s]
Loading 0:  37%|███▋      | 136/363 [01:51<02:03,  1.84it/s]
Loading 0:  38%|███▊      | 138/363 [01:53<02:52,  1.30it/s]
Loading 0:  38%|███▊      | 139/363 [01:55<04:03,  1.09s/it]
Loading 0:  39%|███▊      | 140/363 [01:57<05:08,  1.38s/it]
Loading 0:  39%|███▉      | 143/363 [01:58<02:44,  1.34it/s]
Loading 0:  40%|███▉      | 144/363 [01:58<02:24,  1.52it/s]
Loading 0:  40%|███▉      | 145/363 [01:58<01:59,  1.83it/s]
Loading 0:  40%|████      | 147/363 [01:59<01:27,  2.47it/s]
Loading 0:  41%|████      | 148/363 [01:59<01:21,  2.65it/s]
Loading 0:  41%|████      | 149/363 [01:59<01:09,  3.10it/s]
Loading 0:  41%|████▏     | 150/363 [01:59<01:00,  3.51it/s]
Loading 0:  42%|████▏     | 151/363 [02:01<02:50,  1.24it/s]
Loading 0:  42%|████▏     | 152/363 [02:04<04:13,  1.20s/it]
Loading 0:  42%|████▏     | 153/363 [02:06<05:20,  1.52s/it]
Loading 0:  43%|████▎     | 156/363 [02:08<03:47,  1.10s/it]
Loading 0:  43%|████▎     | 157/363 [02:10<04:34,  1.33s/it]
Loading 0:  44%|████▎     | 158/363 [02:13<05:20,  1.56s/it]
Loading 0:  44%|████▍     | 161/363 [02:13<02:51,  1.18it/s]
Loading 0:  45%|████▍     | 162/363 [02:13<02:27,  1.36it/s]
Loading 0:  45%|████▍     | 163/363 [02:14<02:01,  1.65it/s]
Loading 0:  45%|████▌     | 165/363 [02:16<02:39,  1.24it/s]
Loading 0:  46%|████▌     | 166/363 [02:18<03:39,  1.11s/it]
Loading 0:  46%|████▌     | 167/363 [02:20<04:34,  1.40s/it]
Loading 0:  47%|████▋     | 170/363 [02:21<02:26,  1.32it/s]
Loading 0:  47%|████▋     | 171/363 [02:21<02:07,  1.50it/s]
Loading 0:  47%|████▋     | 172/363 [02:21<01:45,  1.80it/s]
Loading 0:  48%|████▊     | 174/363 [02:23<02:25,  1.30it/s]
Loading 0:  48%|████▊     | 175/363 [02:26<03:24,  1.09s/it]
Loading 0:  48%|████▊     | 176/363 [02:28<04:17,  1.38s/it]
Loading 0:  49%|████▉     | 179/363 [02:28<02:17,  1.34it/s]
Loading 0:  50%|████▉     | 180/363 [02:29<01:59,  1.53it/s]
Loading 0:  50%|████▉     | 181/363 [02:29<01:39,  1.84it/s]
Loading 0:  50%|█████     | 182/363 [02:31<02:50,  1.06it/s]
Loading 0:  51%|█████     | 184/363 [02:31<01:52,  1.59it/s]
Loading 0:  51%|█████     | 185/363 [02:32<01:36,  1.84it/s]
Loading 0:  51%|█████     | 186/363 [02:32<01:19,  2.23it/s]
Loading 0:  52%|█████▏    | 187/363 [02:32<01:05,  2.68it/s]
Loading 0:  52%|█████▏    | 188/363 [02:34<02:32,  1.15it/s]
Loading 0:  52%|█████▏    | 189/363 [02:36<03:39,  1.26s/it]
Loading 0:  53%|█████▎    | 192/363 [02:39<02:47,  1.02it/s]
Loading 0:  53%|█████▎    | 193/363 [02:41<03:29,  1.23s/it]
Loading 0:  53%|█████▎    | 194/363 [02:43<04:09,  1.48s/it]
Loading 0:  54%|█████▍    | 197/363 [02:43<02:13,  1.24it/s]
Loading 0:  55%|█████▍    | 198/363 [02:44<01:56,  1.42it/s]
Loading 0:  55%|█████▍    | 199/363 [02:44<01:35,  1.71it/s]
Loading 0:  55%|█████▌    | 201/363 [02:46<02:07,  1.27it/s]
Loading 0:  56%|█████▌    | 202/363 [02:48<02:55,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [02:51<03:40,  1.38s/it]
Loading 0:  57%|█████▋    | 206/363 [02:51<01:57,  1.34it/s]
Loading 0:  57%|█████▋    | 207/363 [02:51<01:42,  1.52it/s]
Loading 0:  57%|█████▋    | 208/363 [02:51<01:24,  1.84it/s]
Loading 0:  58%|█████▊    | 210/363 [02:54<01:56,  1.31it/s]
Loading 0:  58%|█████▊    | 211/363 [02:56<02:43,  1.07s/it]
Loading 0:  58%|█████▊    | 212/363 [02:58<03:25,  1.36s/it]
Loading 0:  59%|█████▉    | 215/363 [02:58<01:48,  1.36it/s]
Loading 0:  60%|█████▉    | 216/363 [02:59<01:35,  1.54it/s]
Loading 0:  60%|█████▉    | 217/363 [02:59<01:18,  1.86it/s]
Loading 0:  60%|██████    | 218/363 [03:01<02:15,  1.07it/s]
Loading 0:  60%|██████    | 219/363 [03:03<03:05,  1.29s/it]
Loading 0:  61%|██████    | 221/363 [03:04<01:56,  1.22it/s]
Loading 0:  61%|██████    | 222/363 [03:04<01:38,  1.44it/s]
Loading 0:  61%|██████▏   | 223/363 [03:04<01:18,  1.79it/s]
Loading 0:  62%|██████▏   | 224/363 [03:04<01:03,  2.20it/s]
Loading 0:  62%|██████▏   | 225/363 [03:07<02:09,  1.06it/s]
Loading 0:  63%|██████▎   | 228/363 [03:09<01:52,  1.20it/s]
Loading 0:  63%|██████▎   | 229/363 [03:11<02:29,  1.11s/it]
Loading 0:  63%|██████▎   | 230/363 [03:13<03:03,  1.38s/it]
Loading 0:  64%|██████▍   | 233/363 [03:14<01:38,  1.32it/s]
Loading 0:  64%|██████▍   | 234/363 [03:14<01:26,  1.50it/s]
Loading 0:  65%|██████▍   | 235/363 [03:14<01:11,  1.80it/s]
Loading 0:  65%|██████▌   | 237/363 [03:16<01:36,  1.31it/s]
Loading 0:  66%|██████▌   | 238/363 [03:19<02:14,  1.08s/it]
Loading 0:  66%|██████▌   | 239/363 [03:21<02:48,  1.36s/it]
Loading 0:  67%|██████▋   | 242/363 [03:21<01:29,  1.36it/s]
Loading 0:  67%|██████▋   | 243/363 [03:21<01:17,  1.54it/s]
Loading 0:  67%|██████▋   | 244/363 [03:22<01:04,  1.86it/s]
Loading 0:  68%|██████▊   | 246/363 [03:24<01:28,  1.32it/s]
Loading 0:  68%|██████▊   | 247/363 [03:26<02:04,  1.07s/it]
Loading 0:  68%|██████▊   | 248/363 [03:28<02:36,  1.36s/it]
Loading 0:  69%|██████▉   | 251/363 [03:29<01:22,  1.36it/s]
Loading 0:  69%|██████▉   | 252/363 [03:29<01:11,  1.54it/s]
Loading 0:  70%|██████▉   | 253/363 [03:29<00:59,  1.86it/s]
Loading 0:  70%|███████   | 255/363 [03:31<01:21,  1.32it/s]
Loading 0:  71%|███████   | 256/363 [03:34<01:54,  1.07s/it]
Loading 0:  71%|███████   | 257/363 [03:36<02:23,  1.36s/it]
Loading 0:  72%|███████▏  | 260/363 [03:36<01:15,  1.36it/s]
Loading 0:  72%|███████▏  | 261/363 [03:37<01:05,  1.55it/s]
Loading 0:  72%|███████▏  | 262/363 [03:37<00:54,  1.86it/s]
Loading 0:  73%|███████▎  | 264/363 [03:37<00:39,  2.51it/s]
Loading 0:  73%|███████▎  | 265/363 [03:37<00:36,  2.68it/s]
Loading 0:  73%|███████▎  | 266/363 [03:37<00:30,  3.16it/s]
Loading 0:  74%|███████▎  | 267/363 [03:38<00:26,  3.61it/s]
Loading 0:  74%|███████▍  | 268/363 [03:40<01:15,  1.26it/s]
Loading 0:  74%|███████▍  | 269/363 [03:42<01:50,  1.18s/it]
Loading 0:  74%|███████▍  | 270/363 [03:44<02:19,  1.50s/it]
Loading 0:  75%|███████▌  | 273/363 [04:01<05:36,  3.74s/it]
Loading 0:  75%|███████▌  | 274/363 [04:03<05:04,  3.42s/it]
Loading 0:  76%|███████▌  | 275/363 [04:06<04:38,  3.17s/it]
Loading 0:  77%|███████▋  | 278/363 [04:06<02:20,  1.66s/it]
Loading 0:  77%|███████▋  | 279/363 [04:06<01:56,  1.39s/it]
Loading 0:  77%|███████▋  | 280/363 [04:06<01:32,  1.12s/it]
Loading 0:  78%|███████▊  | 282/363 [04:09<01:30,  1.12s/it]
Loading 0:  78%|███████▊  | 283/363 [04:11<01:47,  1.35s/it]
Loading 0:  78%|███████▊  | 284/363 [04:13<02:03,  1.57s/it]
Loading 0:  79%|███████▉  | 287/363 [04:13<01:03,  1.20it/s]
Loading 0:  79%|███████▉  | 288/363 [04:14<00:53,  1.39it/s]
Loading 0:  80%|███████▉  | 289/363 [04:14<00:43,  1.69it/s]
Loading 0:  80%|████████  | 291/363 [04:16<00:56,  1.27it/s]
Loading 0:  80%|████████  | 292/363 [04:18<01:17,  1.09s/it]
Loading 0:  81%|████████  | 293/363 [04:20<01:35,  1.37s/it]
Loading 0:  82%|████████▏ | 296/363 [04:21<00:49,  1.36it/s]
Loading 0:  82%|████████▏ | 297/363 [04:21<00:42,  1.57it/s]
Loading 0:  82%|████████▏ | 298/363 [04:21<00:34,  1.89it/s]
Loading 0:  82%|████████▏ | 299/363 [04:23<00:59,  1.08it/s]
Loading 0:  83%|████████▎ | 301/363 [04:24<00:38,  1.63it/s]
Loading 0:  83%|████████▎ | 302/363 [04:24<00:32,  1.89it/s]
Loading 0:  83%|████████▎ | 303/363 [04:24<00:26,  2.29it/s]
Loading 0:  84%|████████▎ | 304/363 [04:24<00:21,  2.74it/s]
Loading 0:  84%|████████▍ | 305/363 [04:26<00:49,  1.16it/s]
Loading 0:  84%|████████▍ | 306/363 [04:29<01:11,  1.26s/it]
Loading 0:  85%|████████▌ | 309/363 [04:31<00:52,  1.02it/s]
Loading 0:  85%|████████▌ | 310/363 [04:33<01:05,  1.23s/it]
Loading 0:  86%|████████▌ | 311/363 [04:35<01:16,  1.47s/it]
Loading 0:  87%|████████▋ | 314/363 [04:36<00:39,  1.26it/s]
Loading 0:  87%|████████▋ | 315/363 [04:36<00:33,  1.45it/s]
Loading 0:  87%|████████▋ | 316/363 [04:36<00:26,  1.75it/s]
Loading 0:  88%|████████▊ | 318/363 [04:38<00:34,  1.29it/s]
Loading 0:  88%|████████▊ | 319/363 [04:40<00:47,  1.08s/it]
Loading 0:  88%|████████▊ | 320/363 [04:43<00:58,  1.36s/it]
Loading 0:  89%|████████▉ | 323/363 [04:43<00:29,  1.37it/s]
Loading 0:  89%|████████▉ | 324/363 [04:43<00:24,  1.57it/s]
Loading 0:  90%|████████▉ | 325/363 [04:43<00:20,  1.89it/s]
Loading 0:  90%|█████████ | 327/363 [04:46<00:26,  1.33it/s]
Loading 0:  90%|█████████ | 328/363 [04:48<00:37,  1.06s/it]
Loading 0:  91%|█████████ | 329/363 [04:50<00:45,  1.35s/it]
Loading 0:  91%|█████████▏| 332/363 [04:50<00:22,  1.38it/s]
Loading 0:  92%|█████████▏| 333/363 [04:51<00:18,  1.58it/s]
Loading 0:  92%|█████████▏| 334/363 [04:51<00:15,  1.91it/s]
Loading 0:  92%|█████████▏| 335/363 [04:53<00:25,  1.08it/s]
Loading 0:  93%|█████████▎| 336/363 [04:55<00:34,  1.27s/it]
Loading 0:  93%|█████████▎| 338/363 [04:56<00:19,  1.25it/s]
Loading 0:  93%|█████████▎| 339/363 [04:56<00:16,  1.49it/s]
Loading 0:  94%|█████████▎| 340/363 [04:56<00:12,  1.86it/s]
Loading 0:  94%|█████████▍| 341/363 [04:56<00:10,  2.07it/s]
Loading 0:  94%|█████████▍| 343/363 [04:59<00:15,  1.33it/s]
Loading 0:  95%|█████████▌| 346/363 [05:01<00:12,  1.34it/s]
Loading 0:  96%|█████████▌| 347/363 [05:03<00:16,  1.02s/it]
Loading 0:  96%|█████████▌| 348/363 [05:05<00:19,  1.28s/it]
Loading 0:  97%|█████████▋| 351/363 [05:06<00:08,  1.38it/s]
Loading 0:  97%|█████████▋| 352/363 [05:06<00:07,  1.57it/s]
Loading 0:  97%|█████████▋| 353/363 [05:06<00:05,  1.87it/s]
Loading 0:  98%|█████████▊| 355/363 [05:08<00:06,  1.32it/s]
Loading 0:  98%|█████████▊| 356/363 [05:10<00:07,  1.06s/it]
Loading 0:  98%|█████████▊| 357/363 [05:13<00:08,  1.35s/it]
Loading 0:  99%|█████████▉| 360/363 [05:13<00:02,  1.37it/s]
Loading 0:  99%|█████████▉| 361/363 [05:13<00:01,  1.57it/s]
Loading 0: 100%|█████████▉| 362/363 [05:13<00:00,  1.89it/s]
                                                            
Job chaiml-cai-real-v3-cosine-v12-mkmlizer completed after 422.02s with status: succeeded
Stopping job with name chaiml-cai-real-v3-cosine-v12-mkmlizer
Pipeline stage MKMLizer completed in 424.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-real-v3-cosine-v12
Waiting for inference service chaiml-cai-real-v3-cosine-v12 to be ready
Inference service chaiml-cai-real-v3-cosine-v12 ready after 171.81818914413452s
Pipeline stage MKMLDeployer completed in 173.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.821687936782837s
Received healthy response to inference request in 3.564507246017456s
Received healthy response to inference request in 3.967862367630005s
Received healthy response to inference request in 3.4564032554626465s
Received healthy response to inference request in 3.6177585124969482s
5 requests
0 failed requests
5th percentile: 3.478024053573608
10th percentile: 3.4996448516845704
20th percentile: 3.5428864479064943
30th percentile: 3.5751574993133546
40th percentile: 3.596458005905151
50th percentile: 3.6177585124969482
60th percentile: 3.757800054550171
70th percentile: 3.8978415966033935
80th percentile: 4.538627481460572
90th percentile: 5.680157709121705
95th percentile: 6.25092282295227
99th percentile: 6.7075349140167235
mean time: 4.285643863677978
%s, retrying in %s seconds...
Received healthy response to inference request in 3.345113515853882s
Received healthy response to inference request in 3.501085042953491s
Received healthy response to inference request in 3.3506555557250977s
Received healthy response to inference request in 3.515028715133667s
Received healthy response to inference request in 3.3038785457611084s
5 requests
0 failed requests
5th percentile: 3.312125539779663
10th percentile: 3.320372533798218
20th percentile: 3.336866521835327
30th percentile: 3.346221923828125
40th percentile: 3.3484387397766113
50th percentile: 3.3506555557250977
60th percentile: 3.4108273506164553
70th percentile: 3.4709991455078124
80th percentile: 3.5038737773895265
90th percentile: 3.5094512462615968
95th percentile: 3.5122399806976317
99th percentile: 3.51447096824646
mean time: 3.403152275085449
Pipeline stage StressChecker completed in 41.37s
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 1.25s
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 1.01s
Shutdown handler de-registered
chaiml-cai-real-v3-cosine_v12 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3436.97s
Shutdown handler de-registered