chaiml-ca18-fd43-linear-w01

developer_uid: zonemercy
submission_id: chaiml-ca18-fd43-linear-w01_v4
model_name: chaiml-ca18-fd43-linear-w01_v4
model_group: ChaiML/ca18-fd43-linear-
status: torndown
timestamp: 2025-10-08T13:31:16+00:00
num_battles: 6036
num_wins: 3485
celo_rating: 1289.4
family_friendly_score: 0.5116
family_friendly_standard_error: 0.007069164589963937
submission_type: basic
model_repo: ChaiML/ca18-fd43-linear-w01
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1280
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.8845934255855223, 'latency_mean': 1.1303403198719024, 'latency_p50': 1.129500389099121, 'latency_p90': 1.2532025098800659}, {'batch_size': 4, 'throughput': 2.0277239878450577, 'latency_mean': 1.963984466791153, 'latency_p50': 1.9574729204177856, 'latency_p90': 2.1863658666610717}, {'batch_size': 5, 'throughput': 2.2310110748985204, 'latency_mean': 2.227952711582184, 'latency_p50': 2.2123637199401855, 'latency_p90': 2.529826831817627}, {'batch_size': 8, 'throughput': 2.5868696240539384, 'latency_mean': 3.0620370161533357, 'latency_p50': 3.0664050579071045, 'latency_p90': 3.4682735443115233}, {'batch_size': 10, 'throughput': 2.697589755407314, 'latency_mean': 3.6739510130882262, 'latency_p50': 3.6938652992248535, 'latency_p90': 4.166074109077454}, {'batch_size': 12, 'throughput': 2.7848884354392776, 'latency_mean': 4.260143562555313, 'latency_p50': 4.253955245018005, 'latency_p90': 4.87185161113739}, {'batch_size': 15, 'throughput': 2.8374473089250003, 'latency_mean': 5.217838190793991, 'latency_p50': 5.193621873855591, 'latency_p90': 6.004391574859619}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-ca18-fd43-linear-w01_v4
is_internal_developer: True
language_model: ChaiML/ca18-fd43-linear-w01
model_size: 13B
ranking_group: single
throughput_3p7s: 2.73
us_pacific_date: 2025-10-08
win_ratio: 0.5773691186216037
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.15, 'frequency_penalty': 0.15, 'stopping_words': ['\n', '</s>', 'You:', '###'], 'max_input_tokens': 1280, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-ca18-fd43-linear-w01-v4-mkmlizer
Waiting for job on chaiml-ca18-fd43-linear-w01-v4-mkmlizer to finish
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║                                                                     ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║                                                                     ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║                                                                     ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║                                                                     ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ║                                                                     ║
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: Downloaded to shared memory in 29.474s
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: Checking if ChaiML/ca18-fd43-linear-w01 already exists in ChaiML
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp518ybsrm, device:0
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-ca18-fd43-linear-w01-v4-mkmlizer: quantized model in 143.402s
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: Processed model ChaiML/ca18-fd43-linear-w01 in 172.876s
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-fd43-linear-w01-v4/nvidia
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-fd43-linear-w01-v4/nvidia/config.json
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-fd43-linear-w01-v4/nvidia/special_tokens_map.json
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-fd43-linear-w01-v4/nvidia/tokenizer_config.json
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-fd43-linear-w01-v4/nvidia/tokenizer.json
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-fd43-linear-w01-v4/nvidia/flywheel_model.0.safetensors
chaiml-ca18-fd43-linear-w01-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:30, 12.01it/s]
Loading 0:   1%|          | 4/363 [00:01<01:42,  3.52it/s]
Loading 0:   1%|▏         | 5/363 [00:01<02:42,  2.20it/s]
Loading 0:   2%|▏         | 6/363 [00:02<03:34,  1.67it/s]
Loading 0:   2%|▏         | 9/363 [00:03<01:54,  3.09it/s]
Loading 0:   3%|▎         | 10/363 [00:03<01:50,  3.18it/s]
Loading 0:   3%|▎         | 11/363 [00:03<01:36,  3.65it/s]
Loading 0:   4%|▎         | 13/363 [00:04<01:58,  2.96it/s]
Loading 0:   4%|▍         | 14/363 [00:05<02:38,  2.20it/s]
Loading 0:   4%|▍         | 15/363 [00:06<03:18,  1.76it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:54,  3.01it/s]
Loading 0:   5%|▌         | 19/363 [00:06<01:48,  3.17it/s]
Loading 0:   6%|▌         | 20/363 [00:06<01:33,  3.66it/s]
Loading 0:   6%|▌         | 22/363 [00:07<01:53,  3.00it/s]
Loading 0:   6%|▋         | 23/363 [00:08<02:31,  2.25it/s]
Loading 0:   7%|▋         | 24/363 [00:09<03:08,  1.80it/s]
Loading 0:   7%|▋         | 27/363 [00:09<01:50,  3.04it/s]
Loading 0:   8%|▊         | 28/363 [00:10<01:44,  3.20it/s]
Loading 0:   8%|▊         | 29/363 [00:10<01:30,  3.69it/s]
Loading 0:   9%|▊         | 31/363 [00:11<01:50,  3.02it/s]
Loading 0:   9%|▉         | 32/363 [00:11<02:26,  2.26it/s]
Loading 0:   9%|▉         | 33/363 [00:12<03:04,  1.79it/s]
Loading 0:  10%|▉         | 36/363 [00:13<01:46,  3.06it/s]
Loading 0:  10%|█         | 37/363 [00:13<01:41,  3.22it/s]
Loading 0:  10%|█         | 38/363 [00:13<01:27,  3.72it/s]
Loading 0:  11%|█         | 40/363 [00:14<01:55,  2.79it/s]
Loading 0:  11%|█▏        | 41/363 [00:15<02:29,  2.15it/s]
Loading 0:  12%|█▏        | 42/363 [00:16<03:04,  1.74it/s]
Loading 0:  12%|█▏        | 45/363 [00:16<01:47,  2.97it/s]
Loading 0:  13%|█▎        | 46/363 [00:16<01:41,  3.13it/s]
Loading 0:  13%|█▎        | 47/363 [00:16<01:27,  3.63it/s]
Loading 0:  13%|█▎        | 49/363 [00:17<01:44,  3.00it/s]
Loading 0:  14%|█▍        | 50/363 [00:18<02:18,  2.25it/s]
Loading 0:  14%|█▍        | 51/363 [00:19<02:53,  1.80it/s]
Loading 0:  15%|█▍        | 54/363 [00:19<01:40,  3.09it/s]
Loading 0:  15%|█▌        | 55/363 [00:20<01:35,  3.24it/s]
Loading 0:  15%|█▌        | 56/363 [00:20<01:22,  3.74it/s]
Loading 0:  16%|█▌        | 58/363 [00:21<01:40,  3.05it/s]
Loading 0:  16%|█▋        | 59/363 [00:21<02:14,  2.27it/s]
Loading 0:  17%|█▋        | 60/363 [00:22<02:48,  1.80it/s]
Loading 0:  17%|█▋        | 63/363 [00:23<01:37,  3.08it/s]
Loading 0:  18%|█▊        | 64/363 [00:23<01:32,  3.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:23<01:19,  3.74it/s]
Loading 0:  18%|█▊        | 67/363 [00:24<01:37,  3.04it/s]
Loading 0:  19%|█▊        | 68/363 [00:25<02:10,  2.27it/s]
Loading 0:  19%|█▉        | 69/363 [00:26<02:42,  1.80it/s]
Loading 0:  20%|█▉        | 72/363 [00:26<01:34,  3.09it/s]
Loading 0:  20%|██        | 73/363 [00:26<01:29,  3.24it/s]
Loading 0:  20%|██        | 74/363 [00:26<01:17,  3.74it/s]
Loading 0:  21%|██        | 76/363 [00:27<01:34,  3.04it/s]
Loading 0:  21%|██        | 77/363 [00:28<02:06,  2.27it/s]
Loading 0:  21%|██▏       | 78/363 [00:29<02:37,  1.81it/s]
Loading 0:  22%|██▏       | 81/363 [00:29<01:31,  3.09it/s]
Loading 0:  23%|██▎       | 82/363 [00:29<01:26,  3.24it/s]
Loading 0:  23%|██▎       | 83/363 [00:30<01:14,  3.74it/s]
Loading 0:  23%|██▎       | 85/363 [00:30<01:31,  3.02it/s]
Loading 0:  24%|██▎       | 86/363 [00:31<02:02,  2.26it/s]
Loading 0:  24%|██▍       | 87/363 [00:32<02:32,  1.81it/s]
Loading 0:  25%|██▍       | 90/363 [00:32<01:28,  3.07it/s]
Loading 0:  25%|██▌       | 91/363 [00:33<01:24,  3.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:33<01:13,  3.70it/s]
Loading 0:  26%|██▌       | 94/363 [00:34<01:28,  3.03it/s]
Loading 0:  26%|██▌       | 95/363 [00:35<01:58,  2.26it/s]
Loading 0:  26%|██▋       | 96/363 [00:35<02:27,  1.81it/s]
Loading 0:  27%|██▋       | 99/363 [00:36<01:26,  3.06it/s]
Loading 0:  28%|██▊       | 100/363 [00:36<01:21,  3.22it/s]
Loading 0:  28%|██▊       | 101/363 [00:36<01:10,  3.71it/s]
Loading 0:  28%|██▊       | 103/363 [00:37<01:25,  3.04it/s]
Loading 0:  29%|██▊       | 104/363 [00:38<01:54,  2.27it/s]
Loading 0:  29%|██▉       | 105/363 [00:39<02:22,  1.81it/s]
Loading 0:  30%|██▉       | 108/363 [00:39<01:23,  3.05it/s]
Loading 0:  30%|███       | 109/363 [00:39<01:19,  3.21it/s]
Loading 0:  30%|███       | 110/363 [00:39<01:08,  3.70it/s]
Loading 0:  31%|███       | 112/363 [00:40<01:22,  3.03it/s]
Loading 0:  31%|███       | 113/363 [00:41<01:50,  2.26it/s]
Loading 0:  31%|███▏      | 114/363 [00:42<02:18,  1.80it/s]
Loading 0:  32%|███▏      | 117/363 [00:42<01:20,  3.04it/s]
Loading 0:  33%|███▎      | 118/363 [00:43<01:16,  3.20it/s]
Loading 0:  33%|███▎      | 119/363 [00:43<01:05,  3.70it/s]
Loading 0:  33%|███▎      | 121/363 [00:44<01:25,  2.82it/s]
Loading 0:  34%|███▎      | 122/363 [00:45<01:50,  2.17it/s]
Loading 0:  34%|███▍      | 123/363 [00:45<02:16,  1.76it/s]
Loading 0:  35%|███▍      | 126/363 [00:46<01:18,  3.02it/s]
Loading 0:  35%|███▍      | 127/363 [00:46<01:14,  3.19it/s]
Loading 0:  35%|███▌      | 128/363 [00:46<01:03,  3.68it/s]
Loading 0:  36%|███▌      | 130/363 [00:47<01:16,  3.03it/s]
Loading 0:  36%|███▌      | 131/363 [00:48<01:42,  2.26it/s]
Loading 0:  36%|███▋      | 132/363 [00:49<02:07,  1.81it/s]
Loading 0:  37%|███▋      | 135/363 [00:49<01:14,  3.05it/s]
Loading 0:  37%|███▋      | 136/363 [00:49<01:10,  3.21it/s]
Loading 0:  38%|███▊      | 137/363 [00:49<01:01,  3.70it/s]
Loading 0:  38%|███▊      | 139/363 [00:50<01:13,  3.04it/s]
Loading 0:  39%|███▊      | 140/363 [00:51<01:38,  2.27it/s]
Loading 0:  39%|███▉      | 141/363 [00:52<02:02,  1.81it/s]
Loading 0:  40%|███▉      | 144/363 [00:52<01:11,  3.06it/s]
Loading 0:  40%|███▉      | 145/363 [00:53<01:07,  3.22it/s]
Loading 0:  40%|████      | 146/363 [00:53<00:58,  3.71it/s]
Loading 0:  41%|████      | 148/363 [00:54<01:10,  3.04it/s]
Loading 0:  41%|████      | 149/363 [00:54<01:34,  2.27it/s]
Loading 0:  41%|████▏     | 150/363 [00:55<01:58,  1.80it/s]
Loading 0:  42%|████▏     | 153/363 [00:56<01:08,  3.05it/s]
Loading 0:  42%|████▏     | 154/363 [00:56<01:05,  3.21it/s]
Loading 0:  43%|████▎     | 155/363 [00:56<00:56,  3.70it/s]
Loading 0:  43%|████▎     | 157/363 [00:57<01:07,  3.03it/s]
Loading 0:  44%|████▎     | 158/363 [00:58<01:30,  2.27it/s]
Loading 0:  44%|████▍     | 159/363 [00:59<01:52,  1.82it/s]
Loading 0:  45%|████▍     | 162/363 [00:59<01:05,  3.07it/s]
Loading 0:  45%|████▍     | 163/363 [00:59<01:02,  3.22it/s]
Loading 0:  45%|████▌     | 164/363 [00:59<00:53,  3.72it/s]
Loading 0:  46%|████▌     | 166/363 [01:00<01:04,  3.05it/s]
Loading 0:  46%|████▌     | 167/363 [01:01<01:26,  2.28it/s]
Loading 0:  46%|████▋     | 168/363 [01:02<01:47,  1.81it/s]
Loading 0:  47%|████▋     | 171/363 [01:02<01:02,  3.06it/s]
Loading 0:  47%|████▋     | 172/363 [01:02<00:59,  3.22it/s]
Loading 0:  48%|████▊     | 173/363 [01:03<00:51,  3.71it/s]
Loading 0:  48%|████▊     | 175/363 [01:03<01:01,  3.04it/s]
Loading 0:  48%|████▊     | 176/363 [01:04<01:22,  2.27it/s]
Loading 0:  49%|████▉     | 177/363 [01:05<01:42,  1.82it/s]
Loading 0:  50%|████▉     | 180/363 [01:06<00:59,  3.07it/s]
Loading 0:  50%|████▉     | 181/363 [01:06<00:56,  3.22it/s]
Loading 0:  50%|█████     | 182/363 [01:06<00:48,  3.71it/s]
Loading 0:  51%|█████     | 184/363 [01:07<00:58,  3.04it/s]
Loading 0:  51%|█████     | 185/363 [01:08<01:18,  2.27it/s]
Loading 0:  51%|█████     | 186/363 [01:09<01:38,  1.80it/s]
Loading 0:  52%|█████▏    | 189/363 [01:09<00:56,  3.08it/s]
Loading 0:  52%|█████▏    | 190/363 [01:09<00:53,  3.24it/s]
Loading 0:  53%|█████▎    | 191/363 [01:09<00:46,  3.73it/s]
Loading 0:  53%|█████▎    | 193/363 [01:10<00:55,  3.06it/s]
Loading 0:  53%|█████▎    | 194/363 [01:11<01:13,  2.29it/s]
Loading 0:  54%|█████▎    | 195/363 [01:12<01:32,  1.83it/s]
Loading 0:  55%|█████▍    | 198/363 [01:12<00:52,  3.12it/s]
Loading 0:  55%|█████▍    | 199/363 [01:12<00:50,  3.27it/s]
Loading 0:  55%|█████▌    | 200/363 [01:12<00:43,  3.75it/s]
Loading 0:  56%|█████▌    | 202/363 [01:13<00:56,  2.83it/s]
Loading 0:  56%|█████▌    | 203/363 [01:14<01:13,  2.19it/s]
Loading 0:  56%|█████▌    | 204/363 [01:15<01:29,  1.78it/s]
Loading 0:  57%|█████▋    | 207/363 [01:15<00:51,  3.05it/s]
Loading 0:  57%|█████▋    | 208/363 [01:16<00:48,  3.21it/s]
Loading 0:  58%|█████▊    | 209/363 [01:16<00:41,  3.72it/s]
Loading 0:  58%|█████▊    | 211/363 [01:17<00:49,  3.04it/s]
Loading 0:  58%|█████▊    | 212/363 [01:17<01:06,  2.28it/s]
Loading 0:  59%|█████▊    | 213/363 [01:18<01:22,  1.82it/s]
Loading 0:  60%|█████▉    | 216/363 [01:19<00:47,  3.09it/s]
Loading 0:  60%|█████▉    | 217/363 [01:19<00:45,  3.24it/s]
Loading 0:  60%|██████    | 218/363 [01:19<00:39,  3.69it/s]
Loading 0:  61%|██████    | 220/363 [01:20<00:47,  3.04it/s]
Loading 0:  61%|██████    | 221/363 [01:21<01:02,  2.27it/s]
Loading 0:  61%|██████    | 222/363 [01:22<01:17,  1.82it/s]
Loading 0:  62%|██████▏   | 225/363 [01:22<00:44,  3.10it/s]
Loading 0:  62%|██████▏   | 226/363 [01:22<00:42,  3.26it/s]
Loading 0:  63%|██████▎   | 227/363 [01:22<00:36,  3.74it/s]
Loading 0:  63%|██████▎   | 229/363 [01:23<00:43,  3.06it/s]
Loading 0:  63%|██████▎   | 230/363 [01:24<00:58,  2.28it/s]
Loading 0:  64%|██████▎   | 231/363 [01:25<01:12,  1.83it/s]
Loading 0:  64%|██████▍   | 234/363 [01:25<00:41,  3.12it/s]
Loading 0:  65%|██████▍   | 235/363 [01:25<00:39,  3.28it/s]
Loading 0:  65%|██████▌   | 236/363 [01:26<00:33,  3.78it/s]
Loading 0:  66%|██████▌   | 238/363 [01:26<00:40,  3.07it/s]
Loading 0:  66%|██████▌   | 239/363 [01:27<00:54,  2.29it/s]
Loading 0:  66%|██████▌   | 240/363 [01:28<01:07,  1.83it/s]
Loading 0:  67%|██████▋   | 243/363 [01:28<00:38,  3.10it/s]
Loading 0:  67%|██████▋   | 244/363 [01:29<00:36,  3.25it/s]
Loading 0:  67%|██████▋   | 245/363 [01:29<00:31,  3.75it/s]
Loading 0:  68%|██████▊   | 247/363 [01:30<00:37,  3.07it/s]
Loading 0:  68%|██████▊   | 248/363 [01:31<00:50,  2.29it/s]
Loading 0:  69%|██████▊   | 249/363 [01:31<01:02,  1.81it/s]
Loading 0:  69%|██████▉   | 252/363 [01:32<00:35,  3.09it/s]
Loading 0:  70%|██████▉   | 253/363 [01:32<00:33,  3.25it/s]
Loading 0:  70%|██████▉   | 254/363 [01:32<00:29,  3.75it/s]
Loading 0:  71%|███████   | 256/363 [01:33<00:34,  3.06it/s]
Loading 0:  71%|███████   | 257/363 [01:34<00:46,  2.29it/s]
Loading 0:  71%|███████   | 258/363 [01:35<00:57,  1.83it/s]
Loading 0:  72%|███████▏  | 261/363 [01:35<00:32,  3.13it/s]
Loading 0:  72%|███████▏  | 262/363 [01:35<00:30,  3.28it/s]
Loading 0:  72%|███████▏  | 263/363 [01:35<00:26,  3.78it/s]
Loading 0:  73%|███████▎  | 265/363 [01:36<00:31,  3.07it/s]
Loading 0:  73%|███████▎  | 266/363 [01:37<00:42,  2.29it/s]
Loading 0:  74%|███████▎  | 267/363 [01:38<00:52,  1.82it/s]
Loading 0:  74%|███████▍  | 270/363 [01:38<00:29,  3.12it/s]
Loading 0:  75%|███████▍  | 271/363 [01:38<00:28,  3.27it/s]
Loading 0:  75%|███████▍  | 272/363 [01:39<00:24,  3.78it/s]
Loading 0:  75%|███████▌  | 274/363 [01:39<00:29,  3.06it/s]
Loading 0:  76%|███████▌  | 275/363 [01:40<00:38,  2.29it/s]
Loading 0:  76%|███████▌  | 276/363 [01:41<00:47,  1.83it/s]
Loading 0:  77%|███████▋  | 279/363 [01:41<00:26,  3.12it/s]
Loading 0:  77%|███████▋  | 280/363 [01:42<00:25,  3.27it/s]
Loading 0:  77%|███████▋  | 281/363 [01:42<00:21,  3.77it/s]
Loading 0:  78%|███████▊  | 283/363 [01:43<00:28,  2.85it/s]
Loading 0:  78%|███████▊  | 284/363 [01:44<00:36,  2.18it/s]
Loading 0:  79%|███████▊  | 285/363 [01:45<00:44,  1.77it/s]
Loading 0:  79%|███████▉  | 288/363 [01:45<00:24,  3.04it/s]
Loading 0:  80%|███████▉  | 289/363 [01:45<00:23,  3.20it/s]
Loading 0:  80%|███████▉  | 290/363 [01:45<00:19,  3.70it/s]
Loading 0:  80%|████████  | 292/363 [01:46<00:23,  3.03it/s]
Loading 0:  81%|████████  | 293/363 [01:47<00:30,  2.27it/s]
Loading 0:  81%|████████  | 294/363 [01:48<00:38,  1.81it/s]
Loading 0:  82%|████████▏ | 297/363 [01:48<00:21,  3.08it/s]
Loading 0:  82%|████████▏ | 298/363 [01:48<00:20,  3.23it/s]
Loading 0:  82%|████████▏ | 299/363 [01:48<00:17,  3.74it/s]
Loading 0:  83%|████████▎ | 301/363 [01:49<00:20,  3.01it/s]
Loading 0:  83%|████████▎ | 302/363 [01:50<00:26,  2.26it/s]
Loading 0:  83%|████████▎ | 303/363 [01:51<00:33,  1.81it/s]
Loading 0:  84%|████████▍ | 306/363 [01:51<00:18,  3.06it/s]
Loading 0:  85%|████████▍ | 307/363 [01:52<00:17,  3.22it/s]
Loading 0:  85%|████████▍ | 308/363 [01:52<00:14,  3.71it/s]
Loading 0:  85%|████████▌ | 310/363 [01:53<00:17,  3.04it/s]
Loading 0:  86%|████████▌ | 311/363 [01:53<00:22,  2.27it/s]
Loading 0:  86%|████████▌ | 312/363 [01:54<00:28,  1.81it/s]
Loading 0:  87%|████████▋ | 315/363 [01:55<00:15,  3.07it/s]
Loading 0:  87%|████████▋ | 316/363 [01:55<00:14,  3.22it/s]
Loading 0:  87%|████████▋ | 317/363 [01:55<00:12,  3.72it/s]
Loading 0:  88%|████████▊ | 319/363 [01:56<00:14,  3.04it/s]
Loading 0:  88%|████████▊ | 320/363 [01:57<00:18,  2.27it/s]
Loading 0:  88%|████████▊ | 321/363 [01:58<00:23,  1.81it/s]
Loading 0:  89%|████████▉ | 324/363 [01:58<00:12,  3.07it/s]
Loading 0:  90%|████████▉ | 325/363 [01:58<00:11,  3.22it/s]
Loading 0:  90%|████████▉ | 326/363 [01:58<00:09,  3.72it/s]
Loading 0:  90%|█████████ | 328/363 [01:59<00:11,  3.03it/s]
Loading 0:  91%|█████████ | 329/363 [02:00<00:15,  2.27it/s]
Loading 0:  91%|█████████ | 330/363 [02:01<00:18,  1.81it/s]
Loading 0:  92%|█████████▏| 333/363 [02:01<00:09,  3.06it/s]
Loading 0:  92%|█████████▏| 334/363 [02:02<00:09,  3.22it/s]
Loading 0:  92%|█████████▏| 335/363 [02:02<00:07,  3.70it/s]
Loading 0:  93%|█████████▎| 337/363 [02:02<00:08,  3.04it/s]
Loading 0:  93%|█████████▎| 338/363 [02:03<00:11,  2.27it/s]
Loading 0:  93%|█████████▎| 339/363 [02:04<00:13,  1.80it/s]
Loading 0:  94%|█████████▍| 342/363 [02:05<00:06,  3.05it/s]
Loading 0:  94%|█████████▍| 343/363 [02:05<00:06,  3.21it/s]
Loading 0:  95%|█████████▍| 344/363 [02:05<00:05,  3.69it/s]
Loading 0:  95%|█████████▌| 346/363 [02:06<00:05,  3.03it/s]
Loading 0:  96%|█████████▌| 347/363 [02:07<00:07,  2.26it/s]
Loading 0:  96%|█████████▌| 348/363 [02:08<00:08,  1.81it/s]
Loading 0:  97%|█████████▋| 351/363 [02:08<00:03,  3.06it/s]
Loading 0:  97%|█████████▋| 352/363 [02:08<00:03,  3.21it/s]
Loading 0:  97%|█████████▋| 353/363 [02:08<00:02,  3.70it/s]
Loading 0:  98%|█████████▊| 355/363 [02:09<00:02,  3.03it/s]
Loading 0:  98%|█████████▊| 356/363 [02:10<00:03,  2.26it/s]
Loading 0:  98%|█████████▊| 357/363 [02:11<00:03,  1.81it/s]
Loading 0:  99%|█████████▉| 360/363 [02:11<00:00,  3.06it/s]
Loading 0:  99%|█████████▉| 361/363 [02:11<00:00,  3.21it/s]
Loading 0: 100%|█████████▉| 362/363 [02:12<00:00,  3.70it/s]
                                                            
Job chaiml-ca18-fd43-linear-w01-v4-mkmlizer completed after 236.71s with status: succeeded
Stopping job with name chaiml-ca18-fd43-linear-w01-v4-mkmlizer
Pipeline stage MKMLizer completed in 237.36s
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-ca18-fd43-linear-w01-v4
Waiting for inference service chaiml-ca18-fd43-linear-w01-v4 to be ready
Inference service chaiml-ca18-fd43-linear-w01-v4 ready after 60.35303449630737s
Pipeline stage MKMLDeployer completed in 60.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8580286502838135s
Received healthy response to inference request in 1.5412318706512451s
Received healthy response to inference request in 1.341099739074707s
Received healthy response to inference request in 1.2796046733856201s
{"detail":"('http://chaiml-llama31-mer-v2-t-44570-v4-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:47142->127.0.0.1:8080: read: connection reset by peer\\n')"}
Received unhealthy response to inference request!
5 requests
1 failed requests
5th percentile: 1.173621702194214
10th percentile: 1.2001174449920655
20th percentile: 1.2531089305877685
30th percentile: 1.2919036865234375
40th percentile: 1.3165017127990724
50th percentile: 1.341099739074707
60th percentile: 1.4211525917053223
70th percentile: 1.5012054443359375
80th percentile: 1.6045912265777589
90th percentile: 1.7313099384307862
95th percentile: 1.7946692943572997
99th percentile: 1.8453567790985108
mean time: 1.4334181785583495
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6084535121917725s
Received healthy response to inference request in 1.3214421272277832s
Received healthy response to inference request in 1.1110970973968506s
Received healthy response to inference request in 1.1571693420410156s
Received healthy response to inference request in 1.185319423675537s
5 requests
0 failed requests
5th percentile: 1.1203115463256836
10th percentile: 1.1295259952545167
20th percentile: 1.1479548931121826
30th percentile: 1.16279935836792
40th percentile: 1.1740593910217285
50th percentile: 1.185319423675537
60th percentile: 1.2397685050964355
70th percentile: 1.294217586517334
80th percentile: 1.3788444042205812
90th percentile: 1.4936489582061767
95th percentile: 1.5510512351989745
99th percentile: 1.5969730567932128
mean time: 1.2766963005065919
Pipeline stage StressChecker completed in 16.40s
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 0.65s
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 0.71s
Shutdown handler de-registered
chaiml-ca18-fd43-linear-w01_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2089.13s
Shutdown handler de-registered
chaiml-ca18-fd43-linear-w01_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-fd43-linear-w01_v4 status is now torndown due to DeploymentManager action