developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_47271_v3
model_name: chaiml-mn24b-v2preferwi_47271_v3
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-21T00:32:39+00:00
num_battles: 6437
num_wins: 3404
celo_rating: 1276.7
family_friendly_score: 0.5680000000000001
family_friendly_standard_error: 0.007005369369276684
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_bo16_idxs4_tune4
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5464255735408241, 'latency_mean': 1.829975415468216, 'latency_p50': 1.821974277496338, 'latency_p90': 2.0573873996734617}, {'batch_size': 3, 'throughput': 1.1152678016871578, 'latency_mean': 2.689470410346985, 'latency_p50': 2.684749484062195, 'latency_p90': 3.0079631567001344}, {'batch_size': 5, 'throughput': 1.4229603534728803, 'latency_mean': 3.4889925897121428, 'latency_p50': 3.5077762603759766, 'latency_p90': 3.898178791999817}, {'batch_size': 6, 'throughput': 1.5397564588000856, 'latency_mean': 3.8557566452026366, 'latency_p50': 3.8633428812026978, 'latency_p90': 4.362718343734741}, {'batch_size': 8, 'throughput': 1.691255742158677, 'latency_mean': 4.681356000900268, 'latency_p50': 4.681846261024475, 'latency_p90': 5.358631539344787}, {'batch_size': 10, 'throughput': 1.7769507746128301, 'latency_mean': 5.596393451690674, 'latency_p50': 5.61071503162384, 'latency_p90': 6.506099581718445}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_47271_v3
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo16_idxs4_tune4
model_size: 24B
ranking_group: single
throughput_3p7s: 1.51
us_pacific_date: 2025-09-20
win_ratio: 0.5288177722541557
generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '\n<START>\n', '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-mn24b-v2preferwi-47271-v3-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-47271-v3-mkmlizer to finish
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ Version: 0.30.2 ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ belonging to: ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: Downloaded to shared memory in 64.667s
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo16_idxs4_tune4 already exists in ChaiML
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp0v6b0kjq, device:0
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: quantized model in 286.315s
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo16_idxs4_tune4 in 350.982s
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47271-v3/nvidia
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47271-v3/nvidia/config.json
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47271-v3/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47271-v3/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47271-v3/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47271-v3/nvidia/flywheel_model.0.safetensors
chaiml-mn24b-v2preferwi-47271-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:01<03:58, 1.51it/s] Loading 0: 1%| | 4/363 [00:03<06:27, 1.08s/it] Loading 0: 1%|▏ | 5/363 [00:05<08:15, 1.38s/it] Loading 0: 2%|▏ | 8/363 [00:06<03:50, 1.54it/s] Loading 0: 2%|▏ | 9/363 [00:06<03:22, 1.75it/s] Loading 0: 3%|▎ | 10/363 [00:06<02:44, 2.15it/s] Loading 0: 3%|▎ | 12/363 [00:08<03:55, 1.49it/s] Loading 0: 4%|▎ | 13/363 [00:10<05:35, 1.04it/s] Loading 0: 4%|▍ | 14/363 [00:12<07:10, 1.23s/it] Loading 0: 5%|▍ | 17/363 [00:13<03:48, 1.51it/s] Loading 0: 5%|▍ | 18/363 [00:13<03:25, 1.68it/s] Loading 0: 5%|▌ | 19/363 [00:13<02:49, 2.03it/s] Loading 0: 6%|▌ | 21/363 [00:15<03:52, 1.47it/s] Loading 0: 6%|▌ | 22/363 [00:17<05:26, 1.04it/s] Loading 0: 6%|▋ | 23/363 [00:19<06:51, 1.21s/it] Loading 0: 7%|▋ | 26/363 [00:19<03:39, 1.53it/s] Loading 0: 7%|▋ | 27/363 [00:19<03:12, 1.74it/s] Loading 0: 8%|▊ | 28/363 [00:20<02:40, 2.09it/s] Loading 0: 8%|▊ | 30/363 [00:20<01:57, 2.83it/s] Loading 0: 9%|▊ | 31/363 [00:20<01:48, 3.05it/s] Loading 0: 9%|▉ | 32/363 [00:20<01:32, 3.59it/s] Loading 0: 9%|▉ | 33/363 [00:20<01:20, 4.09it/s] Loading 0: 9%|▉ | 34/363 [00:22<03:49, 1.44it/s] Loading 0: 10%|▉ | 35/363 [00:24<05:41, 1.04s/it] Loading 0: 10%|▉ | 36/363 [00:26<07:13, 1.32s/it] Loading 0: 11%|█ | 39/363 [00:28<05:10, 1.04it/s] Loading 0: 11%|█ | 40/363 [00:30<06:16, 1.17s/it] Loading 0: 11%|█▏ | 41/363 [00:32<07:19, 1.36s/it] Loading 0: 12%|█▏ | 44/363 [00:33<03:55, 1.35it/s] Loading 0: 12%|█▏ | 45/363 [00:33<03:23, 1.56it/s] Loading 0: 13%|█▎ | 46/363 [00:33<02:47, 1.89it/s] Loading 0: 13%|█▎ | 48/363 [00:35<03:41, 1.42it/s] Loading 0: 13%|█▎ | 49/363 [00:37<05:04, 1.03it/s] Loading 0: 14%|█▍ | 50/363 [00:39<06:21, 1.22s/it] Loading 0: 15%|█▍ | 53/363 [00:39<03:24, 1.52it/s] Loading 0: 15%|█▍ | 54/363 [00:40<02:59, 1.73it/s] Loading 0: 15%|█▌ | 55/363 [00:40<02:27, 2.08it/s] Loading 0: 16%|█▌ | 57/363 [00:42<03:25, 1.49it/s] Loading 0: 16%|█▌ | 58/363 [00:44<04:49, 1.05it/s] Loading 0: 16%|█▋ | 59/363 [00:46<06:05, 1.20s/it] Loading 0: 17%|█▋ | 62/363 [00:46<03:15, 1.54it/s] Loading 0: 17%|█▋ | 63/363 [00:46<02:51, 1.75it/s] Loading 0: 18%|█▊ | 64/363 [00:46<02:21, 2.11it/s] Loading 0: 18%|█▊ | 65/363 [00:48<04:05, 1.21it/s] Loading 0: 18%|█▊ | 67/363 [00:49<02:43, 1.81it/s] Loading 0: 19%|█▊ | 68/363 [00:49<02:23, 2.06it/s] Loading 0: 19%|█▉ | 69/363 [00:49<01:57, 2.50it/s] Loading 0: 19%|█▉ | 70/363 [00:49<01:36, 3.03it/s] Loading 0: 20%|█▉ | 71/363 [00:51<03:44, 1.30it/s] Loading 0: 20%|█▉ | 72/363 [00:53<05:19, 1.10s/it] Loading 0: 20%|██ | 73/363 [00:55<06:36, 1.37s/it] Loading 0: 21%|██ | 76/363 [00:55<03:12, 1.49it/s] Loading 0: 21%|██ | 77/363 [00:56<02:46, 1.72it/s] Loading 0: 21%|██▏ | 78/363 [00:56<02:15, 2.10it/s] Loading 0: 22%|██▏ | 79/363 [00:58<03:59, 1.19it/s] Loading 0: 22%|██▏ | 80/363 [01:00<05:26, 1.15s/it] Loading 0: 23%|██▎ | 82/363 [01:00<03:23, 1.38it/s] Loading 0: 23%|██▎ | 83/363 [01:00<02:51, 1.63it/s] Loading 0: 23%|██▎ | 84/363 [01:00<02:16, 2.04it/s] Loading 0: 24%|██▎ | 86/363 [01:02<03:13, 1.44it/s] Loading 0: 24%|██▍ | 87/363 [01:04<04:37, 1.01s/it] Loading 0: 25%|██▍ | 90/363 [01:06<03:47, 1.20it/s] Loading 0: 25%|██▌ | 91/363 [01:08<04:45, 1.05s/it] Loading 0: 25%|██▌ | 92/363 [01:10<05:42, 1.26s/it] Loading 0: 26%|██▌ | 95/363 [01:11<03:09, 1.42it/s] Loading 0: 26%|██▋ | 96/363 [01:11<02:45, 1.61it/s] Loading 0: 27%|██▋ | 97/363 [01:11<02:17, 1.94it/s] Loading 0: 27%|██▋ | 99/363 [01:13<03:03, 1.44it/s] Loading 0: 28%|██▊ | 100/363 [01:15<04:13, 1.04it/s] Loading 0: 28%|██▊ | 101/363 [01:17<05:17, 1.21s/it] Loading 0: 29%|██▊ | 104/363 [01:17<02:50, 1.52it/s] Loading 0: 29%|██▉ | 105/363 [01:18<02:29, 1.72it/s] Loading 0: 29%|██▉ | 106/363 [01:18<02:03, 2.08it/s] Loading 0: 29%|██▉ | 107/363 [01:18<01:42, 2.50it/s] Loading 0: 30%|██▉ | 108/363 [01:20<03:23, 1.26it/s] Loading 0: 31%|███ | 111/363 [01:22<03:02, 1.38it/s] Loading 0: 31%|███ | 112/363 [01:24<04:03, 1.03it/s] Loading 0: 31%|███ | 113/363 [01:26<05:02, 1.21s/it] Loading 0: 32%|███▏ | 116/363 [01:26<02:45, 1.50it/s] Loading 0: 32%|███▏ | 117/363 [01:26<02:25, 1.69it/s] Loading 0: 33%|███▎ | 118/363 [01:26<02:00, 2.04it/s] Loading 0: 33%|███▎ | 120/363 [01:28<02:44, 1.48it/s] Loading 0: 33%|███▎ | 121/363 [01:30<03:49, 1.05it/s] Loading 0: 34%|███▎ | 122/363 [01:32<04:49, 1.20s/it] Loading 0: 34%|███▍ | 125/363 [01:33<02:35, 1.53it/s] Loading 0: 35%|███▍ | 126/363 [01:33<02:16, 1.74it/s] Loading 0: 35%|███▍ | 127/363 [01:33<01:52, 2.10it/s] Loading 0: 36%|███▌ | 129/363 [01:35<02:36, 1.49it/s] Loading 0: 36%|███▌ | 130/363 [01:37<03:40, 1.06it/s] Loading 0: 36%|███▌ | 131/363 [01:39<04:38, 1.20s/it] Loading 0: 37%|███▋ | 134/363 [01:39<02:28, 1.54it/s] Loading 0: 37%|███▋ | 135/363 [01:40<02:10, 1.75it/s] Loading 0: 37%|███▋ | 136/363 [01:40<01:47, 2.11it/s] Loading 0: 38%|███▊ | 138/363 [01:42<02:30, 1.49it/s] Loading 0: 38%|███▊ | 139/363 [01:44<03:32, 1.06it/s] Loading 0: 39%|███▊ | 140/363 [01:46<04:27, 1.20s/it] Loading 0: 39%|███▉ | 143/363 [01:46<02:23, 1.54it/s] Loading 0: 40%|███▉ | 144/363 [01:46<02:05, 1.74it/s] Loading 0: 40%|███▉ | 145/363 [01:46<01:43, 2.10it/s] Loading 0: 40%|████ | 147/363 [01:47<01:16, 2.82it/s] Loading 0: 41%|████ | 148/363 [01:47<01:11, 3.02it/s] Loading 0: 41%|████ | 149/363 [01:47<01:00, 3.55it/s] Loading 0: 41%|████▏ | 150/363 [01:47<00:52, 4.09it/s] Loading 0: 42%|████▏ | 151/363 [01:49<02:28, 1.43it/s] Loading 0: 42%|████▏ | 152/363 [01:51<03:40, 1.05s/it] Loading 0: 42%|████▏ | 153/363 [01:53<04:38, 1.32s/it] Loading 0: 43%|████▎ | 156/363 [01:55<03:18, 1.04it/s] Loading 0: 43%|████▎ | 157/363 [01:57<04:00, 1.17s/it] Loading 0: 44%|████▎ | 158/363 [01:59<04:39, 1.36s/it] Loading 0: 44%|████▍ | 161/363 [01:59<02:29, 1.35it/s] Loading 0: 45%|████▍ | 162/363 [02:00<02:10, 1.55it/s] Loading 0: 45%|████▍ | 163/363 [02:00<01:46, 1.87it/s] Loading 0: 45%|████▌ | 165/363 [02:02<02:20, 1.41it/s] Loading 0: 46%|████▌ | 166/363 [02:04<03:12, 1.03it/s] Loading 0: 46%|████▌ | 167/363 [02:06<03:59, 1.22s/it] Loading 0: 47%|████▋ | 170/363 [02:06<02:08, 1.51it/s] Loading 0: 47%|████▋ | 171/363 [02:06<01:51, 1.71it/s] Loading 0: 47%|████▋ | 172/363 [02:06<01:32, 2.07it/s] Loading 0: 48%|████▊ | 174/363 [02:08<02:07, 1.48it/s] Loading 0: 48%|████▊ | 175/363 [02:10<02:58, 1.05it/s] Loading 0: 48%|████▊ | 176/363 [02:12<03:45, 1.20s/it] Loading 0: 49%|████▉ | 179/363 [02:13<02:00, 1.53it/s] Loading 0: 50%|████▉ | 180/363 [02:13<01:45, 1.74it/s] Loading 0: 50%|████▉ | 181/363 [02:13<01:26, 2.09it/s] Loading 0: 50%|█████ | 182/363 [02:15<02:29, 1.21it/s] Loading 0: 51%|█████ | 184/363 [02:15<01:39, 1.80it/s] Loading 0: 51%|█████ | 185/363 [02:16<01:26, 2.05it/s] Loading 0: 51%|█████ | 186/363 [02:16<01:10, 2.51it/s] Loading 0: 52%|█████▏ | 187/363 [02:16<00:58, 3.02it/s] Loading 0: 52%|█████▏ | 188/363 [02:18<02:14, 1.30it/s] Loading 0: 52%|█████▏ | 189/363 [02:20<03:14, 1.12s/it] Loading 0: 53%|█████▎ | 192/363 [02:22<02:28, 1.15it/s] Loading 0: 53%|█████▎ | 193/363 [02:24<03:05, 1.09s/it] Loading 0: 53%|█████▎ | 194/363 [02:26<03:40, 1.30s/it] Loading 0: 54%|█████▍ | 197/363 [02:26<01:58, 1.41it/s] Loading 0: 55%|█████▍ | 198/363 [02:26<01:42, 1.60it/s] Loading 0: 55%|█████▍ | 199/363 [02:26<01:24, 1.93it/s] Loading 0: 55%|█████▌ | 201/363 [02:28<01:52, 1.44it/s] Loading 0: 56%|█████▌ | 202/363 [02:30<02:35, 1.04it/s] Loading 0: 56%|█████▌ | 203/363 [02:32<03:13, 1.21s/it] Loading 0: 57%|█████▋ | 206/363 [02:33<01:43, 1.52it/s] Loading 0: 57%|█████▋ | 207/363 [02:33<01:30, 1.73it/s] Loading 0: 57%|█████▋ | 208/363 [02:33<01:14, 2.08it/s] Loading 0: 58%|█████▊ | 210/363 [02:35<01:42, 1.49it/s] Loading 0: 58%|█████▊ | 211/363 [02:37<02:23, 1.06it/s] Loading 0: 58%|█████▊ | 212/363 [02:39<03:01, 1.20s/it] Loading 0: 59%|█████▉ | 215/363 [02:39<01:36, 1.54it/s] Loading 0: 60%|█████▉ | 216/363 [02:40<01:24, 1.75it/s] Loading 0: 60%|█████▉ | 217/363 [02:40<01:09, 2.11it/s] Loading 0: 60%|██████ | 218/363 [02:42<01:59, 1.21it/s] Loading 0: 60%|██████ | 219/363 [02:44<02:42, 1.13s/it] Loading 0: 61%|██████ | 221/363 [02:44<01:42, 1.39it/s] Loading 0: 61%|██████ | 222/363 [02:44<01:26, 1.63it/s] Loading 0: 61%|██████▏ | 223/363 [02:44<01:09, 2.03it/s] Loading 0: 62%|██████▏ | 224/363 [02:45<00:55, 2.51it/s] Loading 0: 62%|██████▏ | 225/363 [02:47<01:53, 1.21it/s] Loading 0: 63%|██████▎ | 228/363 [02:48<01:39, 1.36it/s] Loading 0: 63%|██████▎ | 229/363 [02:50<02:11, 1.02it/s] Loading 0: 63%|██████▎ | 230/363 [02:52<02:42, 1.22s/it] Loading 0: 64%|██████▍ | 233/363 [02:53<01:27, 1.49it/s] Loading 0: 64%|██████▍ | 234/363 [02:53<01:16, 1.69it/s] Loading 0: 65%|██████▍ | 235/363 [02:53<01:02, 2.04it/s] Loading 0: 65%|██████▌ | 237/363 [02:55<01:25, 1.47it/s] Loading 0: 66%|██████▌ | 238/363 [02:57<01:59, 1.05it/s] Loading 0: 66%|██████▌ | 239/363 [02:59<02:29, 1.20s/it] Loading 0: 67%|██████▋ | 242/363 [02:59<01:19, 1.53it/s] Loading 0: 67%|██████▋ | 243/363 [03:00<01:09, 1.74it/s] Loading 0: 67%|██████▋ | 244/363 [03:00<00:56, 2.09it/s] Loading 0: 68%|██████▊ | 246/363 [03:02<01:18, 1.49it/s] Loading 0: 68%|██████▊ | 247/363 [03:04<01:50, 1.05it/s] Loading 0: 68%|██████▊ | 248/363 [03:06<02:18, 1.20s/it] Loading 0: 69%|██████▉ | 251/363 [03:06<01:13, 1.53it/s] Loading 0: 69%|██████▉ | 252/363 [03:06<01:03, 1.74it/s] Loading 0: 70%|██████▉ | 253/363 [03:06<00:52, 2.10it/s] Loading 0: 70%|███████ | 255/363 [03:08<01:12, 1.49it/s] Loading 0: 71%|███████ | 256/363 [03:10<01:41, 1.05it/s] Loading 0: 71%|███████ | 257/363 [03:12<02:07, 1.21s/it] Loading 0: 72%|███████▏ | 260/363 [03:13<01:07, 1.53it/s] Loading 0: 72%|███████▏ | 261/363 [03:13<00:58, 1.74it/s] Loading 0: 72%|███████▏ | 262/363 [03:13<00:48, 2.10it/s] Loading 0: 73%|███████▎ | 264/363 [03:13<00:35, 2.83it/s] Loading 0: 73%|███████▎ | 265/363 [03:14<00:32, 3.02it/s] Loading 0: 73%|███████▎ | 266/363 [03:14<00:27, 3.56it/s] Loading 0: 74%|███████▎ | 267/363 [03:14<00:23, 4.09it/s] Loading 0: 74%|███████▍ | 268/363 [03:16<01:06, 1.43it/s] Loading 0: 74%|███████▍ | 269/363 [03:18<01:38, 1.05s/it] Loading 0: 74%|███████▍ | 270/363 [03:20<02:03, 1.33s/it] Loading 0: 75%|███████▌ | 273/363 [03:35<05:00, 3.34s/it] Loading 0: 75%|███████▌ | 274/363 [03:37<04:32, 3.06s/it] Loading 0: 76%|███████▌ | 275/363 [03:39<04:09, 2.84s/it] Loading 0: 77%|███████▋ | 278/363 [03:39<02:06, 1.49s/it] Loading 0: 77%|███████▋ | 279/363 [03:40<01:44, 1.24s/it] Loading 0: 77%|███████▋ | 280/363 [03:40<01:23, 1.00s/it] Loading 0: 78%|███████▊ | 282/363 [03:42<01:20, 1.00it/s] Loading 0: 78%|███████▊ | 283/363 [03:44<01:36, 1.20s/it] Loading 0: 78%|███████▊ | 284/363 [03:46<01:50, 1.39s/it] Loading 0: 79%|███████▉ | 287/363 [03:46<00:56, 1.35it/s] Loading 0: 79%|███████▉ | 288/363 [03:46<00:48, 1.55it/s] Loading 0: 80%|███████▉ | 289/363 [03:46<00:39, 1.89it/s] Loading 0: 80%|████████ | 291/363 [03:48<00:50, 1.42it/s] Loading 0: 80%|████████ | 292/363 [03:50<01:09, 1.03it/s] Loading 0: 81%|████████ | 293/363 [03:52<01:25, 1.22s/it] Loading 0: 82%|████████▏ | 296/363 [03:52<00:43, 1.52it/s] Loading 0: 82%|████████▏ | 297/363 [03:53<00:37, 1.74it/s] Loading 0: 82%|████████▏ | 298/363 [03:53<00:30, 2.11it/s] Loading 0: 82%|████████▏ | 299/363 [03:55<00:52, 1.21it/s] Loading 0: 83%|████████▎ | 301/363 [03:55<00:34, 1.82it/s] Loading 0: 83%|████████▎ | 302/363 [03:55<00:29, 2.10it/s] Loading 0: 83%|████████▎ | 303/363 [03:55<00:23, 2.55it/s] Loading 0: 84%|████████▎ | 304/363 [03:56<00:19, 3.06it/s] Loading 0: 84%|████████▍ | 305/363 [03:58<00:44, 1.31it/s] Loading 0: 84%|████████▍ | 306/363 [04:00<01:03, 1.12s/it] Loading 0: 85%|████████▌ | 309/363 [04:02<00:46, 1.15it/s] Loading 0: 85%|████████▌ | 310/363 [04:03<00:57, 1.09s/it] Loading 0: 86%|████████▌ | 311/363 [04:06<01:07, 1.31s/it] Loading 0: 87%|████████▋ | 314/363 [04:06<00:34, 1.41it/s] Loading 0: 87%|████████▋ | 315/363 [04:06<00:29, 1.62it/s] Loading 0: 87%|████████▋ | 316/363 [04:06<00:24, 1.94it/s] Loading 0: 88%|████████▊ | 318/363 [04:08<00:31, 1.44it/s] Loading 0: 88%|████████▊ | 319/363 [04:10<00:42, 1.04it/s] Loading 0: 88%|████████▊ | 320/363 [04:12<00:52, 1.21s/it] Loading 0: 89%|████████▉ | 323/363 [04:12<00:26, 1.54it/s] Loading 0: 89%|████████▉ | 324/363 [04:13<00:22, 1.75it/s] Loading 0: 90%|████████▉ | 325/363 [04:13<00:17, 2.12it/s] Loading 0: 90%|█████████ | 327/363 [04:15<00:24, 1.49it/s] Loading 0: 90%|█████████ | 328/363 [04:17<00:33, 1.06it/s] Loading 0: 91%|█████████ | 329/363 [04:19<00:40, 1.20s/it] Loading 0: 91%|█████████▏| 332/363 [04:19<00:20, 1.54it/s] Loading 0: 92%|█████████▏| 333/363 [04:19<00:16, 1.77it/s] Loading 0: 92%|█████████▏| 334/363 [04:19<00:13, 2.13it/s] Loading 0: 92%|█████████▏| 335/363 [04:21<00:23, 1.22it/s] Loading 0: 93%|█████████▎| 336/363 [04:23<00:30, 1.13s/it] Loading 0: 93%|█████████▎| 338/363 [04:24<00:17, 1.40it/s] Loading 0: 93%|█████████▎| 339/363 [04:24<00:14, 1.66it/s] Loading 0: 94%|█████████▎| 340/363 [04:24<00:11, 2.06it/s] Loading 0: 94%|█████████▍| 341/363 [04:24<00:09, 2.30it/s] Loading 0: 94%|█████████▍| 343/363 [04:26<00:13, 1.49it/s] Loading 0: 95%|█████████▌| 346/363 [04:28<00:11, 1.50it/s] Loading 0: 96%|█████████▌| 347/363 [04:30<00:14, 1.10it/s] Loading 0: 96%|█████████▌| 348/363 [04:32<00:17, 1.14s/it] Loading 0: 97%|█████████▋| 351/363 [04:33<00:07, 1.54it/s] Loading 0: 97%|█████████▋| 352/363 [04:33<00:06, 1.75it/s] Loading 0: 97%|█████████▋| 353/363 [04:33<00:04, 2.09it/s] Loading 0: 98%|█████████▊| 355/363 [04:35<00:05, 1.48it/s] Loading 0: 98%|█████████▊| 356/363 [04:37<00:06, 1.06it/s] Loading 0: 98%|█████████▊| 357/363 [04:39<00:07, 1.20s/it] Loading 0: 99%|█████████▉| 360/363 [04:39<00:01, 1.53it/s] Loading 0: 99%|█████████▉| 361/363 [04:39<00:01, 1.74it/s] Loading 0: 100%|█████████▉| 362/363 [04:40<00:00, 2.11it/s]
Job chaiml-mn24b-v2preferwi-47271-v3-mkmlizer completed after 428.81s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-47271-v3-mkmlizer
Pipeline stage MKMLizer completed in 429.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mn24b-v2preferwi-47271-v3
Waiting for inference service chaiml-mn24b-v2preferwi-47271-v3 to be ready
Inference service chaiml-mn24b-v2preferwi-47271-v3 ready after 70.33016991615295s
Pipeline stage MKMLDeployer completed in 70.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.111629009246826s
Received healthy response to inference request in 1.710975170135498s
Received healthy response to inference request in 2.058966875076294s
Received healthy response to inference request in 1.7257025241851807s
Received healthy response to inference request in 2.0877933502197266s
5 requests
0 failed requests
5th percentile: 1.7139206409454346
10th percentile: 1.7168661117553712
20th percentile: 1.722757053375244
30th percentile: 1.7923553943634034
40th percentile: 1.9256611347198487
50th percentile: 2.058966875076294
60th percentile: 2.070497465133667
70th percentile: 2.08202805519104
80th percentile: 2.0925604820251467
90th percentile: 2.1020947456359864
95th percentile: 2.106861877441406
99th percentile: 2.110675582885742
mean time: 1.939013385772705
Pipeline stage StressChecker completed in 11.02s
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 0.92s
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 0.66s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_47271_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-mn24b-v2preferwi-47271-v3-profiler
Waiting for inference service chaiml-mn24b-v2preferwi-47271-v3-profiler to be ready
Inference service chaiml-mn24b-v2preferwi-47271-v3-profiler ready after 70.67417454719543s
Pipeline stage MKMLProfilerDeployer completed in 71.32s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mn24b-v2prefe15ee257cdae1275008e03f34867269a3-deplovwbbk:/code/chaiverse_profiler_1758415444 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-mn24b-v2prefe15ee257cdae1275008e03f34867269a3-deplovwbbk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1758415444 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1758415444/summary.json'
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 2811.83s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_47271_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_47271_v3 status is now torndown due to DeploymentManager action