developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_76008_v4
model_name: chaiml-mn24b-v2preferwi_76008_v4
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-17T14:50:03+00:00
num_battles: 5900
num_wins: 3039
celo_rating: 1272.42
family_friendly_score: 0.5664
family_friendly_standard_error: 0.007008438342455472
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune7
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': 0.5473540183182484, 'latency_mean': 1.8268658757209777, 'latency_p50': 1.82206130027771, 'latency_p90': 2.0295079231262205}, {'batch_size': 3, 'throughput': 1.1197089110926117, 'latency_mean': 2.670581945180893, 'latency_p50': 2.6843085289001465, 'latency_p90': 2.937256932258606}, {'batch_size': 5, 'throughput': 1.4392297089903328, 'latency_mean': 3.4556104385852815, 'latency_p50': 3.446750044822693, 'latency_p90': 3.889504408836365}, {'batch_size': 6, 'throughput': 1.5472003480114795, 'latency_mean': 3.8564804911613466, 'latency_p50': 3.866570234298706, 'latency_p90': 4.348435425758362}, {'batch_size': 8, 'throughput': 1.7013776777303558, 'latency_mean': 4.65790510058403, 'latency_p50': 4.666629791259766, 'latency_p90': 5.351078772544861}, {'batch_size': 10, 'throughput': 1.7739578369793176, 'latency_mean': 5.595183727741241, 'latency_p50': 5.583729386329651, 'latency_p90': 6.498552083969116}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_76008_v4
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune7
model_size: 24B
ranking_group: single
throughput_3p7s: 1.52
us_pacific_date: 2025-09-17
win_ratio: 0.5150847457627119
generation_params: {'temperature': 0.75, '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-76008-v4-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-76008-v4-mkmlizer to finish
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ Version: 0.30.2 ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ belonging to: ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: Downloaded to shared memory in 49.727s
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo4_tune7 already exists in ChaiML
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp82qyldz_, device:0
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: quantized model in 287.605s
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo4_tune7 in 337.332s
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia/config.json
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia/tokenizer.json
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76008-v4/nvidia/flywheel_model.0.safetensors
chaiml-mn24b-v2preferwi-76008-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:02<04:02, 1.49it/s] Loading 0: 1%| | 4/363 [00:04<06:33, 1.10s/it] Loading 0: 1%|▏ | 5/363 [00:06<08:20, 1.40s/it] Loading 0: 2%|▏ | 8/363 [00:06<03:53, 1.52it/s] Loading 0: 2%|▏ | 9/363 [00:06<03:24, 1.73it/s] Loading 0: 3%|▎ | 10/363 [00:06<02:47, 2.11it/s] Loading 0: 3%|▎ | 12/363 [00:08<03:59, 1.47it/s] Loading 0: 4%|▎ | 13/363 [00:10<05:40, 1.03it/s] Loading 0: 4%|▍ | 14/363 [00:12<07:11, 1.24s/it] Loading 0: 5%|▍ | 17/363 [00:13<03:48, 1.52it/s] Loading 0: 5%|▍ | 18/363 [00:13<03:20, 1.72it/s] Loading 0: 5%|▌ | 19/363 [00:13<02:45, 2.08it/s] Loading 0: 6%|▌ | 21/363 [00:15<03:51, 1.48it/s] Loading 0: 6%|▌ | 22/363 [00:17<05:26, 1.05it/s] Loading 0: 6%|▋ | 23/363 [00:19<06:53, 1.22s/it] Loading 0: 7%|▋ | 26/363 [00:19<03:41, 1.52it/s] Loading 0: 7%|▋ | 27/363 [00:20<03:14, 1.73it/s] Loading 0: 8%|▊ | 28/363 [00:20<02:40, 2.08it/s] Loading 0: 8%|▊ | 30/363 [00:20<01:58, 2.80it/s] Loading 0: 9%|▊ | 31/363 [00:20<01:51, 2.99it/s] Loading 0: 9%|▉ | 32/363 [00:20<01:34, 3.52it/s] Loading 0: 9%|▉ | 33/363 [00:21<01:23, 3.97it/s] Loading 0: 9%|▉ | 34/363 [00:23<03:53, 1.41it/s] Loading 0: 10%|▉ | 35/363 [00:25<05:46, 1.06s/it] Loading 0: 10%|▉ | 36/363 [00:27<07:17, 1.34s/it] Loading 0: 11%|█ | 39/363 [00:29<05:13, 1.03it/s] Loading 0: 11%|█ | 40/363 [00:31<06:20, 1.18s/it] Loading 0: 11%|█▏ | 41/363 [00:33<07:23, 1.38s/it] Loading 0: 12%|█▏ | 44/363 [00:33<03:58, 1.34it/s] Loading 0: 12%|█▏ | 45/363 [00:33<03:27, 1.53it/s] Loading 0: 13%|█▎ | 46/363 [00:33<02:50, 1.86it/s] Loading 0: 13%|█▎ | 48/363 [00:35<03:43, 1.41it/s] Loading 0: 13%|█▎ | 49/363 [00:37<05:07, 1.02it/s] Loading 0: 14%|█▍ | 50/363 [00:39<06:24, 1.23s/it] Loading 0: 15%|█▍ | 53/363 [00:40<03:26, 1.50it/s] Loading 0: 15%|█▍ | 54/363 [00:40<03:00, 1.71it/s] Loading 0: 15%|█▌ | 55/363 [00:40<02:29, 2.06it/s] Loading 0: 16%|█▌ | 57/363 [00:42<03:27, 1.48it/s] Loading 0: 16%|█▌ | 58/363 [00:44<04:51, 1.05it/s] Loading 0: 16%|█▋ | 59/363 [00:46<06:07, 1.21s/it] Loading 0: 17%|█▋ | 62/363 [00:46<03:16, 1.53it/s] Loading 0: 17%|█▋ | 63/363 [00:47<02:52, 1.73it/s] Loading 0: 18%|█▊ | 64/363 [00:47<02:23, 2.09it/s] Loading 0: 18%|█▊ | 65/363 [00:49<04:07, 1.20it/s] Loading 0: 18%|█▊ | 67/363 [00:49<02:45, 1.79it/s] Loading 0: 19%|█▊ | 68/363 [00:49<02:24, 2.04it/s] Loading 0: 19%|█▉ | 69/363 [00:49<01:57, 2.49it/s] Loading 0: 19%|█▉ | 70/363 [00:49<01:38, 2.99it/s] Loading 0: 20%|█▉ | 71/363 [00:51<03:46, 1.29it/s] Loading 0: 20%|█▉ | 72/363 [00:53<05:22, 1.11s/it] Loading 0: 20%|██ | 73/363 [00:55<06:39, 1.38s/it] Loading 0: 21%|██ | 76/363 [00:56<03:14, 1.48it/s] Loading 0: 21%|██ | 77/363 [00:56<02:48, 1.70it/s] Loading 0: 21%|██▏ | 78/363 [00:56<02:17, 2.08it/s] Loading 0: 22%|██▏ | 79/363 [00:58<04:01, 1.18it/s] Loading 0: 22%|██▏ | 80/363 [01:00<05:28, 1.16s/it] Loading 0: 23%|██▎ | 82/363 [01:00<03:25, 1.37it/s] Loading 0: 23%|██▎ | 83/363 [01:01<02:53, 1.61it/s] Loading 0: 23%|██▎ | 84/363 [01:01<02:17, 2.02it/s] Loading 0: 24%|██▎ | 86/363 [01:03<03:14, 1.42it/s] Loading 0: 24%|██▍ | 87/363 [01:05<04:38, 1.01s/it] Loading 0: 25%|██▍ | 90/363 [01:07<03:48, 1.20it/s] Loading 0: 25%|██▌ | 91/363 [01:09<04:46, 1.05s/it] Loading 0: 25%|██▌ | 92/363 [01:11<05:43, 1.27s/it] Loading 0: 26%|██▌ | 95/363 [01:11<03:10, 1.41it/s] Loading 0: 26%|██▋ | 96/363 [01:11<02:46, 1.60it/s] Loading 0: 27%|██▋ | 97/363 [01:12<02:18, 1.92it/s] Loading 0: 27%|██▋ | 99/363 [01:14<03:03, 1.44it/s] Loading 0: 28%|██▊ | 100/363 [01:16<04:14, 1.03it/s] Loading 0: 28%|██▊ | 101/363 [01:18<05:18, 1.22s/it] Loading 0: 29%|██▊ | 104/363 [01:18<02:51, 1.51it/s] Loading 0: 29%|██▉ | 105/363 [01:18<02:30, 1.72it/s] Loading 0: 29%|██▉ | 106/363 [01:18<02:04, 2.07it/s] Loading 0: 29%|██▉ | 107/363 [01:18<01:42, 2.49it/s] Loading 0: 30%|██▉ | 108/363 [01:20<03:23, 1.25it/s] Loading 0: 31%|███ | 111/363 [01:22<03:03, 1.38it/s] Loading 0: 31%|███ | 112/363 [01:24<04:04, 1.03it/s] Loading 0: 31%|███ | 113/363 [01:26<05:03, 1.21s/it] Loading 0: 32%|███▏ | 116/363 [01:27<02:46, 1.48it/s] Loading 0: 32%|███▏ | 117/363 [01:27<02:26, 1.68it/s] Loading 0: 33%|███▎ | 118/363 [01:27<02:00, 2.03it/s] Loading 0: 33%|███▎ | 120/363 [01:29<02:45, 1.47it/s] Loading 0: 33%|███▎ | 121/363 [01:31<03:51, 1.05it/s] Loading 0: 34%|███▎ | 122/363 [01:33<04:51, 1.21s/it] Loading 0: 34%|███▍ | 125/363 [01:33<02:36, 1.52it/s] Loading 0: 35%|███▍ | 126/363 [01:34<02:17, 1.73it/s] Loading 0: 35%|███▍ | 127/363 [01:34<01:53, 2.08it/s] Loading 0: 36%|███▌ | 129/363 [01:36<02:37, 1.48it/s] Loading 0: 36%|███▌ | 130/363 [01:38<03:41, 1.05it/s] Loading 0: 36%|███▌ | 131/363 [01:40<04:39, 1.21s/it] Loading 0: 37%|███▋ | 134/363 [01:40<02:29, 1.53it/s] Loading 0: 37%|███▋ | 135/363 [01:40<02:11, 1.74it/s] Loading 0: 37%|███▋ | 136/363 [01:40<01:48, 2.10it/s] Loading 0: 38%|███▊ | 138/363 [01:42<02:31, 1.48it/s] Loading 0: 38%|███▊ | 139/363 [01:44<03:33, 1.05it/s] Loading 0: 39%|███▊ | 140/363 [01:46<04:29, 1.21s/it] Loading 0: 39%|███▉ | 143/363 [01:47<02:24, 1.53it/s] Loading 0: 40%|███▉ | 144/363 [01:47<02:06, 1.73it/s] Loading 0: 40%|███▉ | 145/363 [01:47<01:44, 2.09it/s] Loading 0: 40%|████ | 147/363 [01:47<01:16, 2.81it/s] Loading 0: 41%|████ | 148/363 [01:48<01:11, 3.01it/s] Loading 0: 41%|████ | 149/363 [01:48<01:01, 3.51it/s] Loading 0: 41%|████▏ | 150/363 [01:48<00:52, 4.03it/s] Loading 0: 42%|████▏ | 151/363 [01:50<02:29, 1.42it/s] Loading 0: 42%|████▏ | 152/363 [01:52<03:41, 1.05s/it] Loading 0: 42%|████▏ | 153/363 [01:54<04:39, 1.33s/it] Loading 0: 43%|████▎ | 156/363 [01:56<03:19, 1.04it/s] Loading 0: 43%|████▎ | 157/363 [01:58<04:01, 1.17s/it] Loading 0: 44%|████▎ | 158/363 [02:00<04:41, 1.37s/it] Loading 0: 44%|████▍ | 161/363 [02:00<02:30, 1.34it/s] Loading 0: 45%|████▍ | 162/363 [02:00<02:10, 1.54it/s] Loading 0: 45%|████▍ | 163/363 [02:01<01:47, 1.86it/s] Loading 0: 45%|████▌ | 165/363 [02:03<02:20, 1.41it/s] Loading 0: 46%|████▌ | 166/363 [02:05<03:12, 1.02it/s] Loading 0: 46%|████▌ | 167/363 [02:07<04:00, 1.23s/it] Loading 0: 47%|████▋ | 170/363 [02:07<02:08, 1.50it/s] Loading 0: 47%|████▋ | 171/363 [02:07<01:52, 1.71it/s] Loading 0: 47%|████▋ | 172/363 [02:07<01:32, 2.06it/s] Loading 0: 48%|████▊ | 174/363 [02:09<02:08, 1.47it/s] Loading 0: 48%|████▊ | 175/363 [02:11<02:59, 1.05it/s] Loading 0: 48%|████▊ | 176/363 [02:13<03:46, 1.21s/it] Loading 0: 49%|████▉ | 179/363 [02:14<02:00, 1.52it/s] Loading 0: 50%|████▉ | 180/363 [02:14<01:46, 1.73it/s] Loading 0: 50%|████▉ | 181/363 [02:14<01:27, 2.08it/s] Loading 0: 50%|█████ | 182/363 [02:16<02:31, 1.20it/s] Loading 0: 51%|█████ | 184/363 [02:16<01:40, 1.78it/s] Loading 0: 51%|█████ | 185/363 [02:16<01:27, 2.03it/s] Loading 0: 51%|█████ | 186/363 [02:17<01:11, 2.49it/s] Loading 0: 52%|█████▏ | 187/363 [02:17<00:58, 3.01it/s] Loading 0: 52%|█████▏ | 188/363 [02:19<02:15, 1.29it/s] Loading 0: 52%|█████▏ | 189/363 [02:21<03:16, 1.13s/it] Loading 0: 53%|█████▎ | 192/363 [02:23<02:29, 1.14it/s] Loading 0: 53%|█████▎ | 193/363 [02:25<03:07, 1.10s/it] Loading 0: 53%|█████▎ | 194/363 [02:27<03:41, 1.31s/it] Loading 0: 54%|█████▍ | 197/363 [02:27<01:58, 1.40it/s] Loading 0: 55%|█████▍ | 198/363 [02:27<01:43, 1.59it/s] Loading 0: 55%|█████▍ | 199/363 [02:27<01:25, 1.92it/s] Loading 0: 55%|█████▌ | 201/363 [02:29<01:53, 1.43it/s] Loading 0: 56%|█████▌ | 202/363 [02:31<02:36, 1.03it/s] Loading 0: 56%|█████▌ | 203/363 [02:33<03:16, 1.23s/it] Loading 0: 57%|█████▋ | 206/363 [02:34<01:44, 1.50it/s] Loading 0: 57%|█████▋ | 207/363 [02:34<01:31, 1.71it/s] Loading 0: 57%|█████▋ | 208/363 [02:34<01:15, 2.06it/s] Loading 0: 58%|█████▊ | 210/363 [02:36<01:43, 1.48it/s] Loading 0: 58%|█████▊ | 211/363 [02:38<02:25, 1.05it/s] Loading 0: 58%|█████▊ | 212/363 [02:40<03:02, 1.21s/it] Loading 0: 59%|█████▉ | 215/363 [02:40<01:36, 1.53it/s] Loading 0: 60%|█████▉ | 216/363 [02:41<01:24, 1.73it/s] Loading 0: 60%|█████▉ | 217/363 [02:41<01:09, 2.09it/s] Loading 0: 60%|██████ | 218/363 [02:43<02:00, 1.20it/s] Loading 0: 60%|██████ | 219/363 [02:45<02:44, 1.14s/it] Loading 0: 61%|██████ | 221/363 [02:45<01:43, 1.37it/s] Loading 0: 61%|██████ | 222/363 [02:45<01:27, 1.62it/s] Loading 0: 61%|██████▏ | 223/363 [02:46<01:09, 2.02it/s] Loading 0: 62%|██████▏ | 224/363 [02:46<00:55, 2.49it/s] Loading 0: 62%|██████▏ | 225/363 [02:48<01:54, 1.20it/s] Loading 0: 63%|██████▎ | 228/363 [02:50<01:39, 1.36it/s] Loading 0: 63%|██████▎ | 229/363 [02:52<02:12, 1.01it/s] Loading 0: 63%|██████▎ | 230/363 [02:54<02:43, 1.23s/it] Loading 0: 64%|██████▍ | 233/363 [02:54<01:27, 1.48it/s] Loading 0: 64%|██████▍ | 234/363 [02:54<01:16, 1.68it/s] Loading 0: 65%|██████▍ | 235/363 [02:54<01:03, 2.03it/s] Loading 0: 65%|██████▌ | 237/363 [02:56<01:25, 1.47it/s] Loading 0: 66%|██████▌ | 238/363 [02:58<01:59, 1.05it/s] Loading 0: 66%|██████▌ | 239/363 [03:00<02:30, 1.21s/it] Loading 0: 67%|██████▋ | 242/363 [03:01<01:19, 1.52it/s] Loading 0: 67%|██████▋ | 243/363 [03:01<01:09, 1.72it/s] Loading 0: 67%|██████▋ | 244/363 [03:01<00:57, 2.08it/s] Loading 0: 68%|██████▊ | 246/363 [03:03<01:19, 1.48it/s] Loading 0: 68%|██████▊ | 247/363 [03:05<01:50, 1.05it/s] Loading 0: 68%|██████▊ | 248/363 [03:07<02:19, 1.21s/it] Loading 0: 69%|██████▉ | 251/363 [03:07<01:13, 1.52it/s] Loading 0: 69%|██████▉ | 252/363 [03:08<01:04, 1.73it/s] Loading 0: 70%|██████▉ | 253/363 [03:08<00:52, 2.08it/s] Loading 0: 70%|███████ | 255/363 [03:10<01:12, 1.48it/s] Loading 0: 71%|███████ | 256/363 [03:12<01:42, 1.05it/s] Loading 0: 71%|███████ | 257/363 [03:14<02:08, 1.21s/it] Loading 0: 72%|███████▏ | 260/363 [03:14<01:07, 1.52it/s] Loading 0: 72%|███████▏ | 261/363 [03:14<00:59, 1.72it/s] Loading 0: 72%|███████▏ | 262/363 [03:14<00:48, 2.08it/s] Loading 0: 73%|███████▎ | 264/363 [03:15<00:35, 2.80it/s] Loading 0: 73%|███████▎ | 265/363 [03:15<00:32, 2.99it/s] Loading 0: 73%|███████▎ | 266/363 [03:15<00:27, 3.50it/s] Loading 0: 74%|███████▎ | 267/363 [03:15<00:23, 4.01it/s] Loading 0: 74%|███████▍ | 268/363 [03:17<01:07, 1.41it/s] Loading 0: 74%|███████▍ | 269/363 [03:19<01:39, 1.06s/it] Loading 0: 74%|███████▍ | 270/363 [03:21<02:04, 1.33s/it] Loading 0: 75%|███████▌ | 273/363 [03:36<05:02, 3.36s/it] Loading 0: 75%|███████▌ | 274/363 [03:38<04:33, 3.08s/it] Loading 0: 76%|███████▌ | 275/363 [03:41<04:11, 2.86s/it] Loading 0: 77%|███████▋ | 278/363 [03:41<02:07, 1.50s/it] Loading 0: 77%|███████▋ | 279/363 [03:41<01:45, 1.25s/it] Loading 0: 77%|███████▋ | 280/363 [03:41<01:23, 1.01s/it] Loading 0: 78%|███████▊ | 282/363 [03:43<01:21, 1.00s/it] Loading 0: 78%|███████▊ | 283/363 [03:45<01:36, 1.21s/it] Loading 0: 78%|███████▊ | 284/363 [03:47<01:51, 1.41s/it] Loading 0: 79%|███████▉ | 287/363 [03:47<00:56, 1.34it/s] Loading 0: 79%|███████▉ | 288/363 [03:48<00:48, 1.55it/s] Loading 0: 80%|███████▉ | 289/363 [03:48<00:39, 1.88it/s] Loading 0: 80%|████████ | 291/363 [03:50<00:50, 1.42it/s] Loading 0: 80%|████████ | 292/363 [03:52<01:09, 1.02it/s] Loading 0: 81%|████████ | 293/363 [03:54<01:25, 1.22s/it] Loading 0: 82%|████████▏ | 296/363 [03:54<00:44, 1.52it/s] Loading 0: 82%|████████▏ | 297/363 [03:54<00:37, 1.74it/s] Loading 0: 82%|████████▏ | 298/363 [03:54<00:30, 2.10it/s] Loading 0: 82%|████████▏ | 299/363 [03:56<00:53, 1.20it/s] Loading 0: 83%|████████▎ | 301/363 [03:57<00:34, 1.81it/s] Loading 0: 83%|████████▎ | 302/363 [03:57<00:29, 2.10it/s] Loading 0: 83%|████████▎ | 303/363 [03:57<00:23, 2.56it/s] Loading 0: 84%|████████▎ | 304/363 [03:57<00:19, 3.09it/s] Loading 0: 84%|████████▍ | 305/363 [03:59<00:44, 1.30it/s] Loading 0: 84%|████████▍ | 306/363 [04:01<01:04, 1.12s/it] Loading 0: 85%|████████▌ | 309/363 [04:03<00:47, 1.15it/s] Loading 0: 85%|████████▌ | 310/363 [04:05<00:58, 1.10s/it] Loading 0: 86%|████████▌ | 311/363 [04:07<01:08, 1.31s/it] Loading 0: 87%|████████▋ | 314/363 [04:07<00:34, 1.41it/s] Loading 0: 87%|████████▋ | 315/363 [04:08<00:29, 1.62it/s] Loading 0: 87%|████████▋ | 316/363 [04:08<00:24, 1.95it/s] Loading 0: 88%|████████▊ | 318/363 [04:10<00:31, 1.44it/s] Loading 0: 88%|████████▊ | 319/363 [04:12<00:42, 1.03it/s] Loading 0: 88%|████████▊ | 320/363 [04:14<00:52, 1.22s/it] Loading 0: 89%|████████▉ | 323/363 [04:14<00:26, 1.53it/s] Loading 0: 89%|████████▉ | 324/363 [04:14<00:22, 1.75it/s] Loading 0: 90%|████████▉ | 325/363 [04:14<00:18, 2.11it/s] Loading 0: 90%|█████████ | 327/363 [04:16<00:24, 1.49it/s] Loading 0: 90%|█████████ | 328/363 [04:18<00:33, 1.05it/s] Loading 0: 91%|█████████ | 329/363 [04:20<00:41, 1.21s/it] Loading 0: 91%|█████████▏| 332/363 [04:21<00:20, 1.54it/s] Loading 0: 92%|█████████▏| 333/363 [04:21<00:16, 1.77it/s] Loading 0: 92%|█████████▏| 334/363 [04:21<00:13, 2.13it/s] Loading 0: 92%|█████████▏| 335/363 [04:23<00:23, 1.21it/s] Loading 0: 93%|█████████▎| 336/363 [04:25<00:30, 1.13s/it] Loading 0: 93%|█████████▎| 338/363 [04:25<00:17, 1.40it/s] Loading 0: 93%|█████████▎| 339/363 [04:26<00:14, 1.67it/s] Loading 0: 94%|█████████▎| 340/363 [04:26<00:11, 2.08it/s] Loading 0: 94%|█████████▍| 341/363 [04:26<00:09, 2.29it/s] Loading 0: 94%|█████████▍| 343/363 [04:28<00:13, 1.48it/s] Loading 0: 95%|█████████▌| 346/363 [04:30<00:11, 1.50it/s] Loading 0: 96%|█████████▌| 347/363 [04:32<00:14, 1.10it/s] Loading 0: 96%|█████████▌| 348/363 [04:34<00:17, 1.15s/it] Loading 0: 97%|█████████▋| 351/363 [04:34<00:07, 1.54it/s] Loading 0: 97%|█████████▋| 352/363 [04:34<00:06, 1.75it/s] Loading 0: 97%|█████████▋| 353/363 [04:35<00:04, 2.10it/s] Loading 0: 98%|█████████▊| 355/363 [04:37<00:05, 1.48it/s] Loading 0: 98%|█████████▊| 356/363 [04:39<00:06, 1.05it/s] Loading 0: 98%|█████████▊| 357/363 [04:41<00:07, 1.21s/it] Loading 0: 99%|█████████▉| 360/363 [04:41<00:01, 1.53it/s] Loading 0: 99%|█████████▉| 361/363 [04:41<00:01, 1.75it/s] Loading 0: 100%|█████████▉| 362/363 [04:41<00:00, 2.11it/s]
Job chaiml-mn24b-v2preferwi-76008-v4-mkmlizer completed after 450.61s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-76008-v4-mkmlizer
Pipeline stage MKMLizer completed in 451.16s
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-mn24b-v2preferwi-76008-v4
Waiting for inference service chaiml-mn24b-v2preferwi-76008-v4 to be ready
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', '')
Inference service chaiml-mn24b-v2preferwi-76008-v4 ready after 60.3901572227478s
Pipeline stage MKMLDeployer completed in 60.83s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.038921356201172s
Received healthy response to inference request in 1.678581714630127s
Received healthy response to inference request in 1.9399313926696777s
Received healthy response to inference request in 2.001176595687866s
5 requests
1 failed requests
5th percentile: 1.730851650238037
10th percentile: 1.7831215858459473
20th percentile: 1.8876614570617676
30th percentile: 1.9521804332733155
40th percentile: 1.9766785144805907
50th percentile: 2.001176595687866
60th percentile: 2.0162744998931883
70th percentile: 2.031372404098511
80th percentile: 5.665506029129031
90th percentile: 12.918675374984744
95th percentile: 16.545260047912596
99th percentile: 19.446527786254883
mean time: 5.566091156005859
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7993707656860352s
Received healthy response to inference request in 1.9032313823699951s
Received healthy response to inference request in 1.8965167999267578s
Received healthy response to inference request in 1.7467834949493408s
Received healthy response to inference request in 1.654975414276123s
5 requests
0 failed requests
5th percentile: 1.6733370304107666
10th percentile: 1.6916986465454102
20th percentile: 1.7284218788146972
30th percentile: 1.7573009490966798
40th percentile: 1.7783358573913575
50th percentile: 1.7993707656860352
60th percentile: 1.8382291793823242
70th percentile: 1.8770875930786133
80th percentile: 1.8978597164154052
90th percentile: 1.9005455493927002
95th percentile: 1.9018884658813477
99th percentile: 1.9029627990722657
mean time: 1.8001755714416503
Pipeline stage StressChecker completed in 39.84s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.72s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.91s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_76008_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
Received signal 15, running shutdown handler
Shutdown handler de-registered
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-76008-v4-profiler
Waiting for inference service chaiml-mn24b-v2preferwi-76008-v4-profiler to be ready
Inference service chaiml-mn24b-v2preferwi-76008-v4-profiler ready after 60.59763765335083s
Pipeline stage MKMLProfilerDeployer completed in 61.26s
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-v2prefebb28b67efde7f2c24fac8fb8e84fd2dc-deplohrjct:/code/chaiverse_profiler_1758122133 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-mn24b-v2prefebb28b67efde7f2c24fac8fb8e84fd2dc-deplohrjct --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1758122133 && 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_1758122133/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 2995.97s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_76008_v4 status is now torndown due to DeploymentManager action