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-2a6f-6970-linear-w02-v3-mkmlizer
Waiting for job on chaiml-2a6f-6970-linear-w02-v3-mkmlizer to finish
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ Version: 0.30.2 ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ belonging to: ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ║ ║
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: Downloaded to shared memory in 48.940s
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: Checking if ChaiML/2a6f-6970-linear-w02 already exists in ChaiML
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp3mcrln6p, device:0
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-mistral31-24b-s_69496_v30: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-mistral31-24b-s_69496_v30/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n Field required [type=missing, input_value={\'detail\': \\"503, message=...b-s_69496_v30/predict\'\\"}, input_type=dict]\\n For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: quantized model in 280.406s
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: Processed model ChaiML/2a6f-6970-linear-w02 in 329.347s
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia/config.json
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia/special_tokens_map.json
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia/tokenizer_config.json
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia/tokenizer.json
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia/flywheel_model.1.safetensors
chaiml-2a6f-6970-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w02-v3/nvidia/flywheel_model.0.safetensors
chaiml-2a6f-6970-linear-w02-v3-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:00<00:30, 11.86it/s]
Loading 0: 1%| | 4/363 [00:02<03:51, 1.55it/s]
Loading 0: 1%|▏ | 5/363 [00:04<06:17, 1.06s/it]
Loading 0: 2%|▏ | 6/363 [00:06<08:00, 1.34s/it]
Loading 0: 2%|▏ | 9/363 [00:06<03:50, 1.54it/s]
Loading 0: 3%|▎ | 10/363 [00:06<03:22, 1.74it/s]
Loading 0: 3%|▎ | 11/363 [00:07<02:44, 2.13it/s]
Loading 0: 4%|▎ | 13/363 [00:08<03:54, 1.49it/s]
Loading 0: 4%|▍ | 14/363 [00:10<05:31, 1.05it/s]
Loading 0: 4%|▍ | 15/363 [00:12<06:59, 1.21s/it]
Loading 0: 5%|▍ | 18/363 [00:13<03:41, 1.56it/s]
Loading 0: 5%|▌ | 19/363 [00:13<03:14, 1.77it/s]
Loading 0: 6%|▌ | 20/363 [00:13<02:42, 2.11it/s]
Loading 0: 6%|▌ | 22/363 [00:15<03:56, 1.44it/s]
Loading 0: 6%|▋ | 23/363 [00:17<05:27, 1.04it/s]
Loading 0: 7%|▋ | 24/363 [00:19<06:50, 1.21s/it]
Loading 0: 7%|▋ | 27/363 [00:19<03:39, 1.53it/s]
Loading 0: 8%|▊ | 28/363 [00:20<03:12, 1.74it/s]
Loading 0: 8%|▊ | 29/363 [00:20<02:39, 2.10it/s]
Loading 0: 9%|▊ | 31/363 [00:22<03:41, 1.50it/s]
Loading 0: 9%|▉ | 32/363 [00:24<05:10, 1.07it/s]
Loading 0: 9%|▉ | 33/363 [00:26<06:33, 1.19s/it]
Loading 0: 10%|▉ | 36/363 [00:26<03:30, 1.55it/s]
Loading 0: 10%|█ | 37/363 [00:26<03:05, 1.76it/s]
Loading 0: 10%|█ | 38/363 [00:26<02:32, 2.13it/s]
Loading 0: 11%|█ | 40/363 [00:28<03:43, 1.45it/s]
Loading 0: 11%|█▏ | 41/363 [00:30<05:08, 1.04it/s]
Loading 0: 12%|█▏ | 42/363 [00:32<06:26, 1.20s/it]
Loading 0: 12%|█▏ | 45/363 [00:33<03:26, 1.54it/s]
Loading 0: 13%|█▎ | 46/363 [00:33<03:00, 1.75it/s]
Loading 0: 13%|█▎ | 47/363 [00:33<02:29, 2.11it/s]
Loading 0: 13%|█▎ | 49/363 [00:35<03:28, 1.50it/s]
Loading 0: 14%|█▍ | 50/363 [00:37<04:54, 1.06it/s]
Loading 0: 14%|█▍ | 51/363 [00:39<06:12, 1.19s/it]
Loading 0: 15%|█▍ | 54/363 [00:39<03:19, 1.55it/s]
Loading 0: 15%|█▌ | 55/363 [00:40<02:54, 1.76it/s]
Loading 0: 15%|█▌ | 56/363 [00:40<02:24, 2.13it/s]
Loading 0: 16%|█▌ | 58/363 [00:42<03:22, 1.51it/s]
Loading 0: 16%|█▋ | 59/363 [00:44<04:55, 1.03it/s]
Loading 0: 17%|█▋ | 60/363 [00:46<06:09, 1.22s/it]
Loading 0: 17%|█▋ | 63/363 [00:46<03:16, 1.53it/s]
Loading 0: 18%|█▊ | 64/363 [00:46<02:51, 1.75it/s]
Loading 0: 18%|█▊ | 65/363 [00:46<02:21, 2.11it/s]
Loading 0: 18%|█▊ | 67/363 [00:48<03:17, 1.50it/s]
Loading 0: 19%|█▊ | 68/363 [00:50<04:37, 1.06it/s]
Loading 0: 19%|█▉ | 69/363 [00:52<05:49, 1.19s/it]
Loading 0: 20%|█▉ | 72/363 [00:53<03:06, 1.56it/s]
Loading 0: 20%|██ | 73/363 [00:53<02:42, 1.78it/s]
Loading 0: 20%|██ | 74/363 [00:53<02:14, 2.15it/s]
Loading 0: 21%|██ | 76/363 [00:55<03:09, 1.51it/s]
Loading 0: 21%|██ | 77/363 [00:57<04:27, 1.07it/s]
Loading 0: 21%|██▏ | 78/363 [00:59<05:39, 1.19s/it]
Loading 0: 22%|██▏ | 81/363 [00:59<03:00, 1.56it/s]
Loading 0: 23%|██▎ | 82/363 [00:59<02:38, 1.77it/s]
Loading 0: 23%|██▎ | 83/363 [00:59<02:11, 2.14it/s]
Loading 0: 23%|██▎ | 85/363 [01:01<03:03, 1.51it/s]
Loading 0: 24%|██▎ | 86/363 [01:03<04:19, 1.07it/s]
Loading 0: 24%|██▍ | 87/363 [01:05<05:28, 1.19s/it]
Loading 0: 25%|██▍ | 90/363 [01:06<02:54, 1.56it/s]
Loading 0: 25%|██▌ | 91/363 [01:06<02:32, 1.78it/s]
Loading 0: 25%|██▌ | 92/363 [01:06<02:05, 2.15it/s]
Loading 0: 26%|██▌ | 94/363 [01:08<02:57, 1.51it/s]
Loading 0: 26%|██▌ | 95/363 [01:10<04:11, 1.07it/s]
Loading 0: 26%|██▋ | 96/363 [01:12<05:28, 1.23s/it]
Loading 0: 27%|██▋ | 99/363 [01:12<02:54, 1.51it/s]
Loading 0: 28%|██▊ | 100/363 [01:13<02:31, 1.73it/s]
Loading 0: 28%|██▊ | 101/363 [01:13<02:05, 2.09it/s]
Loading 0: 28%|██▊ | 103/363 [01:15<02:53, 1.50it/s]
Loading 0: 29%|██▊ | 104/363 [01:17<04:03, 1.06it/s]
Loading 0: 29%|██▉ | 105/363 [01:19<05:07, 1.19s/it]
Loading 0: 30%|██▉ | 108/363 [01:19<02:44, 1.55it/s]
Loading 0: 30%|███ | 109/363 [01:19<02:23, 1.77it/s]
Loading 0: 30%|███ | 110/363 [01:19<01:59, 2.12it/s]
Loading 0: 31%|███ | 112/363 [01:21<02:46, 1.51it/s]
Loading 0: 31%|███ | 113/363 [01:23<03:53, 1.07it/s]
Loading 0: 31%|███▏ | 114/363 [01:25<04:55, 1.19s/it]
Loading 0: 32%|███▏ | 117/363 [01:25<02:37, 1.56it/s]
Loading 0: 33%|███▎ | 118/363 [01:26<02:17, 1.78it/s]
Loading 0: 33%|███▎ | 119/363 [01:26<01:53, 2.14it/s]
Loading 0: 33%|███▎ | 121/363 [01:28<02:39, 1.51it/s]
Loading 0: 34%|███▎ | 122/363 [01:30<03:45, 1.07it/s]
Loading 0: 34%|███▍ | 123/363 [01:32<04:45, 1.19s/it]
Loading 0: 35%|███▍ | 126/363 [01:32<02:32, 1.56it/s]
Loading 0: 35%|███▍ | 127/363 [01:32<02:13, 1.77it/s]
Loading 0: 35%|███▌ | 128/363 [01:32<01:50, 2.13it/s]
Loading 0: 36%|███▌ | 130/363 [01:34<02:34, 1.51it/s]
Loading 0: 36%|███▌ | 131/363 [01:36<03:37, 1.07it/s]
Loading 0: 36%|███▋ | 132/363 [01:38<04:34, 1.19s/it]
Loading 0: 37%|███▋ | 135/363 [01:39<02:26, 1.55it/s]
Loading 0: 37%|███▋ | 136/363 [01:39<02:08, 1.76it/s]
Loading 0: 38%|███▊ | 137/363 [01:39<01:46, 2.12it/s]
Loading 0: 38%|███▊ | 139/363 [01:41<02:33, 1.46it/s]
Loading 0: 39%|███▊ | 140/363 [01:43<03:33, 1.05it/s]
Loading 0: 39%|███▉ | 141/363 [01:45<04:27, 1.20s/it]
Loading 0: 40%|███▉ | 144/363 [01:45<02:22, 1.54it/s]
Loading 0: 40%|███▉ | 145/363 [01:46<02:03, 1.76it/s]
Loading 0: 40%|████ | 146/363 [01:46<01:42, 2.13it/s]
Loading 0: 41%|████ | 148/363 [01:48<02:22, 1.51it/s]
Loading 0: 41%|████ | 149/363 [01:50<03:20, 1.07it/s]
Loading 0: 41%|████▏ | 150/363 [01:52<04:12, 1.19s/it]
Loading 0: 42%|████▏ | 153/363 [01:52<02:14, 1.56it/s]
Loading 0: 42%|████▏ | 154/363 [01:52<01:58, 1.77it/s]
Loading 0: 43%|████▎ | 155/363 [01:52<01:37, 2.13it/s]
Loading 0: 43%|████▎ | 157/363 [01:54<02:16, 1.51it/s]
Loading 0: 44%|████▎ | 158/363 [01:56<03:11, 1.07it/s]
Loading 0: 44%|████▍ | 159/363 [01:58<04:01, 1.19s/it]
Loading 0: 45%|████▍ | 162/363 [01:58<02:08, 1.57it/s]
Loading 0: 45%|████▍ | 163/363 [01:59<01:51, 1.79it/s]
Loading 0: 45%|████▌ | 164/363 [01:59<01:32, 2.16it/s]
Loading 0: 46%|████▌ | 166/363 [02:01<02:09, 1.52it/s]
Loading 0: 46%|████▌ | 167/363 [02:03<03:02, 1.07it/s]
Loading 0: 46%|████▋ | 168/363 [02:05<03:50, 1.18s/it]
Loading 0: 47%|████▋ | 171/363 [02:05<02:02, 1.57it/s]
Loading 0: 47%|████▋ | 172/363 [02:05<01:46, 1.79it/s]
Loading 0: 48%|████▊ | 173/363 [02:05<01:27, 2.16it/s]
Loading 0: 48%|████▊ | 175/363 [02:07<02:03, 1.52it/s]
Loading 0: 48%|████▊ | 176/363 [02:09<03:00, 1.04it/s]
Loading 0: 49%|████▉ | 177/363 [02:11<03:44, 1.21s/it]
Loading 0: 50%|████▉ | 180/363 [02:12<01:59, 1.53it/s]
Loading 0: 50%|████▉ | 181/363 [02:12<01:44, 1.74it/s]
Loading 0: 50%|█████ | 182/363 [02:12<01:26, 2.10it/s]
Loading 0: 51%|█████ | 184/363 [02:14<01:59, 1.50it/s]
Loading 0: 51%|█████ | 185/363 [02:16<02:46, 1.07it/s]
Loading 0: 51%|█████ | 186/363 [02:18<03:30, 1.19s/it]
Loading 0: 52%|█████▏ | 189/363 [02:18<01:51, 1.56it/s]
Loading 0: 52%|█████▏ | 190/363 [02:18<01:37, 1.78it/s]
Loading 0: 53%|█████▎ | 191/363 [02:18<01:19, 2.15it/s]
Loading 0: 53%|█████▎ | 193/363 [02:20<01:51, 1.52it/s]
Loading 0: 53%|█████▎ | 194/363 [02:22<02:37, 1.07it/s]
Loading 0: 54%|█████▎ | 195/363 [02:24<03:18, 1.18s/it]
Loading 0: 55%|█████▍ | 198/363 [02:25<01:45, 1.56it/s]
Loading 0: 55%|█████▍ | 199/363 [02:25<01:32, 1.78it/s]
Loading 0: 55%|█████▌ | 200/363 [02:25<01:16, 2.14it/s]
Loading 0: 56%|█████▌ | 202/363 [02:27<01:46, 1.52it/s]
Loading 0: 56%|█████▌ | 203/363 [02:29<02:29, 1.07it/s]
Loading 0: 56%|█████▌ | 204/363 [02:31<03:08, 1.19s/it]
Loading 0: 57%|█████▋ | 207/363 [02:31<01:39, 1.56it/s]
Loading 0: 57%|█████▋ | 208/363 [02:31<01:26, 1.79it/s]
Loading 0: 58%|█████▊ | 209/363 [02:32<01:11, 2.15it/s]
Loading 0: 58%|█████▊ | 211/363 [02:33<01:40, 1.51it/s]
Loading 0: 58%|█████▊ | 212/363 [02:35<02:21, 1.07it/s]
Loading 0: 59%|█████▊ | 213/363 [02:38<03:03, 1.22s/it]
Loading 0: 60%|█████▉ | 216/363 [02:38<01:37, 1.51it/s]
Loading 0: 60%|█████▉ | 217/363 [02:38<01:24, 1.72it/s]
Loading 0: 60%|██████ | 218/363 [02:38<01:09, 2.07it/s]
Loading 0: 61%|██████ | 220/363 [02:40<01:35, 1.49it/s]
Loading 0: 61%|██████ | 221/363 [02:42<02:13, 1.06it/s]
Loading 0: 61%|██████ | 222/363 [02:44<02:48, 1.19s/it]
Loading 0: 62%|██████▏ | 225/363 [02:44<01:28, 1.56it/s]
Loading 0: 62%|██████▏ | 226/363 [02:45<01:17, 1.78it/s]
Loading 0: 63%|██████▎ | 227/363 [02:45<01:03, 2.14it/s]
Loading 0: 63%|██████▎ | 229/363 [02:47<01:28, 1.51it/s]
Loading 0: 63%|██████▎ | 230/363 [02:49<02:04, 1.07it/s]
Loading 0: 64%|██████▎ | 231/363 [03:04<09:12, 4.19s/it]
Loading 0: 64%|██████▍ | 234/363 [03:04<04:35, 2.14s/it]
Loading 0: 65%|██████▍ | 235/363 [03:04<03:46, 1.77s/it]
Loading 0: 65%|██████▌ | 236/363 [03:04<02:59, 1.42s/it]
Loading 0: 66%|██████▌ | 238/363 [03:06<02:33, 1.23s/it]
Loading 0: 66%|██████▌ | 239/363 [03:08<02:47, 1.35s/it]
Loading 0: 66%|██████▌ | 240/363 [03:10<03:02, 1.48s/it]
Loading 0: 67%|██████▋ | 243/363 [03:10<01:34, 1.27it/s]
Loading 0: 67%|██████▋ | 244/363 [03:10<01:20, 1.48it/s]
Loading 0: 67%|██████▋ | 245/363 [03:10<01:05, 1.80it/s]
Loading 0: 68%|██████▊ | 247/363 [03:12<01:20, 1.44it/s]
Loading 0: 68%|██████▊ | 248/363 [03:14<01:47, 1.07it/s]
Loading 0: 69%|██████▊ | 249/363 [03:16<02:14, 1.18s/it]
Loading 0: 69%|██████▉ | 252/363 [03:16<01:10, 1.57it/s]
Loading 0: 70%|██████▉ | 253/363 [03:16<01:01, 1.80it/s]
Loading 0: 70%|██████▉ | 254/363 [03:17<00:50, 2.17it/s]
Loading 0: 71%|███████ | 256/363 [03:19<01:09, 1.53it/s]
Loading 0: 71%|███████ | 257/363 [03:20<01:35, 1.11it/s]
Loading 0: 71%|███████ | 258/363 [03:22<02:01, 1.15s/it]
Loading 0: 72%|███████▏ | 261/363 [03:23<01:03, 1.60it/s]
Loading 0: 72%|███████▏ | 262/363 [03:23<00:54, 1.84it/s]
Loading 0: 72%|███████▏ | 263/363 [03:23<00:45, 2.19it/s]
Loading 0: 73%|███████▎ | 265/363 [03:25<01:01, 1.60it/s]
Loading 0: 73%|███████▎ | 266/363 [03:27<01:25, 1.14it/s]
Loading 0: 74%|███████▎ | 267/363 [03:29<01:49, 1.14s/it]
Loading 0: 74%|███████▍ | 270/363 [03:29<00:57, 1.63it/s]
Loading 0: 75%|███████▍ | 271/363 [03:29<00:49, 1.86it/s]
Loading 0: 75%|███████▍ | 272/363 [03:29<00:40, 2.24it/s]
Loading 0: 75%|███████▌ | 274/363 [03:31<00:55, 1.61it/s]
Loading 0: 76%|███████▌ | 275/363 [03:33<01:17, 1.13it/s]
Loading 0: 76%|███████▌ | 276/363 [03:35<01:39, 1.14s/it]
Loading 0: 77%|███████▋ | 279/363 [03:35<00:51, 1.63it/s]
Loading 0: 77%|███████▋ | 280/363 [03:35<00:44, 1.86it/s]
Loading 0: 77%|███████▋ | 281/363 [03:35<00:36, 2.24it/s]
Loading 0: 78%|███████▊ | 283/363 [03:37<00:49, 1.60it/s]
Loading 0: 78%|███████▊ | 284/363 [03:39<01:09, 1.14it/s]
Loading 0: 79%|███████▊ | 285/363 [03:41<01:28, 1.14s/it]
Loading 0: 79%|███████▉ | 288/363 [03:41<00:45, 1.63it/s]
Loading 0: 80%|███████▉ | 289/363 [03:41<00:39, 1.86it/s]
Loading 0: 80%|███████▉ | 290/363 [03:42<00:32, 2.24it/s]
Loading 0: 80%|████████ | 292/363 [03:44<00:46, 1.54it/s]
Loading 0: 81%|████████ | 293/363 [03:46<01:06, 1.05it/s]
Loading 0: 81%|████████ | 294/363 [03:48<01:23, 1.20s/it]
Loading 0: 82%|████████▏ | 297/363 [03:48<00:42, 1.55it/s]
Loading 0: 82%|████████▏ | 298/363 [03:48<00:36, 1.78it/s]
Loading 0: 82%|████████▏ | 299/363 [03:48<00:29, 2.14it/s]
Loading 0: 83%|████████▎ | 301/363 [03:50<00:41, 1.50it/s]
Loading 0: 83%|████████▎ | 302/363 [03:52<00:57, 1.06it/s]
Loading 0: 83%|████████▎ | 303/363 [03:54<01:11, 1.19s/it]
Loading 0: 84%|████████▍ | 306/363 [03:54<00:36, 1.57it/s]
Loading 0: 85%|████████▍ | 307/363 [03:55<00:31, 1.79it/s]
Loading 0: 85%|████████▍ | 308/363 [03:55<00:25, 2.16it/s]
Loading 0: 85%|████████▌ | 310/363 [03:57<00:34, 1.52it/s]
Loading 0: 86%|████████▌ | 311/363 [03:59<00:48, 1.07it/s]
Loading 0: 86%|████████▌ | 312/363 [04:01<01:00, 1.18s/it]
Loading 0: 87%|████████▋ | 315/363 [04:01<00:30, 1.57it/s]
Loading 0: 87%|████████▋ | 316/363 [04:01<00:26, 1.80it/s]
Loading 0: 87%|████████▋ | 317/363 [04:01<00:21, 2.17it/s]
Loading 0: 88%|████████▊ | 319/363 [04:03<00:28, 1.52it/s]
Loading 0: 88%|████████▊ | 320/363 [04:05<00:39, 1.08it/s]
Loading 0: 88%|████████▊ | 321/363 [04:07<00:49, 1.18s/it]
Loading 0: 89%|████████▉ | 324/363 [04:07<00:24, 1.58it/s]
Loading 0: 90%|████████▉ | 325/363 [04:08<00:21, 1.81it/s]
Loading 0: 90%|████████▉ | 326/363 [04:08<00:16, 2.18it/s]
Loading 0: 90%|█████████ | 328/363 [04:10<00:22, 1.52it/s]
Loading 0: 91%|█████████ | 329/363 [04:12<00:31, 1.07it/s]
Loading 0: 91%|█████████ | 330/363 [04:14<00:40, 1.22s/it]
Loading 0: 92%|█████████▏| 333/363 [04:14<00:19, 1.53it/s]
Loading 0: 92%|█████████▏| 334/363 [04:14<00:16, 1.75it/s]
Loading 0: 92%|█████████▏| 335/363 [04:14<00:13, 2.12it/s]
Loading 0: 93%|█████████▎| 337/363 [04:16<00:17, 1.50it/s]
Loading 0: 93%|█████████▎| 338/363 [04:18<00:23, 1.07it/s]
Loading 0: 93%|█████████▎| 339/363 [04:20<00:28, 1.19s/it]
Loading 0: 94%|█████████▍| 342/363 [04:21<00:13, 1.57it/s]
Loading 0: 94%|█████████▍| 343/363 [04:21<00:11, 1.79it/s]
Loading 0: 95%|█████████▍| 344/363 [04:21<00:08, 2.16it/s]
Loading 0: 95%|█████████▌| 346/363 [04:23<00:11, 1.52it/s]
Loading 0: 96%|█████████▌| 347/363 [04:25<00:14, 1.07it/s]
Loading 0: 96%|█████████▌| 348/363 [04:27<00:17, 1.19s/it]
Loading 0: 97%|█████████▋| 351/363 [04:27<00:07, 1.56it/s]
Loading 0: 97%|█████████▋| 352/363 [04:27<00:06, 1.79it/s]
Loading 0: 97%|█████████▋| 353/363 [04:27<00:04, 2.16it/s]
Loading 0: 98%|█████████▊| 355/363 [04:29<00:05, 1.52it/s]
Loading 0: 98%|█████████▊| 356/363 [04:31<00:06, 1.07it/s]
Loading 0: 98%|█████████▊| 357/363 [04:33<00:07, 1.18s/it]
Loading 0: 99%|█████████▉| 360/363 [04:34<00:01, 1.57it/s]
Loading 0: 99%|█████████▉| 361/363 [04:34<00:01, 1.79it/s]
Loading 0: 100%|█████████▉| 362/363 [04:34<00:00, 2.16it/s]
Job chaiml-2a6f-6970-linear-w02-v3-mkmlizer completed after 450.1s with status: succeeded
Stopping job with name chaiml-2a6f-6970-linear-w02-v3-mkmlizer
Pipeline stage MKMLizer completed in 450.57s
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-2a6f-6970-linear-w02-v3
Waiting for inference service chaiml-2a6f-6970-linear-w02-v3 to be ready
Inference service chaiml-2a6f-6970-linear-w02-v3 ready after 40.19390392303467s
Pipeline stage MKMLDeployer completed in 40.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.383214235305786s
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', '')
Received healthy response to inference request in 2.192873239517212s
Received healthy response to inference request in 2.2059600353240967s
Received healthy response to inference request in 2.007335901260376s
Received healthy response to inference request in 1.8439393043518066s
5 requests
0 failed requests
5th percentile: 1.8766186237335205
10th percentile: 1.9092979431152344
20th percentile: 1.974656581878662
30th percentile: 2.044443368911743
40th percentile: 2.1186583042144775
50th percentile: 2.192873239517212
60th percentile: 2.198107957839966
70th percentile: 2.2033426761627197
80th percentile: 2.2414108753204345
90th percentile: 2.3123125553131105
95th percentile: 2.3477633953094483
99th percentile: 2.3761240673065185
mean time: 2.1266645431518554
Pipeline stage StressChecker completed in 12.00s
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 0.61s
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 0.60s
Shutdown handler de-registered
chaiml-2a6f-6970-linear-w02_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-2a6f-6970-linear-w02-v3-profiler
Waiting for inference service chaiml-2a6f-6970-linear-w02-v3-profiler to be ready
Inference service chaiml-2a6f-6970-linear-w02-v3-profiler ready after 60.4591281414032s
Pipeline stage MKMLProfilerDeployer completed in 61.00s
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-2a6f-6970-linff83df9d352acb35f9953d8931c70b5e-deplowznvw:/code/chaiverse_profiler_1759692713 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-2a6f-6970-linff83df9d352acb35f9953d8931c70b5e-deplowznvw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1759692713 && 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_1759692713/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 2910.77s
Shutdown handler de-registered
chaiml-2a6f-6970-linear-w02_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-2a6f-6970-linear-w02_v3 status is now torndown due to DeploymentManager action