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 infermatic-14b-qwen2-5-i-2442-v1-mkmlizer
Waiting for job on infermatic-14b-qwen2-5-i-2442-v1-mkmlizer to finish
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ Version: 0.30.2 ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ https://mk1.ai ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ The license key for the current software has been verified as ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ belonging to: ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ Chai Research Corp. ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ║ ║
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: Downloaded to shared memory in 30.310s
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: Checking if Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 already exists in ChaiML
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: Creating repo ChaiML/14b-Qwen2.5-Infermatic-Crea-v2 and uploading /tmp/tmphaf534wr to it
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer:
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:04<00:29, 4.98s/it]
29%|██▊ | 2/7 [00:09<00:24, 4.92s/it]
43%|████▎ | 3/7 [00:13<00:17, 4.41s/it]
57%|█████▋ | 4/7 [00:17<00:12, 4.29s/it]
71%|███████▏ | 5/7 [00:21<00:07, 4.00s/it]
86%|████████▌ | 6/7 [00:24<00:03, 3.77s/it]
100%|██████████| 7/7 [00:24<00:00, 2.65s/it]
100%|██████████| 7/7 [00:24<00:00, 3.56s/it]
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmphaf534wr, device:0
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 0%| | 2/579 [00:00<00:58, 9.93it/s]
Loading 0: 1%| | 4/579 [00:01<02:49, 3.40it/s]
Loading 0: 1%| | 5/579 [00:01<04:22, 2.19it/s]
Loading 0: 1%| | 6/579 [00:02<05:43, 1.67it/s]
Loading 0: 2%|▏ | 10/579 [00:03<02:40, 3.55it/s]
Loading 0: 2%|▏ | 12/579 [00:03<02:17, 4.12it/s]
Loading 0: 2%|▏ | 14/579 [00:03<01:49, 5.17it/s]
Loading 0: 3%|▎ | 16/579 [00:04<02:32, 3.69it/s]
Loading 0: 3%|▎ | 17/579 [00:05<03:40, 2.54it/s]
Loading 0: 3%|▎ | 18/579 [00:06<05:02, 1.86it/s]
Loading 0: 4%|▍ | 22/579 [00:07<02:47, 3.32it/s]
Loading 0: 4%|▍ | 24/579 [00:07<02:26, 3.78it/s]
Loading 0: 4%|▍ | 26/579 [00:07<01:59, 4.63it/s]
Loading 0: 5%|▍ | 28/579 [00:08<02:31, 3.63it/s]
Loading 0: 5%|▌ | 29/579 [00:09<03:24, 2.69it/s]
Loading 0: 5%|▌ | 30/579 [00:10<04:24, 2.08it/s]
Loading 0: 6%|▌ | 34/579 [00:10<02:30, 3.62it/s]
Loading 0: 6%|▌ | 36/579 [00:10<02:12, 4.11it/s]
Loading 0: 7%|▋ | 38/579 [00:11<01:49, 4.92it/s]
Loading 0: 7%|▋ | 40/579 [00:11<02:22, 3.78it/s]
Loading 0: 7%|▋ | 41/579 [00:12<03:30, 2.56it/s]
Loading 0: 7%|▋ | 42/579 [00:13<04:25, 2.03it/s]
Loading 0: 8%|▊ | 46/579 [00:14<02:30, 3.54it/s]
Loading 0: 8%|▊ | 48/579 [00:14<02:11, 4.04it/s]
Loading 0: 9%|▊ | 50/579 [00:14<01:48, 4.86it/s]
Loading 0: 9%|▉ | 52/579 [00:15<02:20, 3.76it/s]
Loading 0: 9%|▉ | 53/579 [00:16<03:10, 2.76it/s]
Loading 0: 9%|▉ | 54/579 [00:17<04:05, 2.14it/s]
Loading 0: 10%|█ | 58/579 [00:17<02:20, 3.72it/s]
Loading 0: 10%|█ | 60/579 [00:17<02:03, 4.20it/s]
Loading 0: 11%|█ | 62/579 [00:18<01:41, 5.10it/s]
Loading 0: 11%|█ | 64/579 [00:18<02:13, 3.85it/s]
Loading 0: 11%|█ | 65/579 [00:19<03:03, 2.80it/s]
Loading 0: 11%|█▏ | 66/579 [00:20<03:59, 2.14it/s]
Loading 0: 12%|█▏ | 70/579 [00:21<02:17, 3.71it/s]
Loading 0: 12%|█▏ | 72/579 [00:21<02:00, 4.20it/s]
Loading 0: 13%|█▎ | 74/579 [00:21<01:38, 5.15it/s]
Loading 0: 13%|█▎ | 76/579 [00:22<02:09, 3.88it/s]
Loading 0: 13%|█▎ | 77/579 [00:23<02:58, 2.81it/s]
Loading 0: 13%|█▎ | 78/579 [00:24<03:50, 2.17it/s]
Loading 0: 14%|█▍ | 82/579 [00:24<02:12, 3.76it/s]
Loading 0: 15%|█▍ | 84/579 [00:24<01:56, 4.24it/s]
Loading 0: 15%|█▍ | 86/579 [00:24<01:35, 5.15it/s]
Loading 0: 15%|█▌ | 88/579 [00:25<02:06, 3.87it/s]
Loading 0: 15%|█▌ | 89/579 [00:26<02:54, 2.81it/s]
Loading 0: 16%|█▌ | 90/579 [00:27<03:46, 2.16it/s]
Loading 0: 16%|█▌ | 94/579 [00:27<02:09, 3.74it/s]
Loading 0: 17%|█▋ | 96/579 [00:28<01:54, 4.23it/s]
Loading 0: 17%|█▋ | 98/579 [00:28<01:35, 5.05it/s]
Loading 0: 17%|█▋ | 100/579 [00:29<02:05, 3.83it/s]
Loading 0: 17%|█▋ | 101/579 [00:30<02:51, 2.79it/s]
Loading 0: 18%|█▊ | 102/579 [00:30<03:41, 2.15it/s]
Loading 0: 18%|█▊ | 106/579 [00:31<02:06, 3.73it/s]
Loading 0: 19%|█▊ | 108/579 [00:31<01:51, 4.22it/s]
Loading 0: 19%|█▉ | 110/579 [00:31<01:31, 5.14it/s]
Loading 0: 19%|█▉ | 112/579 [00:32<02:00, 3.87it/s]
Loading 0: 20%|█▉ | 113/579 [00:33<02:45, 2.81it/s]
Loading 0: 20%|█▉ | 114/579 [00:34<03:35, 2.16it/s]
Loading 0: 20%|██ | 118/579 [00:34<02:03, 3.75it/s]
Loading 0: 21%|██ | 120/579 [00:35<01:48, 4.23it/s]
Loading 0: 21%|██ | 122/579 [00:35<01:31, 5.02it/s]
Loading 0: 21%|██▏ | 124/579 [00:36<01:59, 3.82it/s]
Loading 0: 22%|██▏ | 125/579 [00:36<02:42, 2.79it/s]
Loading 0: 22%|██▏ | 126/579 [00:37<03:29, 2.16it/s]
Loading 0: 22%|██▏ | 130/579 [00:38<01:59, 3.76it/s]
Loading 0: 23%|██▎ | 132/579 [00:38<01:45, 4.24it/s]
Loading 0: 23%|██▎ | 134/579 [00:38<01:26, 5.14it/s]
Loading 0: 23%|██▎ | 136/579 [00:39<01:54, 3.86it/s]
Loading 0: 24%|██▎ | 137/579 [00:40<02:37, 2.81it/s]
Loading 0: 24%|██▍ | 138/579 [00:41<03:24, 2.15it/s]
Loading 0: 25%|██▍ | 142/579 [00:41<01:56, 3.74it/s]
Loading 0: 25%|██▍ | 144/579 [00:41<01:42, 4.23it/s]
Loading 0: 25%|██▌ | 146/579 [00:42<01:23, 5.17it/s]
Loading 0: 26%|██▌ | 148/579 [00:42<01:50, 3.90it/s]
Loading 0: 26%|██▌ | 149/579 [00:44<02:49, 2.53it/s]
Loading 0: 26%|██▌ | 150/579 [00:44<03:37, 1.98it/s]
Loading 0: 27%|██▋ | 154/579 [00:45<02:02, 3.46it/s]
Loading 0: 27%|██▋ | 156/579 [00:45<01:50, 3.82it/s]
Loading 0: 27%|██▋ | 158/579 [00:45<01:32, 4.56it/s]
Loading 0: 28%|██▊ | 160/579 [00:46<01:56, 3.61it/s]
Loading 0: 28%|██▊ | 161/579 [00:47<02:35, 2.69it/s]
Loading 0: 28%|██▊ | 162/579 [00:48<03:17, 2.11it/s]
Loading 0: 29%|██▊ | 166/579 [00:48<01:52, 3.68it/s]
Loading 0: 29%|██▉ | 168/579 [00:49<01:38, 4.17it/s]
Loading 0: 29%|██▉ | 170/579 [00:49<01:22, 4.95it/s]
Loading 0: 30%|██▉ | 172/579 [00:50<01:47, 3.79it/s]
Loading 0: 30%|██▉ | 173/579 [00:51<02:26, 2.78it/s]
Loading 0: 30%|███ | 174/579 [00:51<03:07, 2.16it/s]
Loading 0: 31%|███ | 178/579 [00:52<01:46, 3.75it/s]
Loading 0: 31%|███ | 180/579 [00:52<01:34, 4.23it/s]
Loading 0: 31%|███▏ | 182/579 [00:52<01:17, 5.15it/s]
Loading 0: 32%|███▏ | 184/579 [00:53<01:42, 3.87it/s]
Loading 0: 32%|███▏ | 185/579 [00:54<02:20, 2.81it/s]
Loading 0: 32%|███▏ | 186/579 [00:55<03:02, 2.16it/s]
Loading 0: 33%|███▎ | 190/579 [00:55<01:43, 3.74it/s]
Loading 0: 33%|███▎ | 192/579 [00:56<01:31, 4.23it/s]
Loading 0: 34%|███▎ | 194/579 [00:56<01:15, 5.11it/s]
Loading 0: 34%|███▍ | 196/579 [00:57<01:39, 3.85it/s]
Loading 0: 34%|███▍ | 197/579 [00:57<02:16, 2.80it/s]
Loading 0: 34%|███▍ | 198/579 [00:58<02:56, 2.16it/s]
Loading 0: 35%|███▍ | 202/579 [00:59<01:40, 3.75it/s]
Loading 0: 35%|███▌ | 204/579 [00:59<01:28, 4.24it/s]
Loading 0: 36%|███▌ | 206/579 [00:59<01:13, 5.09it/s]
Loading 0: 36%|███▌ | 208/579 [01:00<01:36, 3.84it/s]
Loading 0: 36%|███▌ | 209/579 [01:01<02:12, 2.80it/s]
Loading 0: 36%|███▋ | 210/579 [01:02<02:50, 2.17it/s]
Loading 0: 37%|███▋ | 214/579 [01:02<01:37, 3.76it/s]
Loading 0: 37%|███▋ | 216/579 [01:02<01:25, 4.24it/s]
Loading 0: 38%|███▊ | 218/579 [01:03<01:10, 5.15it/s]
Loading 0: 38%|███▊ | 220/579 [01:03<01:32, 3.88it/s]
Loading 0: 38%|███▊ | 221/579 [01:04<02:07, 2.81it/s]
Loading 0: 38%|███▊ | 222/579 [01:05<02:46, 2.14it/s]
Loading 0: 39%|███▉ | 226/579 [01:06<01:34, 3.72it/s]
Loading 0: 39%|███▉ | 228/579 [01:06<01:23, 4.20it/s]
Loading 0: 40%|███▉ | 230/579 [01:06<01:09, 5.04it/s]
Loading 0: 40%|████ | 232/579 [01:07<01:30, 3.83it/s]
Loading 0: 40%|████ | 233/579 [01:08<02:03, 2.79it/s]
Loading 0: 40%|████ | 234/579 [01:09<02:39, 2.16it/s]
Loading 0: 41%|████ | 238/579 [01:09<01:31, 3.74it/s]
Loading 0: 41%|████▏ | 240/579 [01:09<01:20, 4.22it/s]
Loading 0: 42%|████▏ | 242/579 [01:10<01:07, 4.99it/s]
Loading 0: 42%|████▏ | 244/579 [01:10<01:28, 3.80it/s]
Loading 0: 42%|████▏ | 245/579 [01:11<02:00, 2.77it/s]
Loading 0: 42%|████▏ | 246/579 [01:12<02:35, 2.14it/s]
Loading 0: 43%|████▎ | 250/579 [01:12<01:28, 3.72it/s]
Loading 0: 44%|████▎ | 252/579 [01:13<01:17, 4.20it/s]
Loading 0: 44%|████▍ | 254/579 [01:13<01:03, 5.15it/s]
Loading 0: 44%|████▍ | 256/579 [01:14<01:23, 3.86it/s]
Loading 0: 44%|████▍ | 257/579 [01:15<02:04, 2.59it/s]
Loading 0: 45%|████▍ | 258/579 [01:16<02:36, 2.05it/s]
Loading 0: 45%|████▌ | 262/579 [01:16<01:28, 3.59it/s]
Loading 0: 46%|████▌ | 264/579 [01:16<01:17, 4.09it/s]
Loading 0: 46%|████▌ | 266/579 [01:17<01:02, 5.02it/s]
Loading 0: 46%|████▋ | 268/579 [01:17<01:21, 3.82it/s]
Loading 0: 46%|████▋ | 269/579 [01:18<01:51, 2.78it/s]
Loading 0: 47%|████▋ | 270/579 [01:19<02:23, 2.15it/s]
Loading 0: 47%|████▋ | 274/579 [01:19<01:21, 3.73it/s]
Loading 0: 48%|████▊ | 276/579 [01:20<01:11, 4.21it/s]
Loading 0: 48%|████▊ | 278/579 [01:20<01:00, 4.99it/s]
Loading 0: 48%|████▊ | 280/579 [01:21<01:23, 3.58it/s]
Loading 0: 49%|████▊ | 281/579 [01:22<01:53, 2.63it/s]
Loading 0: 49%|████▊ | 282/579 [01:23<02:24, 2.06it/s]
Loading 0: 49%|████▉ | 286/579 [01:23<01:21, 3.59it/s]
Loading 0: 50%|████▉ | 288/579 [01:23<01:13, 3.98it/s]
Loading 0: 50%|█████ | 290/579 [01:24<00:59, 4.85it/s]
Loading 0: 50%|█████ | 292/579 [01:24<01:16, 3.75it/s]
Loading 0: 51%|█████ | 293/579 [01:25<01:43, 2.76it/s]
Loading 0: 51%|█████ | 294/579 [01:26<02:12, 2.14it/s]
Loading 0: 51%|█████▏ | 298/579 [01:27<01:15, 3.73it/s]
Loading 0: 52%|█████▏ | 300/579 [01:27<01:06, 4.22it/s]
Loading 0: 52%|█████▏ | 302/579 [01:27<00:54, 5.09it/s]
Loading 0: 53%|█████▎ | 304/579 [01:28<01:11, 3.86it/s]
Loading 0: 53%|█████▎ | 305/579 [01:29<01:37, 2.80it/s]
Loading 0: 53%|█████▎ | 306/579 [01:30<02:06, 2.16it/s]
Loading 0: 54%|█████▎ | 310/579 [01:30<01:11, 3.75it/s]
Loading 0: 54%|█████▍ | 312/579 [01:30<01:03, 4.23it/s]
Loading 0: 54%|█████▍ | 314/579 [01:31<00:52, 5.06it/s]
Loading 0: 55%|█████▍ | 316/579 [01:31<01:08, 3.84it/s]
Loading 0: 55%|█████▍ | 317/579 [01:32<01:33, 2.80it/s]
Loading 0: 55%|█████▍ | 318/579 [01:33<02:00, 2.16it/s]
Loading 0: 56%|█████▌ | 322/579 [01:33<01:08, 3.75it/s]
Loading 0: 56%|█████▌ | 324/579 [01:34<01:00, 4.24it/s]
Loading 0: 56%|█████▋ | 326/579 [01:34<00:49, 5.13it/s]
Loading 0: 57%|█████▋ | 328/579 [01:35<01:05, 3.86it/s]
Loading 0: 57%|█████▋ | 329/579 [01:36<01:29, 2.80it/s]
Loading 0: 57%|█████▋ | 330/579 [01:36<01:55, 2.16it/s]
Loading 0: 58%|█████▊ | 334/579 [01:37<01:05, 3.75it/s]
Loading 0: 58%|█████▊ | 336/579 [01:37<00:57, 4.23it/s]
Loading 0: 58%|█████▊ | 338/579 [01:37<00:47, 5.06it/s]
Loading 0: 59%|█████▊ | 340/579 [01:38<01:02, 3.85it/s]
Loading 0: 59%|█████▉ | 341/579 [01:39<01:24, 2.80it/s]
Loading 0: 59%|█████▉ | 342/579 [01:40<01:49, 2.16it/s]
Loading 0: 60%|█████▉ | 346/579 [01:40<01:02, 3.75it/s]
Loading 0: 60%|██████ | 348/579 [01:41<00:54, 4.23it/s]
Loading 0: 60%|██████ | 350/579 [01:41<00:44, 5.15it/s]
Loading 0: 61%|██████ | 352/579 [01:42<00:58, 3.89it/s]
Loading 0: 61%|██████ | 353/579 [01:42<01:19, 2.83it/s]
Loading 0: 61%|██████ | 354/579 [01:43<01:43, 2.18it/s]
Loading 0: 62%|██████▏ | 358/579 [01:44<00:58, 3.77it/s]
Loading 0: 62%|██████▏ | 360/579 [01:44<00:51, 4.26it/s]
Loading 0: 63%|██████▎ | 362/579 [01:44<00:42, 5.11it/s]
Loading 0: 63%|██████▎ | 364/579 [01:45<00:55, 3.86it/s]
Loading 0: 63%|██████▎ | 365/579 [01:46<01:22, 2.61it/s]
Loading 0: 63%|██████▎ | 366/579 [01:47<01:42, 2.08it/s]
Loading 0: 64%|██████▍ | 370/579 [01:47<00:57, 3.63it/s]
Loading 0: 64%|██████▍ | 372/579 [01:48<00:50, 4.13it/s]
Loading 0: 65%|██████▍ | 374/579 [01:48<00:40, 5.05it/s]
Loading 0: 65%|██████▍ | 376/579 [01:49<00:52, 3.85it/s]
Loading 0: 65%|██████▌ | 377/579 [01:49<01:11, 2.81it/s]
Loading 0: 65%|██████▌ | 378/579 [01:50<01:32, 2.17it/s]
Loading 0: 66%|██████▌ | 382/579 [01:51<00:52, 3.76it/s]
Loading 0: 66%|██████▋ | 384/579 [01:51<00:45, 4.25it/s]
Loading 0: 67%|██████▋ | 386/579 [01:51<00:37, 5.18it/s]
Loading 0: 67%|██████▋ | 388/579 [01:52<00:48, 3.90it/s]
Loading 0: 67%|██████▋ | 389/579 [01:53<01:06, 2.84it/s]
Loading 0: 67%|██████▋ | 390/579 [01:54<01:26, 2.19it/s]
Loading 0: 68%|██████▊ | 394/579 [01:54<00:48, 3.79it/s]
Loading 0: 68%|██████▊ | 396/579 [01:54<00:42, 4.28it/s]
Loading 0: 69%|██████▊ | 398/579 [01:55<00:35, 5.15it/s]
Loading 0: 69%|██████▉ | 400/579 [01:55<00:46, 3.89it/s]
Loading 0: 69%|██████▉ | 401/579 [01:56<01:03, 2.83it/s]
Loading 0: 69%|██████▉ | 402/579 [01:57<01:21, 2.16it/s]
Loading 0: 70%|███████ | 406/579 [01:57<00:46, 3.75it/s]
Loading 0: 70%|███████ | 408/579 [01:58<00:40, 4.24it/s]
Loading 0: 71%|███████ | 410/579 [01:58<00:33, 5.09it/s]
Loading 0: 71%|███████ | 412/579 [01:59<00:47, 3.48it/s]
Loading 0: 71%|███████▏ | 413/579 [02:00<01:03, 2.61it/s]
Loading 0: 72%|███████▏ | 414/579 [02:01<01:20, 2.04it/s]
Loading 0: 72%|███████▏ | 418/579 [02:01<00:45, 3.58it/s]
Loading 0: 73%|███████▎ | 420/579 [02:01<00:39, 4.05it/s]
Loading 0: 73%|███████▎ | 422/579 [02:02<00:31, 4.95it/s]
Loading 0: 73%|███████▎ | 424/579 [02:02<00:40, 3.81it/s]
Loading 0: 73%|███████▎ | 425/579 [02:03<00:55, 2.80it/s]
Loading 0: 74%|███████▎ | 426/579 [02:04<01:10, 2.16it/s]
Loading 0: 74%|███████▍ | 430/579 [02:05<00:39, 3.76it/s]
Loading 0: 75%|███████▍ | 432/579 [02:05<00:34, 4.24it/s]
Loading 0: 75%|███████▍ | 434/579 [02:05<00:28, 5.08it/s]
Loading 0: 75%|███████▌ | 436/579 [02:06<00:37, 3.86it/s]
Loading 0: 75%|███████▌ | 437/579 [02:07<00:50, 2.82it/s]
Loading 0: 76%|███████▌ | 438/579 [02:08<01:04, 2.18it/s]
Loading 0: 76%|███████▋ | 442/579 [02:08<00:36, 3.78it/s]
Loading 0: 77%|███████▋ | 444/579 [02:08<00:31, 4.27it/s]
Loading 0: 77%|███████▋ | 446/579 [02:08<00:25, 5.22it/s]
Loading 0: 77%|███████▋ | 448/579 [02:09<00:33, 3.92it/s]
Loading 0: 78%|███████▊ | 449/579 [02:10<00:45, 2.84it/s]
Loading 0: 78%|███████▊ | 450/579 [02:11<00:58, 2.19it/s]
Loading 0: 78%|███████▊ | 454/579 [02:11<00:32, 3.79it/s]
Loading 0: 79%|███████▉ | 456/579 [02:12<00:28, 4.28it/s]
Loading 0: 79%|███████▉ | 458/579 [02:12<00:23, 5.22it/s]
Loading 0: 79%|███████▉ | 460/579 [02:13<00:30, 3.92it/s]
Loading 0: 80%|███████▉ | 461/579 [02:13<00:41, 2.84it/s]
Loading 0: 80%|███████▉ | 462/579 [02:14<00:53, 2.18it/s]
Loading 0: 80%|████████ | 466/579 [02:15<00:29, 3.78it/s]
Loading 0: 81%|████████ | 468/579 [02:15<00:26, 4.26it/s]
Loading 0: 81%|████████ | 4
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: quantized model in 179.880s
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: Processed model Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 in 258.669s
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: creating bucket guanaco-mkml-models
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/config.json
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/added_tokens.json
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/merges.txt
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/tokenizer_config.json
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/special_tokens_map.json
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/vocab.json
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/tokenizer.json
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/infermatic-14b-qwen2-5-i-2442-v1/nvidia/flywheel_model.0.safetensors
infermatic-14b-qwen2-5-i-2442-v1-mkmlizer: 70/579 [02:15<00:21, 5.08it/s]
Loading 0: 82%|████████▏ | 472/579 [02:16<00:27, 3.86it/s]
Loading 0: 82%|████████▏ | 473/579 [02:17<00:40, 2.61it/s]
Loading 0: 82%|████████▏ | 474/579 [02:18<00:50, 2.08it/s]
Loading 0: 83%|████████▎ | 478/579 [02:18<00:27, 3.63it/s]
Loading 0: 83%|████████▎ | 480/579 [02:19<00:24, 4.12it/s]
Loading 0: 83%|████████▎ | 482/579 [02:19<00:19, 4.97it/s]
Loading 0: 84%|████████▎ | 484/579 [02:20<00:24, 3.81it/s]
Loading 0: 84%|████████▍ | 485/579 [02:20<00:33, 2.79it/s]
Loading 0: 84%|████████▍ | 486/579 [02:21<00:42, 2.16it/s]
Loading 0: 85%|████████▍ | 490/579 [02:22<00:23, 3.75it/s]
Loading 0: 85%|████████▍ | 492/579 [02:22<00:20, 4.24it/s]
Loading 0: 85%|████████▌ | 494/579 [02:22<00:16, 5.09it/s]
Loading 0: 86%|████████▌ | 496/579 [02:23<00:21, 3.85it/s]
Loading 0: 86%|████████▌ | 497/579 [02:24<00:29, 2.81it/s]
Loading 0: 86%|████████▌ | 498/579 [02:25<00:37, 2.16it/s]
Loading 0: 87%|████████▋ | 502/579 [02:25<00:20, 3.75it/s]
Loading 0: 87%|████████▋ | 504/579 [02:25<00:17, 4.24it/s]
Loading 0: 87%|████████▋ | 506/579 [02:26<00:14, 5.14it/s]
Loading 0: 88%|████████▊ | 508/579 [02:26<00:18, 3.85it/s]
Loading 0: 88%|████████▊ | 509/579 [02:27<00:24, 2.81it/s]
Loading 0: 88%|████████▊ | 510/579 [02:28<00:31, 2.17it/s]
Loading 0: 89%|████████▉ | 514/579 [02:29<00:17, 3.75it/s]
Loading 0: 89%|████████▉ | 516/579 [02:29<00:14, 4.24it/s]
Loading 0: 89%|████████▉ | 518/579 [02:29<00:11, 5.12it/s]
Loading 0: 90%|████████▉ | 520/579 [02:30<00:16, 3.59it/s]
Loading 0: 90%|████████▉ | 521/579 [02:31<00:21, 2.65it/s]
Loading 0: 90%|█████████ | 522/579 [02:32<00:27, 2.09it/s]
Loading 0: 91%|█████████ | 526/579 [02:32<00:14, 3.65it/s]
Loading 0: 91%|█████████ | 528/579 [02:32<00:12, 4.14it/s]
Loading 0: 92%|█████████▏| 530/579 [02:33<00:09, 5.04it/s]
Loading 0: 92%|█████████▏| 532/579 [02:34<00:12, 3.64it/s]
Loading 0: 92%|█████████▏| 533/579 [02:34<00:17, 2.70it/s]
Loading 0: 92%|█████████▏| 534/579 [02:35<00:21, 2.11it/s]
Loading 0: 93%|█████████▎| 538/579 [02:36<00:11, 3.68it/s]
Loading 0: 93%|█████████▎| 540/579 [02:36<00:09, 4.17it/s]
Loading 0: 94%|█████████▎| 542/579 [02:36<00:07, 5.08it/s]
Loading 0: 94%|█████████▍| 544/579 [02:37<00:09, 3.85it/s]
Loading 0: 94%|█████████▍| 545/579 [02:38<00:12, 2.80it/s]
Loading 0: 94%|█████████▍| 546/579 [02:39<00:15, 2.17it/s]
Loading 0: 95%|█████████▍| 550/579 [02:39<00:07, 3.76it/s]
Loading 0: 95%|█████████▌| 552/579 [02:39<00:06, 4.25it/s]
Loading 0: 96%|█████████▌| 554/579 [02:40<00:04, 5.07it/s]
Loading 0: 96%|█████████▌| 556/579 [02:40<00:05, 3.84it/s]
Loading 0: 96%|█████████▌| 557/579 [02:41<00:07, 2.81it/s]
Loading 0: 96%|█████████▋| 558/579 [02:42<00:09, 2.17it/s]
Loading 0: 97%|█████████▋| 562/579 [02:42<00:04, 3.77it/s]
Loading 0: 97%|█████████▋| 564/579 [02:43<00:03, 4.25it/s]
Loading 0: 98%|█████████▊| 566/579 [02:43<00:02, 5.20it/s]
Loading 0: 98%|█████████▊| 568/579 [02:44<00:02, 3.90it/s]
Loading 0: 98%|█████████▊| 569/579 [02:45<00:03, 2.83it/s]
Loading 0: 98%|█████████▊| 570/579 [02:45<00:04, 2.17it/s]
Loading 0: 99%|█████████▉| 574/579 [02:46<00:01, 3.76it/s]
Loading 0: 99%|█████████▉| 576/579 [02:46<00:00, 4.25it/s]
Loading 0: 100%|█████████▉| 578/579 [02:46<00:00, 5.19it/s]
Job infermatic-14b-qwen2-5-i-2442-v1-mkmlizer completed after 289.14s with status: succeeded
Stopping job with name infermatic-14b-qwen2-5-i-2442-v1-mkmlizer
Pipeline stage MKMLizer completed in 289.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service infermatic-14b-qwen2-5-i-2442-v1
Waiting for inference service infermatic-14b-qwen2-5-i-2442-v1 to be ready
Inference service infermatic-14b-qwen2-5-i-2442-v1 ready after 90.11922264099121s
Pipeline stage MKMLDeployer completed in 90.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0872325897216797s
Received healthy response to inference request in 2.2025463581085205s
Received healthy response to inference request in 0.8149323463439941s
Received healthy response to inference request in 1.112051010131836s
Received healthy response to inference request in 1.7805273532867432s
5 requests
0 failed requests
5th percentile: 0.8743560791015625
10th percentile: 0.9337798118591308
20th percentile: 1.0526272773742675
30th percentile: 1.2457462787628173
40th percentile: 1.5131368160247805
50th percentile: 1.7805273532867432
60th percentile: 1.9032094478607178
70th percentile: 2.0258915424346924
80th percentile: 2.1102953433990477
90th percentile: 2.156420850753784
95th percentile: 2.1794836044311525
99th percentile: 2.197933807373047
mean time: 1.5994579315185546
Pipeline stage StressChecker completed in 9.81s
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 0.64s
Shutdown handler de-registered
infermatic-14b-qwen2-5-i_2442_v1 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 2234.28s
Shutdown handler de-registered
infermatic-14b-qwen2-5-i_2442_v1 status is now inactive due to auto deactivation removed underperforming models
infermatic-14b-qwen2-5-i_2442_v1 status is now torndown due to DeploymentManager action