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 rirv938-llama-8b-mcl-500-9841-v1-mkmlizer
Waiting for job on rirv938-llama-8b-mcl-500-9841-v1-mkmlizer to finish
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ _____ __ __ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ /___/ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ║ ║
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: Downloaded to shared memory in 38.394s
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp9aacgxl9, device:0
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: quantized model in 87.246s
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: Processed model rirv938/llama_8b_mcl_500k_k_1_0_pct_256_tokens_step_1950 in 125.640s
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-mcl-500-9841-v1
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-mcl-500-9841-v1/tokenizer_config.json
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-mcl-500-9841-v1/tokenizer.json
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-mcl-500-9841-v1/flywheel_model.0.safetensors
rirv938-llama-8b-mcl-500-9841-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 3/291 [00:00<00:58, 4.95it/s]
Loading 0: 1%|▏ | 4/291 [00:01<01:34, 3.04it/s]
Loading 0: 2%|▏ | 5/291 [00:01<02:05, 2.27it/s]
Loading 0: 3%|▎ | 8/291 [00:02<01:04, 4.36it/s]
Loading 0: 3%|▎ | 9/291 [00:02<01:03, 4.43it/s]
Loading 0: 3%|▎ | 10/291 [00:02<00:55, 5.08it/s]
Loading 0: 4%|▍ | 12/291 [00:03<01:06, 4.20it/s]
Loading 0: 4%|▍ | 13/291 [00:03<01:28, 3.14it/s]
Loading 0: 5%|▍ | 14/291 [00:04<01:52, 2.46it/s]
Loading 0: 6%|▌ | 17/291 [00:04<01:04, 4.24it/s]
Loading 0: 6%|▌ | 18/291 [00:04<01:00, 4.48it/s]
Loading 0: 7%|▋ | 19/291 [00:04<00:54, 4.97it/s]
Loading 0: 7%|▋ | 21/291 [00:05<01:04, 4.18it/s]
Loading 0: 8%|▊ | 22/291 [00:05<01:24, 3.17it/s]
Loading 0: 8%|▊ | 23/291 [00:06<01:46, 2.51it/s]
Loading 0: 9%|▉ | 26/291 [00:06<01:01, 4.28it/s]
Loading 0: 9%|▉ | 27/291 [00:07<00:58, 4.52it/s]
Loading 0: 10%|▉ | 28/291 [00:07<00:51, 5.07it/s]
Loading 0: 10%|█ | 30/291 [00:07<01:01, 4.24it/s]
Loading 0: 11%|█ | 31/291 [00:08<01:21, 3.20it/s]
Loading 0: 11%|█ | 32/291 [00:09<01:42, 2.52it/s]
Loading 0: 12%|█▏ | 35/291 [00:09<00:59, 4.31it/s]
Loading 0: 12%|█▏ | 36/291 [00:09<00:56, 4.54it/s]
Loading 0: 13%|█▎ | 39/291 [00:10<00:56, 4.45it/s]
Loading 0: 14%|█▎ | 40/291 [00:10<01:13, 3.44it/s]
Loading 0: 14%|█▍ | 41/291 [00:11<01:31, 2.73it/s]
Loading 0: 15%|█▌ | 44/291 [00:11<00:56, 4.36it/s]
Loading 0: 15%|█▌ | 45/291 [00:11<00:53, 4.58it/s]
Loading 0: 16%|█▋ | 48/291 [00:12<00:54, 4.47it/s]
Loading 0: 17%|█▋ | 49/291 [00:13<01:09, 3.48it/s]
Loading 0: 17%|█▋ | 50/291 [00:13<01:27, 2.75it/s]
Loading 0: 18%|█▊ | 53/291 [00:13<00:54, 4.35it/s]
Loading 0: 19%|█▊ | 54/291 [00:14<00:51, 4.56it/s]
Loading 0: 19%|█▉ | 55/291 [00:14<00:46, 5.13it/s]
Loading 0: 20%|█▉ | 57/291 [00:14<00:54, 4.29it/s]
Loading 0: 20%|█▉ | 58/291 [00:15<01:11, 3.24it/s]
Loading 0: 20%|██ | 59/291 [00:16<01:30, 2.57it/s]
Loading 0: 21%|██▏ | 62/291 [00:16<00:52, 4.32it/s]
Loading 0: 22%|██▏ | 63/291 [00:16<00:50, 4.55it/s]
Loading 0: 23%|██▎ | 66/291 [00:17<00:50, 4.46it/s]
Loading 0: 23%|██▎ | 67/291 [00:17<01:04, 3.46it/s]
Loading 0: 23%|██▎ | 68/291 [00:18<01:21, 2.74it/s]
Loading 0: 24%|██▍ | 71/291 [00:18<00:49, 4.43it/s]
Loading 0: 25%|██▍ | 72/291 [00:18<00:47, 4.64it/s]
Loading 0: 26%|██▌ | 75/291 [00:19<00:47, 4.50it/s]
Loading 0: 26%|██▌ | 76/291 [00:20<01:01, 3.49it/s]
Loading 0: 26%|██▋ | 77/291 [00:20<01:17, 2.77it/s]
Loading 0: 27%|██▋ | 80/291 [00:20<00:47, 4.41it/s]
Loading 0: 28%|██▊ | 81/291 [00:21<00:45, 4.62it/s]
Loading 0: 29%|██▊ | 83/291 [00:21<00:40, 5.10it/s]
Loading 0: 29%|██▉ | 84/291 [00:21<00:56, 3.67it/s]
Loading 0: 29%|██▉ | 85/291 [00:22<01:10, 2.91it/s]
Loading 0: 30%|██▉ | 86/291 [00:23<01:25, 2.40it/s]
Loading 0: 31%|███ | 89/291 [00:23<00:48, 4.19it/s]
Loading 0: 31%|███ | 90/291 [00:23<00:45, 4.45it/s]
Loading 0: 32%|███▏ | 93/291 [00:24<00:44, 4.40it/s]
Loading 0: 32%|███▏ | 94/291 [00:24<00:57, 3.42it/s]
Loading 0: 33%|███▎ | 95/291 [00:25<01:11, 2.73it/s]
Loading 0: 34%|███▎ | 98/291 [00:25<00:44, 4.38it/s]
Loading 0: 34%|███▍ | 99/291 [00:25<00:41, 4.60it/s]
Loading 0: 35%|███▌ | 102/291 [00:26<00:42, 4.47it/s]
Loading 0: 35%|███▌ | 103/291 [00:27<00:54, 3.48it/s]
Loading 0: 36%|███▌ | 104/291 [00:27<01:07, 2.77it/s]
Loading 0: 37%|███▋ | 107/291 [00:28<00:41, 4.45it/s]
Loading 0: 37%|███▋ | 108/291 [00:28<00:39, 4.65it/s]
Loading 0: 38%|███▊ | 111/291 [00:28<00:39, 4.52it/s]
Loading 0: 38%|███▊ | 112/291 [00:29<00:50, 3.52it/s]
Loading 0: 39%|███▉ | 113/291 [00:30<01:03, 2.81it/s]
Loading 0: 40%|███▉ | 116/291 [00:30<00:39, 4.46it/s]
Loading 0: 40%|████ | 117/291 [00:30<00:37, 4.66it/s]
Loading 0: 41%|████ | 120/291 [00:31<00:37, 4.51it/s]
Loading 0: 42%|████▏ | 121/291 [00:31<00:48, 3.51it/s]
Loading 0: 42%|████▏ | 122/291 [00:32<01:00, 2.78it/s]
Loading 0: 43%|████▎ | 125/291 [00:32<00:37, 4.40it/s]
Loading 0: 43%|████▎ | 126/291 [00:32<00:35, 4.61it/s]
Loading 0: 44%|████▍ | 129/291 [00:33<00:35, 4.50it/s]
Loading 0: 45%|████▍ | 130/291 [00:34<00:45, 3.51it/s]
Loading 0: 45%|████▌ | 131/291 [00:34<00:57, 2.79it/s]
Loading 0: 46%|████▌ | 134/291 [00:34<00:35, 4.48it/s]
Loading 0: 46%|████▋ | 135/291 [00:35<00:33, 4.68it/s]
Loading 0: 47%|████▋ | 136/291 [00:35<00:29, 5.22it/s]
Loading 0: 47%|████▋ | 138/291 [00:35<00:35, 4.34it/s]
Loading 0: 48%|████▊ | 139/291 [00:36<00:46, 3.25it/s]
Loading 0: 48%|████▊ | 140/291 [00:37<00:58, 2.58it/s]
Loading 0: 49%|████▉ | 143/291 [00:37<00:33, 4.36it/s]
Loading 0: 49%|████▉ | 144/291 [00:37<00:32, 4.59it/s]
Loading 0: 51%|█████ | 147/291 [00:38<00:32, 4.47it/s]
Loading 0: 51%|█████ | 148/291 [00:38<00:41, 3.46it/s]
Loading 0: 51%|█████ | 149/291 [00:39<00:51, 2.75it/s]
Loading 0: 52%|█████▏ | 152/291 [00:39<00:31, 4.45it/s]
Loading 0: 53%|█████▎ | 153/291 [00:39<00:29, 4.65it/s]
Loading 0: 54%|█████▎ | 156/291 [00:40<00:29, 4.52it/s]
Loading 0: 54%|█████▍ | 157/291 [00:41<00:38, 3.49it/s]
Loading 0: 54%|█████▍ | 158/291 [00:41<00:47, 2.78it/s]
Loading 0: 55%|█████▌ | 161/291 [00:41<00:29, 4.40it/s]
Loading 0: 56%|█████▌ | 162/291 [00:42<00:28, 4.60it/s]
Loading 0: 56%|█████▌ | 163/291 [00:42<00:24, 5.17it/s]
Loading 0: 57%|█████▋ | 165/291 [00:42<00:29, 4.32it/s]
Loading 0: 57%|█████▋ | 166/291 [00:43<00:38, 3.25it/s]
Loading 0: 57%|█████▋ | 167/291 [00:44<00:48, 2.57it/s]
Loading 0: 58%|█████▊ | 170/291 [00:44<00:27, 4.38it/s]
Loading 0: 59%|█████▉ | 171/291 [00:44<00:26, 4.60it/s]
Loading 0: 59%|█████▉ | 173/291 [00:45<00:30, 3.82it/s]
Loading 0: 60%|██████ | 175/291 [00:45<00:24, 4.80it/s]
Loading 0: 60%|██████ | 176/291 [00:45<00:23, 4.97it/s]
Loading 0: 62%|██████▏ | 179/291 [00:46<00:23, 4.69it/s]
Loading 0: 62%|██████▏ | 180/291 [00:46<00:31, 3.57it/s]
Loading 0: 62%|██████▏ | 181/291 [00:47<00:39, 2.80it/s]
Loading 0: 63%|██████▎ | 184/291 [00:47<00:23, 4.48it/s]
Loading 0: 64%|██████▎ | 185/291 [00:47<00:22, 4.68it/s]
Loading 0: 64%|██████▍ | 187/291 [00:48<00:19, 5.28it/s]
Loading 0: 65%|██████▍ | 188/291 [00:48<00:27, 3.73it/s]
Loading 0: 65%|██████▍ | 189/291 [00:49<00:35, 2.85it/s]
Loading 0: 66%|██████▌ | 192/291 [00:49<00:27, 3.62it/s]
Loading 0: 66%|██████▋ | 193/291 [00:50<00:32, 2.98it/s]
Loading 0: 67%|██████▋ | 194/291 [00:51<00:39, 2.47it/s]
Loading 0: 68%|██████▊ | 197/291 [00:51<00:23, 4.07it/s]
Loading 0: 68%|██████▊ | 198/291 [00:51<00:21, 4.31it/s]
Loading 0: 69%|██████▉ | 201/291 [00:52<00:20, 4.32it/s]
Loading 0: 69%|██████▉ | 202/291 [00:52<00:26, 3.40it/s]
Loading 0: 70%|██████▉ | 203/291 [00:53<00:32, 2.72it/s]
Loading 0: 71%|███████ | 206/291 [00:53<00:19, 4.32it/s]
Loading 0: 71%|███████ | 207/291 [00:53<00:18, 4.53it/s]
Loading 0: 72%|███████▏ | 210/291 [00:54<00:18, 4.45it/s]
Loading 0: 73%|███████▎ | 211/291 [00:55<00:23, 3.47it/s]
Loading 0: 73%|███████▎ | 212/291 [00:55<00:28, 2.78it/s]
Loading 0: 74%|███████▍ | 215/291 [00:55<00:17, 4.38it/s]
Loading 0: 74%|███████▍ | 216/291 [00:56<00:16, 4.57it/s]
Loading 0: 75%|███████▍ | 217/291 [00:56<00:14, 5.09it/s]
Loading 0: 75%|███████▌ | 219/291 [00:56<00:16, 4.27it/s]
Loading 0: 76%|███████▌ | 220/291 [00:57<00:21, 3.24it/s]
Loading 0: 76%|███████▌ | 221/291 [00:58<00:27, 2.58it/s]
Loading 0: 77%|███████▋ | 224/291 [00:58<00:15, 4.33it/s]
Loading 0: 77%|███████▋ | 225/291 [00:58<00:14, 4.56it/s]
Loading 0: 78%|███████▊ | 226/291 [00:58<00:12, 5.13it/s]
Loading 0: 78%|███████▊ | 228/291 [00:59<00:14, 4.27it/s]
Loading 0: 79%|███████▊ | 229/291 [00:59<00:19, 3.22it/s]
Loading 0: 79%|███████▉ | 230/291 [01:00<00:24, 2.53it/s]
Loading 0: 80%|████████ | 233/291 [01:00<00:13, 4.28it/s]
Loading 0: 80%|████████ | 234/291 [01:00<00:12, 4.51it/s]
Loading 0: 81%|████████ | 235/291 [01:00<00:11, 5.08it/s]
Loading 0: 81%|████████▏ | 237/291 [01:01<00:12, 4.23it/s]
Loading 0: 82%|████████▏ | 238/291 [01:02<00:16, 3.21it/s]
Loading 0: 82%|████████▏ | 239/291 [01:02<00:20, 2.56it/s]
Loading 0: 83%|████████▎ | 242/291 [01:03<00:11, 4.40it/s]
Loading 0: 84%|████████▎ | 243/291 [01:03<00:10, 4.62it/s]
Loading 0: 84%|████████▍ | 244/291 [01:03<00:09, 5.21it/s]
Loading 0: 85%|████████▍ | 246/291 [01:03<00:10, 4.32it/s]
Loading 0: 85%|████████▍ | 247/291 [01:04<00:13, 3.25it/s]
Loading 0: 85%|████████▌ | 248/291 [01:05<00:16, 2.57it/s]
Loading 0: 86%|████████▋ | 251/291 [01:05<00:09, 4.41it/s]
Loading 0: 87%|████████▋ | 252/291 [01:05<00:08, 4.63it/s]
Loading 0: 87%|████████▋ | 253/291 [01:05<00:07, 5.24it/s]
Loading 0: 88%|████████▊ | 255/291 [01:06<00:08, 4.33it/s]
Loading 0: 88%|████████▊ | 256/291 [01:06<00:10, 3.26it/s]
Loading 0: 88%|████████▊ | 257/291 [01:07<00:13, 2.56it/s]
Loading 0: 89%|████████▉ | 260/291 [01:07<00:07, 4.40it/s]
Loading 0: 90%|████████▉ | 261/291 [01:07<00:06, 4.62it/s]
Loading 0: 90%|█████████ | 262/291 [01:07<00:05, 5.22it/s]
Loading 0: 91%|█████████ | 264/291 [01:08<00:06, 4.34it/s]
Loading 0: 91%|█████████ | 265/291 [01:09<00:07, 3.27it/s]
Loading 0: 91%|█████████▏| 266/291 [01:09<00:09, 2.59it/s]
Loading 0: 92%|█████████▏| 269/291 [01:09<00:04, 4.45it/s]
Loading 0: 93%|█████████▎| 270/291 [01:10<00:04, 4.68it/s]
Loading 0: 93%|█████████▎| 272/291 [01:10<00:02, 6.40it/s]
Loading 0: 94%|█████████▍| 274/291 [01:11<00:05, 3.33it/s]
Loading 0: 95%|█████████▍| 275/291 [01:11<00:05, 2.72it/s]
Loading 0: 96%|█████████▌| 278/291 [01:12<00:02, 4.35it/s]
Loading 0: 96%|█████████▌| 279/291 [01:12<00:02, 4.55it/s]
Loading 0: 96%|█████████▌| 280/291 [01:12<00:02, 5.10it/s]
Loading 0: 97%|█████████▋| 281/291 [01:13<00:02, 3.50it/s]
Loading 0: 97%|█████████▋| 282/291 [01:13<00:03, 2.64it/s]
Loading 0: 98%|█████████▊| 284/291 [01:13<00:01, 3.75it/s]
Loading 0: 98%|█████████▊| 285/291 [01:14<00:01, 4.09it/s]
Loading 0: 98%|█████████▊| 286/291 [01:14<00:01, 4.77it/s]
Loading 0: 99%|█████████▊| 287/291 [01:14<00:00, 4.93it/s]
Loading 0: 99%|█████████▉| 288/291 [01:14<00:00, 3.25it/s]
Job rirv938-llama-8b-mcl-500-9841-v1-mkmlizer completed after 144.61s with status: succeeded
Stopping job with name rirv938-llama-8b-mcl-500-9841-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.14s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-mcl-500-9841-v1
Waiting for inference service rirv938-llama-8b-mcl-500-9841-v1 to be ready
Inference service rirv938-llama-8b-mcl-500-9841-v1 ready after 150.72233152389526s
Pipeline stage MKMLDeployer completed in 151.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.533008575439453s
Received healthy response to inference request in 1.9708869457244873s
Received healthy response to inference request in 3.113619565963745s
Received healthy response to inference request in 1.0633573532104492s
Received healthy response to inference request in 2.458446979522705s
5 requests
0 failed requests
5th percentile: 1.2448632717132568
10th percentile: 1.4263691902160645
20th percentile: 1.7893810272216797
30th percentile: 2.068398952484131
40th percentile: 2.263422966003418
50th percentile: 2.458446979522705
60th percentile: 2.720516014099121
70th percentile: 2.982585048675537
80th percentile: 3.1974973678588867
90th percentile: 3.36525297164917
95th percentile: 3.4491307735443115
99th percentile: 3.5162330150604246
mean time: 2.427863883972168
Pipeline stage StressChecker completed in 13.65s
Shutdown handler de-registered
rirv938-llama-8b-mcl-500_9841_v1 status is now deployed due to DeploymentManager action
rirv938-llama-8b-mcl-500_9841_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-mcl-500_9841_v1 status is now torndown due to DeploymentManager action