Running pipeline stage MKMLizer
Starting job with name arlineka-nyans-11b-v1-mkmlizer
Waiting for job on arlineka-nyans-11b-v1-mkmlizer to finish
arlineka-nyans-11b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arlineka-nyans-11b-v1-mkmlizer: ║ _____ __ __ ║
arlineka-nyans-11b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
arlineka-nyans-11b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
arlineka-nyans-11b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
arlineka-nyans-11b-v1-mkmlizer: ║ /___/ ║
arlineka-nyans-11b-v1-mkmlizer: ║ ║
arlineka-nyans-11b-v1-mkmlizer: ║ Version: 0.6.11 ║
arlineka-nyans-11b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
arlineka-nyans-11b-v1-mkmlizer: ║ ║
arlineka-nyans-11b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
arlineka-nyans-11b-v1-mkmlizer: ║ belonging to: ║
arlineka-nyans-11b-v1-mkmlizer: ║ ║
arlineka-nyans-11b-v1-mkmlizer: ║ Chai Research Corp. ║
arlineka-nyans-11b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
arlineka-nyans-11b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
arlineka-nyans-11b-v1-mkmlizer: ║ ║
arlineka-nyans-11b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arlineka-nyans-11b-v1-mkmlizer:
.gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.9MB/s]
arlineka-nyans-11b-v1-mkmlizer:
.gitignore: 0%| | 0.00/19.0 [00:00<?, ?B/s]
.gitignore: 100%|██████████| 19.0/19.0 [00:00<00:00, 155kB/s]
arlineka-nyans-11b-v1-mkmlizer:
README.md: 0%| | 0.00/54.0 [00:00<?, ?B/s]
README.md: 100%|██████████| 54.0/54.0 [00:00<00:00, 448kB/s]
arlineka-nyans-11b-v1-mkmlizer:
config.json: 0%| | 0.00/759 [00:00<?, ?B/s]
config.json: 100%|██████████| 759/759 [00:00<00:00, 7.12MB/s]
arlineka-nyans-11b-v1-mkmlizer:
model-00001-of-00003.safetensors: 0%| | 0.00/9.91G [00:00<?, ?B/s]
model-00001-of-00003.safetensors: 0%| | 10.5M/9.91G [00:01<22:00, 7.50MB/s]
model-00001-of-00003.safetensors: 0%| | 21.0M/9.91G [00:02<16:28, 10.0MB/s]
model-00001-of-00003.safetensors: 0%| | 41.9M/9.91G [00:02<07:41, 21.4MB/s]
model-00001-of-00003.safetensors: 1%| | 52.4M/9.91G [00:02<05:53, 27.9MB/s]
model-00001-of-00003.safetensors: 1%| | 73.4M/9.91G [00:02<03:33, 46.1MB/s]
model-00001-of-00003.safetensors: 2%|▏ | 157M/9.91G [00:02<01:07, 144MB/s]
model-00001-of-00003.safetensors: 3%|▎ | 252M/9.91G [00:02<00:36, 265MB/s]
model-00001-of-00003.safetensors: 3%|▎ | 304M/9.91G [00:03<00:35, 270MB/s]
model-00001-of-00003.safetensors: 4%|▍ | 377M/9.91G [00:03<00:27, 349MB/s]
model-00001-of-00003.safetensors: 7%|▋ | 713M/9.91G [00:03<00:09, 958MB/s]
model-00001-of-00003.safetensors: 11%|█ | 1.11G/9.91G [00:03<00:05, 1.49GB/s]
model-00001-of-00003.safetensors: 13%|█▎ | 1.30G/9.91G [00:04<00:12, 680MB/s]
model-00001-of-00003.safetensors: 14%|█▍ | 1.44G/9.91G [00:04<00:16, 513MB/s]
model-00001-of-00003.safetensors: 16%|█▌ | 1.54G/9.91G [00:04<00:15, 554MB/s]
model-00001-of-00003.safetensors: 17%|█▋ | 1.69G/9.91G [00:04<00:12, 663MB/s]
model-00001-of-00003.safetensors: 18%|█▊ | 1.80G/9.91G [00:05<00:12, 651MB/s]
model-00001-of-00003.safetensors: 19%|█▉ | 1.91G/9.91G [00:05<00:11, 710MB/s]
model-00001-of-00003.safetensors: 24%|██▍ | 2.39G/9.91G [00:05<00:05, 1.47GB/s]
model-00001-of-00003.safetensors: 26%|██▌ | 2.60G/9.91G [00:05<00:09, 773MB/s]
model-00001-of-00003.safetensors: 28%|██▊ | 2.76G/9.91G [00:06<00:09, 753MB/s]
model-00001-of-00003.safetensors: 29%|██▉ | 2.89G/9.91G [00:06<00:12, 547MB/s]
model-00001-of-00003.safetensors: 30%|███ | 3.00G/9.91G [00:06<00:11, 602MB/s]
model-00001-of-00003.safetensors: 31%|███▏ | 3.10G/9.91G [00:06<00:10, 636MB/s]
model-00001-of-00003.safetensors: 33%|███▎ | 3.28G/9.91G [00:06<00:08, 816MB/s]
model-00001-of-00003.safetensors: 36%|███▌ | 3.55G/9.91G [00:07<00:05, 1.12GB/s]
model-00001-of-00003.safetensors: 37%|███▋ | 3.71G/9.91G [00:07<00:07, 849MB/s]
model-00001-of-00003.safetensors: 39%|███▊ | 3.84G/9.91G [00:07<00:08, 740MB/s]
model-00001-of-00003.safetensors: 40%|███▉ | 3.94G/9.91G [00:08<00:12, 469MB/s]
model-00001-of-00003.safetensors: 41%|████ | 4.03G/9.91G [00:08<00:13, 449MB/s]
model-00001-of-00003.safetensors: 42%|████▏ | 4.16G/9.91G [00:08<00:10, 542MB/s]
model-00001-of-00003.safetensors: 43%|████▎ | 4.25G/9.91G [00:08<00:11, 514MB/s]
model-00001-of-00003.safetensors: 44%|████▍ | 4.34G/9.91G [00:08<00:09, 574MB/s]
model-00001-of-00003.safetensors: 45%|████▍ | 4.46G/9.91G [00:08<00:08, 672MB/s]
model-00001-of-00003.safetensors: 46%|████▋ | 4.60G/9.91G [00:09<00:06, 767MB/s]
model-00001-of-00003.safetensors: 49%|████▉ | 4.88G/9.91G [00:09<00:04, 1.18GB/s]
model-00001-of-00003.safetensors: 51%|█████ | 5.02G/9.91G [00:09<00:04, 1.17GB/s]
model-00001-of-00003.safetensors: 52%|█████▏ | 5.16G/9.91G [00:09<00:04, 1.16GB/s]
model-00001-of-00003.safetensors: 53%|█████▎ | 5.30G/9.91G [00:09<00:04, 966MB/s]
model-00001-of-00003.safetensors: 55%|█████▍ | 5.43G/9.91G [00:09<00:04, 1.02GB/s]
model-00001-of-00003.safetensors: 56%|█████▌ | 5.55G/9.91G [00:10<00:06, 666MB/s]
model-00001-of-00003.safetensors: 57%|█████▋ | 5.64G/9.91G [00:10<00:06, 685MB/s]
model-00001-of-00003.safetensors: 58%|█████▊ | 5.74G/9.91G [00:10<00:06, 598MB/s]
model-00001-of-00003.safetensors: 59%|█████▉ | 5.87G/9.91G [00:10<00:05, 737MB/s]
model-00001-of-00003.safetensors: 61%|██████ | 6.04G/9.91G [00:10<00:04, 925MB/s]
model-00001-of-00003.safetensors: 62%|██████▏ | 6.16G/9.91G [00:10<00:03, 957MB/s]
model-00001-of-00003.safetensors: 63%|██████▎ | 6.27G/9.91G [00:10<00:04, 909MB/s]
model-00001-of-00003.safetensors: 64%|██████▍ | 6.38G/9.91G [00:11<00:03, 928MB/s]
model-00001-of-00003.safetensors: 65%|██████▌ | 6.48G/9.91G [00:11<00:03, 918MB/s]
model-00001-of-00003.safetensors: 66%|██████▋ | 6.59G/9.91G [00:11<00:04, 666MB/s]
model-00001-of-00003.safetensors: 67%|██████▋ | 6.67G/9.91G [00:11<00:04, 649MB/s]
model-00001-of-00003.safetensors: 68%|██████▊ | 6.75G/9.91G [00:11<00:05, 597MB/s]
model-00001-of-00003.safetensors: 69%|██████▉ | 6.83G/9.91G [00:11<00:05, 588MB/s]
model-00001-of-00003.safetensors: 70%|███████ | 6.95G/9.91G [00:11<00:04, 731MB/s]
model-00001-of-00003.safetensors: 72%|███████▏ | 7.09G/9.91G [00:12<00:03, 872MB/s]
model-00001-of-00003.safetensors: 73%|███████▎ | 7.25G/9.91G [00:12<00:02, 981MB/s]
model-00001-of-00003.safetensors: 74%|███████▍ | 7.35G/9.91G [00:12<00:02, 961MB/s]
model-00001-of-00003.safetensors: 75%|███████▌ | 7.46G/9.91G [00:12<00:02, 889MB/s]
model-00001-of-00003.safetensors: 76%|███████▌ | 7.55G/9.91G [00:12<00:02, 857MB/s]
model-00001-of-00003.safetensors: 77%|███████▋ | 7.64G/9.91G [00:12<00:03, 738MB/s]
model-00001-of-00003.safetensors: 78%|███████▊ | 7.73G/9.91G [00:13<00:04, 540MB/s]
model-00001-of-00003.safetensors: 79%|███████▊ | 7.80G/9.91G [00:13<00:05, 421MB/s]
model-00001-of-00003.safetensors: 80%|███████▉ | 7.89G/9.91G [00:13<00:04, 487MB/s]
model-00001-of-00003.safetensors: 81%|████████ | 8.02G/9.91G [00:13<00:03, 626MB/s]
model-00001-of-00003.safetensors: 83%|████████▎ | 8.19G/9.91G [00:13<00:02, 835MB/s]
model-00001-of-00003.safetensors: 84%|████████▎ | 8.29G/9.91G [00:13<00:01, 868MB/s]
model-00001-of-00003.safetensors: 86%|████████▌ | 8.50G/9.91G [00:13<00:01, 1.16GB/s]
model-00001-of-00003.safetensors: 87%|████████▋ | 8.64G/9.91G [00:13<00:01, 1.13GB/s]
model-00001-of-00003.safetensors: 89%|████████▉ | 8.82G/9.91G [00:14<00:00, 1.26GB/s]
model-00001-of-00003.safetensors: 90%|█████████ | 8.95G/9.91G [00:14<00:01, 740MB/s]
model-00001-of-00003.safetensors: 92%|█████████▏| 9.07G/9.91G [00:14<00:01, 693MB/s]
model-00001-of-00003.safetensors: 93%|█████████▎| 9.18G/9.91G [00:14<00:00, 747MB/s]
model-00001-of-00003.safetensors: 94%|█████████▍| 9.30G/9.91G [00:14<00:00, 845MB/s]
model-00001-of-00003.safetensors: 95%|█████████▌| 9.44G/9.91G [00:14<00:00, 938MB/s]
model-00001-of-00003.safetensors: 96%|█████████▋| 9.56G/9.91G [00:15<00:00, 951MB/s]
model-00001-of-00003.safetensors: 98%|█████████▊| 9.74G/9.91G [00:15<00:00, 1.18GB/s]
model-00001-of-00003.safetensors: 100%|█████████▉| 9.91G/9.91G [00:15<00:00, 649MB/s]
arlineka-nyans-11b-v1-mkmlizer:
model-00002-of-00003.safetensors: 0%| | 0.00/9.96G [00:00<?, ?B/s]
model-00002-of-00003.safetensors: 0%| | 10.5M/9.96G [00:01<20:43, 8.00MB/s]
model-00002-of-00003.safetensors: 0%| | 21.0M/9.96G [00:01<12:50, 12.9MB/s]
model-00002-of-00003.safetensors: 0%| | 41.9M/9.96G [00:02<06:50, 24.1MB/s]
model-00002-of-00003.safetensors: 1%| | 62.9M/9.96G [00:02<04:37, 35.6MB/s]
model-00002-of-00003.safetensors: 1%| | 73.4M/9.96G [00:02<04:06, 40.1MB/s]
model-00002-of-00003.safetensors: 1%| | 105M/9.96G [00:02<02:20, 70.0MB/s]
model-00002-of-00003.safetensors: 2%|▏ | 189M/9.96G [00:02<00:55, 174MB/s]
model-00002-of-00003.safetensors: 2%|▏ | 241M/9.96G [00:03<00:45, 214MB/s]
model-00002-of-00003.safetensors: 3%|▎ | 283M/9.96G [00:03<00:38, 250MB/s]
model-00002-of-00003.safetensors: 4%|▍ | 388M/9.96G [00:03<00:24, 393MB/s]
model-00002-of-00003.safetensors: 10%|█ | 1.04G/9.96G [00:03<00:05, 1.69GB/s]
model-00002-of-00003.safetensors: 13%|█▎ | 1.27G/9.96G [00:04<00:11, 775MB/s]
model-00002-of-00003.safetensors: 14%|█▍ | 1.44G/9.96G [00:04<00:14, 583MB/s]
model-00002-of-00003.safetensors: 16%|█▌ | 1.61G/9.96G [00:04<00:12, 682MB/s]
model-00002-of-00003.safetensors: 18%|█▊ | 1.75G/9.96G [00:04<00:11, 689MB/s]
model-00002-of-00003.safetensors: 19%|█▊ | 1.87G/9.96G [00:05<00:11, 699MB/s]
model-00002-of-00003.safetensors: 20%|█▉ | 1.98G/9.96G [00:05<00:10, 750MB/s]
model-00002-of-00003.safetensors: 21%|██ | 2.09G/9.96G [00:05<00:13, 563MB/s]
model-00002-of-00003.safetensors: 22%|██▏ | 2.19G/9.96G [00:05<00:12, 636MB/s]
model-00002-of-00003.safetensors: 24%|██▍ | 2.43G/9.96G [00:05<00:08, 929MB/s]
model-00002-of-00003.safetensors: 28%|██▊ | 2.80G/9.96G [00:05<00:04, 1.46GB/s]
model-00002-of-00003.safetensors: 32%|███▏ | 3.16G/9.96G [00:06<00:04, 1.68GB/s]
model-00002-of-00003.safetensors: 34%|███▍ | 3.37G/9.96G [00:07<00:11, 584MB/s]
model-00002-of-00003.safetensors: 35%|███▌ | 3.51G/9.96G [00:07<00:10, 621MB/s]
model-00002-of-00003.safetensors: 37%|███▋ | 3.65G/9.96G [00:07<00:09, 673MB/s]
model-00002-of-00003.safetensors: 38%|███▊ | 3.79G/9.96G [00:07<00:08, 762MB/s]
model-00002-of-00003.safetensors: 43%|████▎ | 4.28G/9.96G [00:07<00:04, 1.41GB/s]
model-00002-of-00003.safetensors: 45%|████▌ | 4.52G/9.96G [00:07<00:05, 1.04GB/s]
model-00002-of-00003.safetensors: 47%|████▋ | 4.71G/9.96G [00:08<00:07, 710MB/s]
model-00002-of-00003.safetensors: 49%|████▉ | 4.85G/9.96G [00:08<00:07, 672MB/s]
model-00002-of-00003.safetensors: 50%|████▉ | 4.97G/9.96G [00:08<00:07, 708MB/s]
model-00002-of-00003.safetensors: 51%|█████ | 5.10G/9.96G [00:08<00:06, 777MB/s]
model-00002-of-00003.safetensors: 55%|█████▍ | 5.47G/9.96G [00:09<00:03, 1.28GB/s]
model-00002-of-00003.safetensors: 57%|█████▋ | 5.67G/9.96G [00:09<00:04, 947MB/s]
model-00002-of-00003.safetensors: 59%|█████▊ | 5.83G/9.96G [00:09<00:06, 683MB/s]
model-00002-of-00003.safetensors: 60%|█████▉ | 5.95G/9.96G [00:10<00:05, 712MB/s]
model-00002-of-00003.safetensors: 61%|██████ | 6.06G/9.96G [00:10<00:05, 744MB/s]
model-00002-of-00003.safetensors: 62%|██████▏ | 6.17G/9.96G [00:10<00:04, 762MB/s]
model-00002-of-00003.safetensors: 64%|██████▎ | 6.34G/9.96G [00:10<00:03, 941MB/s]
model-00002-of-00003.safetensors: 65%|██████▍ | 6.47G/9.96G [00:10<00:03, 980MB/s]
model-00002-of-00003.safetensors: 68%|██████▊ | 6.74G/9.96G [00:10<00:02, 1.37GB/s]
model-00002-of-00003.safetensors: 69%|██████▉ | 6.91G/9.96G [00:11<00:04, 733MB/s]
model-00002-of-00003.safetensors: 71%|███████ | 7.04G/9.96G [00:11<00:04, 693MB/s]
model-00002-of-00003.safetensors: 72%|███████▏ | 7.14G/9.96G [00:11<00:04, 671MB/s]
model-00002-of-00003.safetensors: 73%|███████▎ | 7.24G/9.96G [00:11<00:03, 691MB/s]
model-00002-of-00003.safetensors: 74%|███████▍ | 7.37G/9.96G [00:11<00:03, 801MB/s]
model-00002-of-00003.safetensors: 75%|███████▌ | 7.48G/9.96G [00:11<00:03, 778MB/s]
model-00002-of-00003.safetensors: 76%|███████▋ | 7.61G/9.96G [00:11<00:02, 897MB/s]
model-00002-of-00003.safetensors: 78%|███████▊ | 7.77G/9.96G [00:12<00:02, 1.05GB/s]
model-00002-of-00003.safetensors: 80%|███████▉ | 7.93G/9.96G [00:12<00:01, 1.13GB/s]
model-00002-of-00003.safetensors: 81%|████████ | 8.05G/9.96G [00:12<00:02, 798MB/s]
model-00002-of-00003.safetensors: 82%|████████▏ | 8.16G/9.96G [00:12<00:02, 762MB/s]
model-00002-of-00003.safetensors: 83%|████████▎ | 8.25G/9.96G [00:12<00:02, 720MB/s]
model-00002-of-00003.safetensors: 84%|████████▍ | 8.35G/9.96G [00:12<00:02, 736MB/s]
model-00002-of-00003.safetensors: 85%|████████▍ | 8.46G/9.96G [00:13<00:01, 809MB/s]
model-00002-of-00003.safetensors: 86%|████████▌ | 8.57G/9.96G [00:13<00:01, 865MB/s]
model-00002-of-00003.safetensors: 87%|████████▋ | 8.66G/9.96G [00:13<00:01, 804MB/s]
model-00002-of-00003.safetensors: 88%|████████▊ | 8.81G/9.96G [00:13<00:01, 956MB/s]
model-00002-of-00003.safetensors: 90%|█████████ | 8.97G/9.96G [00:13<00:00, 1.09GB/s]
model-00002-of-00003.safetensors: 91%|█████████ | 9.08G/9.96G [00:13<00:00, 1.05GB/s]
model-00002-of-00003.safetensors: 92%|█████████▏| 9.20G/9.96G [00:13<00:00, 921MB/s]
model-00002-of-00003.safetensors: 93%|█████████▎| 9.30G/9.96G [00:13<00:00, 849MB/s]
model-00002-of-00003.safetensors: 95%|█████████▌| 9.47G/9.96G [00:14<00:00, 1.04GB/s]
model-00002-of-00003.safetensors: 96%|█████████▋| 9.58G/9.96G [00:14<00:00, 1.04GB/s]
model-00002-of-00003.safetensors: 97%|█████████▋| 9.69G/9.96G [00:14<00:00, 1.05GB/s]
model-00002-of-00003.safetensors: 100%|█████████▉| 9.96G/9.96G [00:14<00:00, 694MB/s]
arlineka-nyans-11b-v1-mkmlizer:
model-00003-of-00003.safetensors: 0%| | 0.00/1.09G [00:00<?, ?B/s]
model-00003-of-00003.safetensors: 1%| | 10.5M/1.09G [00:01<01:55, 9.35MB/s]
model-00003-of-00003.safetensors: 2%|▏ | 21.0M/1.09G [00:02<02:04, 8.58MB/s]
model-00003-of-00003.safetensors: 3%|▎ | 31.5M/1.09G [00:02<01:16, 13.9MB/s]
model-00003-of-00003.safetensors: 7%|▋ | 73.4M/1.09G [00:02<00:23, 42.4MB/s]
model-00003-of-00003.safetensors: 10%|▉ | 105M/1.09G [00:02<00:14, 66.2MB/s]
model-00003-of-00003.safetensors: 16%|█▋ | 178M/1.09G [00:03<00:06, 142MB/s]
model-00003-of-00003.safetensors: 26%|██▌ | 283M/1.09G [00:03<00:02, 269MB/s]
model-00003-of-00003.safetensors: 32%|███▏ | 346M/1.09G [00:03<00:02, 327MB/s]
model-00003-of-00003.safetensors: 38%|███▊ | 409M/1.09G [00:03<00:02, 278MB/s]
model-00003-of-00003.safetensors: 100%|█████████▉| 1.09G/1.09G [00:03<00:00, 287MB/s]
arlineka-nyans-11b-v1-mkmlizer:
model.safetensors.index.json: 0%| | 0.00/25.1k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 25.1k/25.1k [00:00<00:00, 134MB/s]
arlineka-nyans-11b-v1-mkmlizer:
special_tokens_map.json: 0%| | 0.00/411 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 411/411 [00:00<00:00, 4.62MB/s]
arlineka-nyans-11b-v1-mkmlizer:
tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 19.1MB/s]
arlineka-nyans-11b-v1-mkmlizer:
tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 65.9MB/s]
arlineka-nyans-11b-v1-mkmlizer:
tokenizer_config.json: 0%| | 0.00/869 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 869/869 [00:00<00:00, 8.01MB/s]
arlineka-nyans-11b-v1-mkmlizer: Downloaded to shared memory in 42.041s
arlineka-nyans-11b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
arlineka-nyans-11b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
arlineka-nyans-11b-v1-mkmlizer: Reading /tmp/tmpqb766q9_/model.safetensors.index.json
arlineka-nyans-11b-v1-mkmlizer:
Profiling: 0%| | 0/291 [00:00<?, ?it/s]
Profiling: 0%| | 1/291 [00:01<07:38, 1.58s/it]
Profiling: 3%|▎ | 9/291 [00:01<00:39, 7.21it/s]
Profiling: 6%|▌ | 18/291 [00:01<00:17, 15.94it/s]
Profiling: 10%|▉ | 28/291 [00:01<00:09, 26.89it/s]
Profiling: 13%|█▎ | 38/291 [00:02<00:06, 37.32it/s]
Profiling: 16%|█▋ | 48/291 [00:02<00:05, 48.39it/s]
Profiling: 20%|█▉ | 57/291 [00:02<00:04, 56.73it/s]
Profiling: 23%|██▎ | 67/291 [00:02<00:03, 66.11it/s]
Profiling: 26%|██▋ | 77/291 [00:02<00:02, 71.69it/s]
Profiling: 30%|██▉ | 87/291 [00:02<00:02, 76.23it/s]
Profiling: 33%|███▎ | 96/291 [00:02<00:02, 78.22it/s]
Profiling: 36%|███▌ | 105/291 [00:02<00:02, 78.78it/s]
Profiling: 39%|███▉ | 114/291 [00:02<00:02, 80.27it/s]
Profiling: 42%|████▏ | 123/291 [00:02<00:02, 82.81it/s]
Profiling: 45%|████▌ | 132/291 [00:03<00:01, 83.20it/s]
Profiling: 48%|████▊ | 141/291 [00:03<00:04, 34.57it/s]
Profiling: 51%|█████ | 149/291 [00:03<00:03, 40.56it/s]
Profiling: 55%|█████▍ | 159/291 [00:03<00:02, 50.35it/s]
Profiling: 58%|█████▊ | 169/291 [00:04<00:02, 59.39it/s]
Profiling: 62%|██████▏ | 179/291 [00:04<00:01, 67.30it/s]
Profiling: 65%|██████▍ | 189/291 [00:04<00:01, 73.66it/s]
Profiling: 68%|██████▊ | 198/291 [00:04<00:01, 76.94it/s]
Profiling: 71%|███████▏ | 208/291 [00:04<00:01, 81.80it/s]
Profiling: 75%|███████▌ | 219/291 [00:04<00:00, 83.69it/s]
Profiling: 78%|███████▊ | 228/291 [00:04<00:00, 81.54it/s]
Profiling: 81%|████████▏ | 237/291 [00:04<00:00, 81.19it/s]
Profiling: 85%|████████▍ | 246/291 [00:04<00:00, 81.02it/s]
Profiling: 88%|████████▊ | 256/291 [00:04<00:00, 86.01it/s]
Profiling: 91%|█████████ | 265/291 [00:05<00:00, 84.38it/s]
Profiling: 94%|█████████▍| 274/291 [00:05<00:00, 81.35it/s]
Profiling: 97%|█████████▋| 283/291 [00:07<00:00, 11.47it/s]
Profiling: 100%|██████████| 291/291 [00:07<00:00, 37.54it/s]
arlineka-nyans-11b-v1-mkmlizer: quantized model in 23.436s
arlineka-nyans-11b-v1-mkmlizer: Processed model arlineka/Nyans-11b in 67.208s
arlineka-nyans-11b-v1-mkmlizer: creating bucket guanaco-mkml-models
arlineka-nyans-11b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arlineka-nyans-11b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arlineka-nyans-11b-v1
arlineka-nyans-11b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arlineka-nyans-11b-v1/config.json
arlineka-nyans-11b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arlineka-nyans-11b-v1/special_tokens_map.json
arlineka-nyans-11b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arlineka-nyans-11b-v1/tokenizer_config.json
arlineka-nyans-11b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/arlineka-nyans-11b-v1/tokenizer.model
arlineka-nyans-11b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arlineka-nyans-11b-v1/tokenizer.json
arlineka-nyans-11b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/arlineka-nyans-11b-v1/mkml_model.tensors
arlineka-nyans-11b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
arlineka-nyans-11b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
arlineka-nyans-11b-v1-mkmlizer: warnings.warn(
arlineka-nyans-11b-v1-mkmlizer:
config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.3MB/s]
arlineka-nyans-11b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
arlineka-nyans-11b-v1-mkmlizer: warnings.warn(
arlineka-nyans-11b-v1-mkmlizer:
tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.49MB/s]
arlineka-nyans-11b-v1-mkmlizer:
vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 27.9MB/s]
arlineka-nyans-11b-v1-mkmlizer:
tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 27.6MB/s]
arlineka-nyans-11b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
arlineka-nyans-11b-v1-mkmlizer: warnings.warn(
arlineka-nyans-11b-v1-mkmlizer:
pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:18, 76.4MB/s]
pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:10, 137MB/s]
pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:16, 84.0MB/s]
pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:08, 155MB/s]
pytorch_model.bin: 18%|█▊ | 262M/1.44G [00:00<00:02, 443MB/s]
pytorch_model.bin: 28%|██▊ | 409M/1.44G [00:00<00:01, 677MB/s]
pytorch_model.bin: 35%|███▍ | 503M/1.44G [00:01<00:01, 726MB/s]
pytorch_model.bin: 49%|████▊ | 703M/1.44G [00:01<00:00, 1.03GB/s]
pytorch_model.bin: 59%|█████▉ | 849M/1.44G [00:01<00:00, 1.14GB/s]
pytorch_model.bin: 68%|██████▊ | 983M/1.44G [00:01<00:00, 1.07GB/s]
pytorch_model.bin: 80%|███████▉ | 1.15G/1.44G [00:01<00:00, 1.22GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.21GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 777MB/s]
arlineka-nyans-11b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
arlineka-nyans-11b-v1-mkmlizer: Saving duration: 0.279s
arlineka-nyans-11b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.094s
arlineka-nyans-11b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/arlineka-nyans-11b-v1_reward/reward.tensors
Job arlineka-nyans-11b-v1-mkmlizer completed after 95.12s with status: succeeded
Stopping job with name arlineka-nyans-11b-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service arlineka-nyans-11b-v1
Waiting for inference service arlineka-nyans-11b-v1 to be ready
Inference service arlineka-nyans-11b-v1 ready after 40.44971489906311s
Pipeline stage ISVCDeployer completed in 47.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0119245052337646s
Received healthy response to inference request in 1.4675617218017578s
Received healthy response to inference request in 1.4887585639953613s
Received healthy response to inference request in 1.4564898014068604s
Received healthy response to inference request in 1.4899532794952393s
5 requests
0 failed requests
5th percentile: 1.4587041854858398
10th percentile: 1.4609185695648192
20th percentile: 1.4653473377227784
30th percentile: 1.4718010902404786
40th percentile: 1.4802798271179198
50th percentile: 1.4887585639953613
60th percentile: 1.4892364501953126
70th percentile: 1.4897143363952636
80th percentile: 1.5943475246429444
90th percentile: 1.8031360149383546
95th percentile: 1.9075302600860595
99th percentile: 1.9910456562042236
mean time: 1.5829375743865968
Pipeline stage StressChecker completed in 8.67s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
arlineka-nyans-11b_v1 status is now deployed due to DeploymentManager action
arlineka-nyans-11b_v1 status is now rejected due to ELO is less than acceptable minimum 6.5