Running pipeline stage MKMLizer
Starting job with name arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer
Waiting for job on arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer to finish
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ _____ __ __ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ /___/ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ Version: 0.6.11 ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ The license key for the current software has been verified as ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ belonging to: ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ Chai Research Corp. ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ║ ║
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
.gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 13.8MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
README.md: 0%| | 0.00/903 [00:00<?, ?B/s]
README.md: 100%|██████████| 903/903 [00:00<00:00, 14.2MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
config.json: 0%| | 0.00/698 [00:00<?, ?B/s]
config.json: 100%|██████████| 698/698 [00:00<00:00, 7.49MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
mergekit_config.yml: 0%| | 0.00/395 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 395/395 [00:00<00:00, 4.73MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00001-of-00009.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s]
model-00001-of-00009.safetensors: 1%| | 10.5M/1.98G [00:01<04:38, 7.08MB/s]
model-00001-of-00009.safetensors: 1%| | 21.0M/1.98G [00:02<03:16, 9.98MB/s]
model-00001-of-00009.safetensors: 2%|▏ | 41.9M/1.98G [00:02<01:23, 23.3MB/s]
model-00001-of-00009.safetensors: 7%|▋ | 147M/1.98G [00:02<00:15, 115MB/s]
model-00001-of-00009.safetensors: 14%|█▍ | 273M/1.98G [00:02<00:07, 240MB/s]
model-00001-of-00009.safetensors: 26%|██▌ | 514M/1.98G [00:02<00:02, 537MB/s]
model-00001-of-00009.safetensors: 34%|███▍ | 682M/1.98G [00:02<00:01, 714MB/s]
model-00001-of-00009.safetensors: 42%|████▏ | 839M/1.98G [00:02<00:01, 875MB/s]
model-00001-of-00009.safetensors: 55%|█████▌ | 1.09G/1.98G [00:03<00:00, 1.19GB/s]
model-00001-of-00009.safetensors: 64%|██████▎ | 1.26G/1.98G [00:03<00:01, 701MB/s]
model-00001-of-00009.safetensors: 74%|███████▎ | 1.46G/1.98G [00:03<00:00, 888MB/s]
model-00001-of-00009.safetensors: 81%|████████ | 1.60G/1.98G [00:04<00:00, 405MB/s]
model-00001-of-00009.safetensors: 88%|████████▊ | 1.74G/1.98G [00:04<00:00, 493MB/s]
model-00001-of-00009.safetensors: 94%|█████████▍| 1.86G/1.98G [00:04<00:00, 582MB/s]
model-00001-of-00009.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 412MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00002-of-00009.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s]
model-00002-of-00009.safetensors: 1%| | 10.5M/1.95G [00:01<04:54, 6.57MB/s]
model-00002-of-00009.safetensors: 1%| | 21.0M/1.95G [00:01<02:11, 14.6MB/s]
model-00002-of-00009.safetensors: 2%|▏ | 31.5M/1.95G [00:02<02:01, 15.8MB/s]
model-00002-of-00009.safetensors: 3%|▎ | 62.9M/1.95G [00:02<00:45, 41.3MB/s]
model-00002-of-00009.safetensors: 8%|▊ | 147M/1.95G [00:02<00:13, 129MB/s]
model-00002-of-00009.safetensors: 12%|█▏ | 241M/1.95G [00:02<00:07, 239MB/s]
model-00002-of-00009.safetensors: 25%|██▍ | 482M/1.95G [00:02<00:02, 583MB/s]
model-00002-of-00009.safetensors: 32%|███▏ | 619M/1.95G [00:02<00:01, 719MB/s]
model-00002-of-00009.safetensors: 38%|███▊ | 744M/1.95G [00:02<00:01, 812MB/s]
model-00002-of-00009.safetensors: 52%|█████▏ | 1.01G/1.95G [00:03<00:00, 1.21GB/s]
model-00002-of-00009.safetensors: 60%|██████ | 1.17G/1.95G [00:03<00:01, 696MB/s]
model-00002-of-00009.safetensors: 67%|██████▋ | 1.30G/1.95G [00:03<00:01, 585MB/s]
model-00002-of-00009.safetensors: 72%|███████▏ | 1.41G/1.95G [00:03<00:00, 626MB/s]
model-00002-of-00009.safetensors: 86%|████████▌ | 1.67G/1.95G [00:04<00:00, 931MB/s]
model-00002-of-00009.safetensors: 93%|█████████▎| 1.81G/1.95G [00:04<00:00, 994MB/s]
model-00002-of-00009.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 448MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00003-of-00009.safetensors: 0%| | 0.00/1.92G [00:00<?, ?B/s]
model-00003-of-00009.safetensors: 1%| | 10.5M/1.92G [00:01<04:17, 7.44MB/s]
model-00003-of-00009.safetensors: 1%| | 21.0M/1.92G [00:02<02:50, 11.2MB/s]
model-00003-of-00009.safetensors: 2%|▏ | 31.5M/1.92G [00:02<01:41, 18.7MB/s]
model-00003-of-00009.safetensors: 4%|▍ | 83.9M/1.92G [00:02<00:31, 58.8MB/s]
model-00003-of-00009.safetensors: 11%|█▏ | 220M/1.92G [00:02<00:08, 198MB/s]
model-00003-of-00009.safetensors: 14%|█▍ | 273M/1.92G [00:02<00:09, 183MB/s]
model-00003-of-00009.safetensors: 22%|██▏ | 430M/1.92G [00:02<00:04, 358MB/s]
model-00003-of-00009.safetensors: 35%|███▌ | 682M/1.92G [00:03<00:01, 684MB/s]
model-00003-of-00009.safetensors: 67%|██████▋ | 1.28G/1.92G [00:03<00:00, 1.36GB/s]
model-00003-of-00009.safetensors: 76%|███████▌ | 1.46G/1.92G [00:03<00:00, 820MB/s]
model-00003-of-00009.safetensors: 83%|████████▎ | 1.60G/1.92G [00:04<00:00, 700MB/s]
model-00003-of-00009.safetensors: 89%|████████▉ | 1.71G/1.92G [00:04<00:00, 748MB/s]
model-00003-of-00009.safetensors: 100%|█████████▉| 1.92G/1.92G [00:04<00:00, 438MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00004-of-00009.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s]
model-00004-of-00009.safetensors: 1%| | 10.5M/1.95G [00:01<03:50, 8.39MB/s]
model-00004-of-00009.safetensors: 1%| | 21.0M/1.95G [00:02<03:12, 9.98MB/s]
model-00004-of-00009.safetensors: 5%|▍ | 94.4M/1.95G [00:02<00:29, 62.7MB/s]
model-00004-of-00009.safetensors: 12%|█▏ | 231M/1.95G [00:02<00:09, 185MB/s]
model-00004-of-00009.safetensors: 17%|█▋ | 325M/1.95G [00:02<00:05, 274MB/s]
model-00004-of-00009.safetensors: 30%|██▉ | 577M/1.95G [00:02<00:02, 580MB/s]
model-00004-of-00009.safetensors: 36%|███▌ | 703M/1.95G [00:02<00:01, 659MB/s]
model-00004-of-00009.safetensors: 46%|████▌ | 891M/1.95G [00:02<00:01, 857MB/s]
model-00004-of-00009.safetensors: 57%|█████▋ | 1.10G/1.95G [00:02<00:00, 1.11GB/s]
model-00004-of-00009.safetensors: 65%|██████▍ | 1.26G/1.95G [00:03<00:01, 648MB/s]
model-00004-of-00009.safetensors: 71%|███████ | 1.38G/1.95G [00:03<00:00, 714MB/s]
model-00004-of-00009.safetensors: 77%|███████▋ | 1.50G/1.95G [00:03<00:00, 779MB/s]
model-00004-of-00009.safetensors: 87%|████████▋ | 1.69G/1.95G [00:03<00:00, 953MB/s]
model-00004-of-00009.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 495MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00005-of-00009.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s]
model-00005-of-00009.safetensors: 1%| | 10.5M/1.98G [00:01<03:50, 8.53MB/s]
model-00005-of-00009.safetensors: 1%| | 21.0M/1.98G [00:01<02:06, 15.5MB/s]
model-00005-of-00009.safetensors: 2%|▏ | 31.5M/1.98G [00:02<01:53, 17.1MB/s]
model-00005-of-00009.safetensors: 2%|▏ | 41.9M/1.98G [00:02<01:19, 24.3MB/s]
model-00005-of-00009.safetensors: 4%|▎ | 73.4M/1.98G [00:02<00:33, 56.4MB/s]
model-00005-of-00009.safetensors: 12%|█▏ | 231M/1.98G [00:02<00:06, 256MB/s]
model-00005-of-00009.safetensors: 15%|█▌ | 304M/1.98G [00:02<00:05, 326MB/s]
model-00005-of-00009.safetensors: 31%|███ | 619M/1.98G [00:02<00:01, 833MB/s]
model-00005-of-00009.safetensors: 38%|███▊ | 755M/1.98G [00:02<00:01, 801MB/s]
model-00005-of-00009.safetensors: 58%|█████▊ | 1.14G/1.98G [00:02<00:00, 1.40GB/s]
model-00005-of-00009.safetensors: 68%|██████▊ | 1.34G/1.98G [00:03<00:00, 957MB/s]
model-00005-of-00009.safetensors: 76%|███████▌ | 1.50G/1.98G [00:03<00:00, 887MB/s]
model-00005-of-00009.safetensors: 83%|████████▎ | 1.64G/1.98G [00:03<00:00, 707MB/s]
model-00005-of-00009.safetensors: 88%|████████▊ | 1.74G/1.98G [00:04<00:00, 707MB/s]
model-00005-of-00009.safetensors: 93%|█████████▎| 1.83G/1.98G [00:04<00:00, 666MB/s]
model-00005-of-00009.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 459MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00006-of-00009.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s]
model-00006-of-00009.safetensors: 1%| | 10.5M/1.95G [00:01<03:15, 9.91MB/s]
model-00006-of-00009.safetensors: 1%| | 21.0M/1.95G [00:02<03:03, 10.5MB/s]
model-00006-of-00009.safetensors: 2%|▏ | 31.5M/1.95G [00:02<01:47, 17.8MB/s]
model-00006-of-00009.safetensors: 9%|▊ | 168M/1.95G [00:02<00:11, 151MB/s]
model-00006-of-00009.safetensors: 16%|█▌ | 304M/1.95G [00:02<00:05, 301MB/s]
model-00006-of-00009.safetensors: 26%|██▌ | 503M/1.95G [00:02<00:02, 490MB/s]
model-00006-of-00009.safetensors: 31%|███ | 598M/1.95G [00:02<00:02, 506MB/s]
model-00006-of-00009.safetensors: 35%|███▌ | 682M/1.95G [00:02<00:02, 528MB/s]
model-00006-of-00009.safetensors: 44%|████▎ | 849M/1.95G [00:02<00:01, 740MB/s]
model-00006-of-00009.safetensors: 62%|██████▏ | 1.21G/1.95G [00:03<00:00, 1.28GB/s]
model-00006-of-00009.safetensors: 71%|███████ | 1.37G/1.95G [00:03<00:00, 825MB/s]
model-00006-of-00009.safetensors: 80%|███████▉ | 1.55G/1.95G [00:03<00:00, 977MB/s]
model-00006-of-00009.safetensors: 90%|█████████ | 1.76G/1.95G [00:03<00:00, 1.17GB/s]
model-00006-of-00009.safetensors: 99%|█████████▉| 1.93G/1.95G [00:03<00:00, 1.20GB/s]
model-00006-of-00009.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 507MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00007-of-00009.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s]
model-00007-of-00009.safetensors: 1%| | 10.5M/1.98G [00:02<07:48, 4.21MB/s]
model-00007-of-00009.safetensors: 6%|▌ | 115M/1.98G [00:02<00:30, 60.3MB/s]
model-00007-of-00009.safetensors: 9%|▉ | 178M/1.98G [00:02<00:18, 97.8MB/s]
model-00007-of-00009.safetensors: 12%|█▏ | 231M/1.98G [00:02<00:13, 130MB/s]
model-00007-of-00009.safetensors: 17%|█▋ | 336M/1.98G [00:03<00:07, 221MB/s]
model-00007-of-00009.safetensors: 31%|███ | 608M/1.98G [00:03<00:02, 544MB/s]
model-00007-of-00009.safetensors: 62%|██████▏ | 1.23G/1.98G [00:03<00:00, 1.40GB/s]
model-00007-of-00009.safetensors: 76%|███████▌ | 1.50G/1.98G [00:04<00:00, 670MB/s]
model-00007-of-00009.safetensors: 86%|████████▌ | 1.70G/1.98G [00:04<00:00, 782MB/s]
model-00007-of-00009.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 448MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model-00009-of-00009.safetensors: 0%| | 0.00/1.17G [00:00<?, ?B/s]
model-00009-of-00009.safetensors: 1%| | 10.5M/1.17G [00:01<02:42, 7.14MB/s]
model-00009-of-00009.safetensors: 2%|▏ | 21.0M/1.17G [00:01<01:39, 11.5MB/s]
model-00009-of-00009.safetensors: 3%|▎ | 31.5M/1.17G [00:02<00:59, 19.2MB/s]
model-00009-of-00009.safetensors: 11%|█ | 126M/1.17G [00:02<00:08, 116MB/s]
model-00009-of-00009.safetensors: 22%|██▏ | 252M/1.17G [00:02<00:03, 264MB/s]
model-00009-of-00009.safetensors: 40%|████ | 472M/1.17G [00:02<00:01, 523MB/s]
model-00009-of-00009.safetensors: 49%|████▉ | 570M/1.17G [00:02<00:01, 394MB/s]
model-00009-of-00009.safetensors: 55%|█████▌ | 644M/1.17G [00:02<00:01, 433MB/s]
model-00009-of-00009.safetensors: 61%|██████▏ | 717M/1.17G [00:03<00:00, 478MB/s]
model-00009-of-00009.safetensors: 74%|███████▍ | 864M/1.17G [00:03<00:00, 645MB/s]
model-00009-of-00009.safetensors: 100%|█████████▉| 1.17G/1.17G [00:03<00:00, 344MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
model.safetensors.index.json: 0%| | 0.00/22.8k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 22.8k/22.8k [00:00<00:00, 5.95MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
special_tokens_map.json: 0%| | 0.00/301 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 301/301 [00:00<00:00, 2.46MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
tokenizer.json: 0%| | 0.00/9.08M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 9.08M/9.08M [00:00<00:00, 24.2MB/s]
tokenizer.json: 100%|██████████| 9.08M/9.08M [00:00<00:00, 23.9MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
tokenizer_config.json: 0%| | 0.00/50.9k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 50.9k/50.9k [00:00<00:00, 285MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Downloaded to shared memory in 44.557s
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: quantizing model to /dev/shm/model_cache
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Reading /tmp/tmpfgp5cavl/model.safetensors.index.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
Profiling: 0%| | 0/291 [00:00<?, ?it/s]
Profiling: 0%| | 1/291 [00:00<00:38, 7.59it/s]
Profiling: 5%|▍ | 14/291 [00:00<00:04, 65.71it/s]
Profiling: 11%|█ | 31/291 [00:00<00:02, 103.54it/s]
Profiling: 14%|█▍ | 42/291 [00:00<00:03, 79.36it/s]
Profiling: 20%|██ | 59/291 [00:00<00:02, 102.47it/s]
Profiling: 26%|██▌ | 76/291 [00:00<00:01, 118.43it/s]
Profiling: 31%|███ | 89/291 [00:05<00:23, 8.74it/s]
Profiling: 34%|███▍ | 99/291 [00:05<00:17, 11.20it/s]
Profiling: 38%|███▊ | 111/291 [00:05<00:11, 15.27it/s]
Profiling: 44%|████▍ | 128/291 [00:05<00:07, 23.12it/s]
Profiling: 49%|████▉ | 142/291 [00:05<00:04, 29.91it/s]
Profiling: 53%|█████▎ | 154/291 [00:06<00:03, 37.35it/s]
Profiling: 59%|█████▉ | 171/291 [00:06<00:02, 51.57it/s]
Profiling: 63%|██████▎ | 184/291 [00:06<00:01, 53.62it/s]
Profiling: 69%|██████▉ | 201/291 [00:06<00:01, 68.90it/s]
Profiling: 75%|███████▍ | 217/291 [00:06<00:00, 83.93it/s]
Profiling: 79%|███████▉ | 231/291 [00:06<00:00, 77.23it/s]
Profiling: 84%|████████▍ | 245/291 [00:06<00:00, 87.91it/s]
Profiling: 89%|████████▉ | 260/291 [00:07<00:00, 87.45it/s]
Profiling: 94%|█████████▍| 274/291 [00:07<00:00, 96.92it/s]
Profiling: 99%|█████████▊| 287/291 [00:12<00:00, 8.48it/s]
Profiling: 100%|██████████| 291/291 [00:12<00:00, 23.33it/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: quantized model in 27.225s
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Processed model arcee-ai/Llama-3-8B-Instruct-Base-Slerp in 72.844s
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arcee-ai-llama-3-8b-inst-7156-v1/config.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arcee-ai-llama-3-8b-inst-7156-v1/special_tokens_map.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arcee-ai-llama-3-8b-inst-7156-v1/tokenizer_config.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arcee-ai-llama-3-8b-inst-7156-v1/tokenizer.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/arcee-ai-llama-3-8b-inst-7156-v1/mkml_model.tensors
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
arcee-ai-llama-3-8b-inst-7156-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.
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: warnings.warn(
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 8.69MB/s]
arcee-ai-llama-3-8b-inst-7156-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.
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: warnings.warn(
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.25MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 3.70MB/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 3.68MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 11.9MB/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 11.9MB/s]
arcee-ai-llama-3-8b-inst-7156-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.
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: warnings.warn(
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer:
pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<01:56, 12.3MB/s]
pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:57, 24.9MB/s]
pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:01<00:28, 48.5MB/s]
pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:01<00:30, 46.3MB/s]
pytorch_model.bin: 5%|▌ | 73.4M/1.44G [00:01<00:23, 58.5MB/s]
pytorch_model.bin: 7%|▋ | 105M/1.44G [00:01<00:13, 98.7MB/s]
pytorch_model.bin: 20%|██ | 294M/1.44G [00:01<00:02, 427MB/s]
pytorch_model.bin: 50%|█████ | 724M/1.44G [00:01<00:00, 1.22GB/s]
pytorch_model.bin: 78%|███████▊ | 1.12G/1.44G [00:02<00:00, 1.80GB/s]
pytorch_model.bin: 95%|█████████▍| 1.37G/1.44G [00:02<00:00, 1.93GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 646MB/s]
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Saving duration: 0.291s
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.728s
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: creating bucket guanaco-reward-models
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/special_tokens_map.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/config.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/tokenizer_config.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/merges.txt
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/vocab.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/tokenizer.json
arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/arcee-ai-llama-3-8b-inst-7156-v1_reward/reward.tensors
Job arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer completed after 113.01s with status: succeeded
Stopping job with name arcee-ai-llama-3-8b-inst-7156-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service arcee-ai-llama-3-8b-inst-7156-v1
Waiting for inference service arcee-ai-llama-3-8b-inst-7156-v1 to be ready
Inference service arcee-ai-llama-3-8b-inst-7156-v1 ready after 50.46587896347046s
Pipeline stage ISVCDeployer completed in 57.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2069141864776611s
Received healthy response to inference request in 0.8290004730224609s
Received healthy response to inference request in 0.832282304763794s
Received healthy response to inference request in 0.6690912246704102s
Received healthy response to inference request in 0.6522197723388672s
5 requests
0 failed requests
5th percentile: 0.6555940628051757
10th percentile: 0.6589683532714844
20th percentile: 0.6657169342041016
30th percentile: 0.7010730743408203
40th percentile: 0.7650367736816406
50th percentile: 0.8290004730224609
60th percentile: 0.8303132057189941
70th percentile: 0.8316259384155273
80th percentile: 0.9072086811065675
90th percentile: 1.0570614337921143
95th percentile: 1.1319878101348877
99th percentile: 1.1919289112091065
mean time: 0.8379015922546387
Pipeline stage StressChecker completed in 5.12s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
arcee-ai-llama-3-8b-inst_7156_v1 status is now deployed due to DeploymentManager action
arcee-ai-llama-3-8b-inst_7156_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of arcee-ai-llama-3-8b-inst_7156_v1
Running pipeline stage ISVCDeleter
Checking if service arcee-ai-llama-3-8b-inst-7156-v1 is running
Tearing down inference service arcee-ai-llama-3-8b-inst-7156-v1
Toredown service arcee-ai-llama-3-8b-inst-7156-v1
Pipeline stage ISVCDeleter completed in 4.15s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key arcee-ai-llama-3-8b-inst-7156-v1/config.json from bucket guanaco-mkml-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/config.json from bucket guanaco-reward-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key arcee-ai-llama-3-8b-inst-7156-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.90s
arcee-ai-llama-3-8b-inst_7156_v1 status is now torndown due to DeploymentManager action