Running pipeline stage MKMLizer
Starting job with name thedrummer-moistral-11b-v1-v1-mkmlizer
Waiting for job on thedrummer-moistral-11b-v1-v1-mkmlizer to finish
thedrummer-moistral-11b-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ _____ __ __ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ /___/ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ Version: 0.6.11 ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ belonging to: ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ Chai Research Corp. ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ║ ║
thedrummer-moistral-11b-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thedrummer-moistral-11b-v1-v1-mkmlizer:
.gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.0MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
LICENSE: 0.00B [00:00, ?B/s]
LICENSE: 0.00B [00:00, ?B/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
README.md: 0%| | 0.00/4.18k [00:00<?, ?B/s]
README.md: 100%|██████████| 4.18k/4.18k [00:00<00:00, 29.7MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
config.json: 0%| | 0.00/685 [00:00<?, ?B/s]
config.json: 100%|██████████| 685/685 [00:00<00:00, 11.0MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
generation_config.json: 0%| | 0.00/154 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 154/154 [00:00<00:00, 1.46MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
pytorch_model-00001-of-00005.bin: 0%| | 0.00/4.94G [00:00<?, ?B/s]
pytorch_model-00001-of-00005.bin: 0%| | 10.5M/4.94G [00:00<03:39, 22.5MB/s]
pytorch_model-00001-of-00005.bin: 2%|▏ | 105M/4.94G [00:00<00:21, 220MB/s]
pytorch_model-00001-of-00005.bin: 7%|▋ | 357M/4.94G [00:00<00:07, 611MB/s]
pytorch_model-00001-of-00005.bin: 9%|▉ | 440M/4.94G [00:01<00:10, 429MB/s]
pytorch_model-00001-of-00005.bin: 10%|█ | 503M/4.94G [00:02<00:32, 135MB/s]
pytorch_model-00001-of-00005.bin: 11%|█ | 545M/4.94G [00:03<00:33, 131MB/s]
pytorch_model-00001-of-00005.bin: 14%|█▍ | 703M/4.94G [00:03<00:18, 233MB/s]
pytorch_model-00001-of-00005.bin: 15%|█▌ | 765M/4.94G [00:03<00:15, 266MB/s]
pytorch_model-00001-of-00005.bin: 20%|██ | 1.01G/4.94G [00:03<00:07, 511MB/s]
pytorch_model-00001-of-00005.bin: 25%|██▌ | 1.25G/4.94G [00:03<00:04, 769MB/s]
pytorch_model-00001-of-00005.bin: 31%|███ | 1.52G/4.94G [00:03<00:03, 1.09GB/s]
pytorch_model-00001-of-00005.bin: 37%|███▋ | 1.82G/4.94G [00:03<00:02, 1.45GB/s]
pytorch_model-00001-of-00005.bin: 42%|████▏ | 2.10G/4.94G [00:03<00:01, 1.72GB/s]
pytorch_model-00001-of-00005.bin: 48%|████▊ | 2.39G/4.94G [00:03<00:01, 1.98GB/s]
pytorch_model-00001-of-00005.bin: 53%|█████▎ | 2.64G/4.94G [00:04<00:01, 1.95GB/s]
pytorch_model-00001-of-00005.bin: 58%|█████▊ | 2.87G/4.94G [00:04<00:01, 1.98GB/s]
pytorch_model-00001-of-00005.bin: 63%|██████▎ | 3.10G/4.94G [00:04<00:00, 1.88GB/s]
pytorch_model-00001-of-00005.bin: 67%|██████▋ | 3.31G/4.94G [00:04<00:00, 1.83GB/s]
pytorch_model-00001-of-00005.bin: 73%|███████▎ | 3.63G/4.94G [00:04<00:00, 2.08GB/s]
pytorch_model-00001-of-00005.bin: 78%|███████▊ | 3.85G/4.94G [00:04<00:00, 1.57GB/s]
pytorch_model-00001-of-00005.bin: 84%|████████▎ | 4.13G/4.94G [00:04<00:00, 1.80GB/s]
pytorch_model-00001-of-00005.bin: 88%|████████▊ | 4.35G/4.94G [00:05<00:00, 1.72GB/s]
pytorch_model-00001-of-00005.bin: 96%|█████████▌| 4.75G/4.94G [00:05<00:00, 2.24GB/s]
pytorch_model-00001-of-00005.bin: 100%|█████████▉| 4.94G/4.94G [00:05<00:00, 947MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
pytorch_model-00002-of-00005.bin: 0%| | 0.00/5.00G [00:00<?, ?B/s]
pytorch_model-00002-of-00005.bin: 0%| | 10.5M/5.00G [00:00<04:09, 20.0MB/s]
pytorch_model-00002-of-00005.bin: 0%| | 21.0M/5.00G [00:00<02:16, 36.4MB/s]
pytorch_model-00002-of-00005.bin: 10%|█ | 503M/5.00G [00:00<00:04, 990MB/s]
pytorch_model-00002-of-00005.bin: 13%|█▎ | 650M/5.00G [00:01<00:06, 691MB/s]
pytorch_model-00002-of-00005.bin: 20%|██ | 1.02G/5.00G [00:01<00:03, 1.13GB/s]
pytorch_model-00002-of-00005.bin: 24%|██▎ | 1.18G/5.00G [00:01<00:06, 623MB/s]
pytorch_model-00002-of-00005.bin: 26%|██▌ | 1.31G/5.00G [00:02<00:06, 555MB/s]
pytorch_model-00002-of-00005.bin: 30%|███ | 1.51G/5.00G [00:02<00:04, 723MB/s]
pytorch_model-00002-of-00005.bin: 35%|███▍ | 1.74G/5.00G [00:02<00:03, 947MB/s]
pytorch_model-00002-of-00005.bin: 45%|████▍ | 2.24G/5.00G [00:02<00:01, 1.63GB/s]
pytorch_model-00002-of-00005.bin: 51%|█████ | 2.56G/5.00G [00:02<00:01, 1.91GB/s]
pytorch_model-00002-of-00005.bin: 57%|█████▋ | 2.83G/5.00G [00:02<00:01, 1.99GB/s]
pytorch_model-00002-of-00005.bin: 62%|██████▏ | 3.09G/5.00G [00:03<00:01, 1.43GB/s]
pytorch_model-00002-of-00005.bin: 66%|██████▌ | 3.30G/5.00G [00:03<00:01, 1.18GB/s]
pytorch_model-00002-of-00005.bin: 72%|███████▏ | 3.60G/5.00G [00:03<00:00, 1.45GB/s]
pytorch_model-00002-of-00005.bin: 76%|███████▌ | 3.80G/5.00G [00:03<00:00, 1.37GB/s]
pytorch_model-00002-of-00005.bin: 79%|███████▉ | 3.97G/5.00G [00:03<00:00, 1.41GB/s]
pytorch_model-00002-of-00005.bin: 83%|████████▎ | 4.14G/5.00G [00:03<00:00, 1.35GB/s]
pytorch_model-00002-of-00005.bin: 86%|████████▌ | 4.30G/5.00G [00:04<00:00, 1.12GB/s]
pytorch_model-00002-of-00005.bin: 89%|████████▊ | 4.43G/5.00G [00:04<00:00, 814MB/s]
pytorch_model-00002-of-00005.bin: 91%|█████████ | 4.55G/5.00G [00:04<00:00, 864MB/s]
pytorch_model-00002-of-00005.bin: 95%|█████████▍| 4.74G/5.00G [00:04<00:00, 1.05GB/s]
pytorch_model-00002-of-00005.bin: 97%|█████████▋| 4.87G/5.00G [00:04<00:00, 832MB/s]
pytorch_model-00002-of-00005.bin: 100%|█████████▉| 5.00G/5.00G [00:04<00:00, 1.01GB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
pytorch_model-00003-of-00005.bin: 0%| | 0.00/4.92G [00:00<?, ?B/s]
pytorch_model-00003-of-00005.bin: 0%| | 10.5M/4.92G [00:00<04:03, 20.1MB/s]
pytorch_model-00003-of-00005.bin: 3%|▎ | 157M/4.92G [00:00<00:16, 297MB/s]
pytorch_model-00003-of-00005.bin: 9%|▉ | 440M/4.92G [00:00<00:06, 728MB/s]
pytorch_model-00003-of-00005.bin: 11%|█▏ | 556M/4.92G [00:01<00:13, 314MB/s]
pytorch_model-00003-of-00005.bin: 13%|█▎ | 629M/4.92G [00:01<00:13, 309MB/s]
pytorch_model-00003-of-00005.bin: 14%|█▍ | 692M/4.92G [00:02<00:13, 323MB/s]
pytorch_model-00003-of-00005.bin: 15%|█▌ | 744M/4.92G [00:02<00:12, 321MB/s]
pytorch_model-00003-of-00005.bin: 16%|█▌ | 797M/4.92G [00:02<00:13, 316MB/s]
pytorch_model-00003-of-00005.bin: 18%|█▊ | 891M/4.92G [00:02<00:11, 354MB/s]
pytorch_model-00003-of-00005.bin: 19%|█▉ | 933M/4.92G [00:02<00:12, 323MB/s]
pytorch_model-00003-of-00005.bin: 25%|██▍ | 1.22G/4.92G [00:02<00:04, 748MB/s]
pytorch_model-00003-of-00005.bin: 31%|███▏ | 1.54G/4.92G [00:03<00:02, 1.22GB/s]
pytorch_model-00003-of-00005.bin: 35%|███▍ | 1.71G/4.92G [00:03<00:02, 1.28GB/s]
pytorch_model-00003-of-00005.bin: 42%|████▏ | 2.08G/4.92G [00:03<00:01, 1.83GB/s]
pytorch_model-00003-of-00005.bin: 48%|████▊ | 2.36G/4.92G [00:03<00:01, 2.03GB/s]
pytorch_model-00003-of-00005.bin: 53%|█████▎ | 2.60G/4.92G [00:03<00:01, 2.09GB/s]
pytorch_model-00003-of-00005.bin: 59%|█████▉ | 2.89G/4.92G [00:03<00:00, 2.29GB/s]
pytorch_model-00003-of-00005.bin: 64%|██████▍ | 3.15G/4.92G [00:03<00:00, 1.83GB/s]
pytorch_model-00003-of-00005.bin: 68%|██████▊ | 3.37G/4.92G [00:03<00:00, 1.74GB/s]
pytorch_model-00003-of-00005.bin: 73%|███████▎ | 3.59G/4.92G [00:04<00:00, 1.85GB/s]
pytorch_model-00003-of-00005.bin: 77%|███████▋ | 3.80G/4.92G [00:04<00:00, 1.73GB/s]
pytorch_model-00003-of-00005.bin: 81%|████████ | 3.98G/4.92G [00:04<00:00, 1.71GB/s]
pytorch_model-00003-of-00005.bin: 87%|████████▋ | 4.29G/4.92G [00:04<00:00, 2.03GB/s]
pytorch_model-00003-of-00005.bin: 92%|█████████▏| 4.51G/4.92G [00:04<00:00, 1.90GB/s]
pytorch_model-00003-of-00005.bin: 96%|█████████▌| 4.71G/4.92G [00:04<00:00, 1.76GB/s]
pytorch_model-00003-of-00005.bin: 100%|█████████▉| 4.89G/4.92G [00:04<00:00, 1.64GB/s]
pytorch_model-00003-of-00005.bin: 100%|█████████▉| 4.92G/4.92G [00:04<00:00, 1.01GB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
pytorch_model-00004-of-00005.bin: 0%| | 0.00/4.92G [00:00<?, ?B/s]
pytorch_model-00004-of-00005.bin: 0%| | 10.5M/4.92G [00:00<02:51, 28.7MB/s]
pytorch_model-00004-of-00005.bin: 3%|▎ | 147M/4.92G [00:00<00:12, 393MB/s]
pytorch_model-00004-of-00005.bin: 8%|▊ | 377M/4.92G [00:00<00:04, 921MB/s]
pytorch_model-00004-of-00005.bin: 11%|█ | 535M/4.92G [00:00<00:04, 1.09GB/s]
pytorch_model-00004-of-00005.bin: 15%|█▍ | 724M/4.92G [00:00<00:03, 1.27GB/s]
pytorch_model-00004-of-00005.bin: 20%|██ | 996M/4.92G [00:00<00:02, 1.66GB/s]
pytorch_model-00004-of-00005.bin: 24%|██▍ | 1.20G/4.92G [00:02<00:09, 397MB/s]
pytorch_model-00004-of-00005.bin: 28%|██▊ | 1.38G/4.92G [00:02<00:07, 496MB/s]
pytorch_model-00004-of-00005.bin: 31%|███ | 1.52G/4.92G [00:02<00:07, 469MB/s]
pytorch_model-00004-of-00005.bin: 33%|███▎ | 1.65G/4.92G [00:02<00:06, 527MB/s]
pytorch_model-00004-of-00005.bin: 36%|███▌ | 1.75G/4.92G [00:02<00:05, 570MB/s]
pytorch_model-00004-of-00005.bin: 39%|███▉ | 1.91G/4.92G [00:03<00:04, 717MB/s]
pytorch_model-00004-of-00005.bin: 41%|████ | 2.02G/4.92G [00:03<00:03, 774MB/s]
pytorch_model-00004-of-00005.bin: 45%|████▍ | 2.20G/4.92G [00:03<00:02, 958MB/s]
pytorch_model-00004-of-00005.bin: 48%|████▊ | 2.34G/4.92G [00:03<00:02, 923MB/s]
pytorch_model-00004-of-00005.bin: 53%|█████▎ | 2.60G/4.92G [00:03<00:01, 1.28GB/s]
pytorch_model-00004-of-00005.bin: 61%|██████ | 2.98G/4.92G [00:03<00:01, 1.80GB/s]
pytorch_model-00004-of-00005.bin: 65%|██████▍ | 3.19G/4.92G [00:03<00:01, 1.37GB/s]
pytorch_model-00004-of-00005.bin: 68%|██████▊ | 3.37G/4.92G [00:04<00:01, 1.40GB/s]
pytorch_model-00004-of-00005.bin: 72%|███████▏ | 3.54G/4.92G [00:04<00:00, 1.44GB/s]
pytorch_model-00004-of-00005.bin: 76%|███████▌ | 3.71G/4.92G [00:04<00:00, 1.48GB/s]
pytorch_model-00004-of-00005.bin: 80%|███████▉ | 3.93G/4.92G [00:04<00:00, 1.64GB/s]
pytorch_model-00004-of-00005.bin: 84%|████████▍ | 4.12G/4.92G [00:04<00:00, 1.36GB/s]
pytorch_model-00004-of-00005.bin: 87%|████████▋ | 4.28G/4.92G [00:04<00:00, 1.12GB/s]
pytorch_model-00004-of-00005.bin: 90%|████████▉ | 4.41G/4.92G [00:04<00:00, 1.00GB/s]
pytorch_model-00004-of-00005.bin: 92%|█████████▏| 4.53G/4.92G [00:05<00:00, 787MB/s]
pytorch_model-00004-of-00005.bin: 94%|█████████▍| 4.62G/4.92G [00:05<00:00, 733MB/s]
pytorch_model-00004-of-00005.bin: 100%|█████████▉| 4.92G/4.92G [00:05<00:00, 897MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
pytorch_model-00005-of-00005.bin: 0%| | 0.00/1.69G [00:00<?, ?B/s]
pytorch_model-00005-of-00005.bin: 1%| | 10.5M/1.69G [00:00<00:59, 28.2MB/s]
pytorch_model-00005-of-00005.bin: 6%|▌ | 94.4M/1.69G [00:00<00:07, 224MB/s]
pytorch_model-00005-of-00005.bin: 9%|▊ | 147M/1.69G [00:00<00:05, 294MB/s]
pytorch_model-00005-of-00005.bin: 16%|█▌ | 262M/1.69G [00:00<00:02, 507MB/s]
pytorch_model-00005-of-00005.bin: 22%|██▏ | 367M/1.69G [00:00<00:02, 647MB/s]
pytorch_model-00005-of-00005.bin: 34%|███▍ | 577M/1.69G [00:00<00:01, 1.04GB/s]
pytorch_model-00005-of-00005.bin: 43%|████▎ | 734M/1.69G [00:01<00:00, 1.19GB/s]
pytorch_model-00005-of-00005.bin: 52%|█████▏ | 870M/1.69G [00:01<00:00, 1.12GB/s]
pytorch_model-00005-of-00005.bin: 59%|█████▉ | 996M/1.69G [00:01<00:00, 887MB/s]
pytorch_model-00005-of-00005.bin: 65%|██████▌ | 1.10G/1.69G [00:01<00:01, 475MB/s]
pytorch_model-00005-of-00005.bin: 70%|███████ | 1.18G/1.69G [00:02<00:01, 452MB/s]
pytorch_model-00005-of-00005.bin: 75%|███████▍ | 1.26G/1.69G [00:02<00:00, 477MB/s]
pytorch_model-00005-of-00005.bin: 87%|████████▋ | 1.47G/1.69G [00:02<00:00, 746MB/s]
pytorch_model-00005-of-00005.bin: 100%|█████████▉| 1.69G/1.69G [00:02<00:00, 672MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
pytorch_model.bin.index.json: 0%| | 0.00/35.8k [00:00<?, ?B/s]
pytorch_model.bin.index.json: 100%|██████████| 35.8k/35.8k [00:00<00:00, 1.62MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 3.50MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 60.9MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
tokenizer_config.json: 0%| | 0.00/1.02k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 1.02k/1.02k [00:00<00:00, 16.1MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer: Downloaded to shared memory in 31.309s
thedrummer-moistral-11b-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thedrummer-moistral-11b-v1-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
thedrummer-moistral-11b-v1-v1-mkmlizer: Reading /tmp/tmpo206t8wg/pytorch_model.bin.index.json
thedrummer-moistral-11b-v1-v1-mkmlizer:
Profiling: 0%| | 0/435 [00:00<?, ?it/s]
Profiling: 0%| | 1/435 [00:02<18:54, 2.61s/it]
Profiling: 23%|██▎ | 98/435 [00:03<00:10, 33.35it/s]
Profiling: 47%|████▋ | 204/435 [00:04<00:04, 55.76it/s]
Profiling: 70%|██████▉ | 304/435 [00:05<00:01, 68.53it/s]
Profiling: 93%|█████████▎| 404/435 [00:06<00:00, 93.31it/s]
Profiling: 100%|██████████| 435/435 [00:07<00:00, 63.95it/s]
Profiling: 100%|██████████| 435/435 [00:07<00:00, 56.67it/s]
thedrummer-moistral-11b-v1-v1-mkmlizer: quantized model in 23.620s
thedrummer-moistral-11b-v1-v1-mkmlizer: Processed model TheDrummer/Moistral-11B-v1 in 56.393s
thedrummer-moistral-11b-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
thedrummer-moistral-11b-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thedrummer-moistral-11b-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1/tokenizer_config.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1/config.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1/special_tokens_map.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1/tokenizer.model
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1/tokenizer.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/thedrummer-moistral-11b-v1-v1/mkml_model.tensors
thedrummer-moistral-11b-v1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thedrummer-moistral-11b-v1-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.
thedrummer-moistral-11b-v1-v1-mkmlizer: warnings.warn(
thedrummer-moistral-11b-v1-v1-mkmlizer:
config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.3MB/s]
thedrummer-moistral-11b-v1-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.
thedrummer-moistral-11b-v1-v1-mkmlizer: warnings.warn(
thedrummer-moistral-11b-v1-v1-mkmlizer:
tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.04MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 40.9MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer:
tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 24.5MB/s]
thedrummer-moistral-11b-v1-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.
thedrummer-moistral-11b-v1-v1-mkmlizer: warnings.warn(
thedrummer-moistral-11b-v1-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, 78.3MB/s]
pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:14, 96.9MB/s]
pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:10, 133MB/s]
pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:10, 124MB/s]
pytorch_model.bin: 9%|▊ | 126M/1.44G [00:01<00:11, 120MB/s]
pytorch_model.bin: 10%|█ | 147M/1.44G [00:01<00:10, 129MB/s]
pytorch_model.bin: 24%|██▍ | 346M/1.44G [00:01<00:02, 516MB/s]
pytorch_model.bin: 68%|██████▊ | 975M/1.44G [00:01<00:00, 1.84GB/s]
pytorch_model.bin: 85%|████████▍ | 1.22G/1.44G [00:01<00:00, 1.90GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 887MB/s]
thedrummer-moistral-11b-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thedrummer-moistral-11b-v1-v1-mkmlizer: Saving duration: 0.262s
thedrummer-moistral-11b-v1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.060s
thedrummer-moistral-11b-v1-v1-mkmlizer: creating bucket guanaco-reward-models
thedrummer-moistral-11b-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thedrummer-moistral-11b-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward/config.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward/special_tokens_map.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward/tokenizer_config.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward/merges.txt
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward/tokenizer.json
thedrummer-moistral-11b-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thedrummer-moistral-11b-v1-v1_reward/vocab.json
Job thedrummer-moistral-11b-v1-v1-mkmlizer completed after 86.22s with status: succeeded
Stopping job with name thedrummer-moistral-11b-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service thedrummer-moistral-11b-v1-v1
Waiting for inference service thedrummer-moistral-11b-v1-v1 to be ready
Inference service thedrummer-moistral-11b-v1-v1 ready after 50.492356300354004s
Pipeline stage ISVCDeployer completed in 57.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0527279376983643s
Received healthy response to inference request in 0.9858577251434326s
Received healthy response to inference request in 1.2113487720489502s
Received healthy response to inference request in 0.7612977027893066s
Received healthy response to inference request in 0.8543920516967773s
5 requests
0 failed requests
5th percentile: 0.7799165725708008
10th percentile: 0.7985354423522949
20th percentile: 0.8357731819152832
30th percentile: 0.8806851863861084
40th percentile: 0.9332714557647706
50th percentile: 0.9858577251434326
60th percentile: 1.0760541439056397
70th percentile: 1.1662505626678465
80th percentile: 1.3796246051788332
90th percentile: 1.7161762714385986
95th percentile: 1.8844521045684812
99th percentile: 2.0190727710723877
mean time: 1.1731248378753663
Pipeline stage StressChecker completed in 6.88s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
admin requested tearing down of thedrummer-moistral-11b-v1_v1
Running pipeline stage ISVCDeleter
Checking if service thedrummer-moistral-11b-v1-v1 is running
Tearing down inference service thedrummer-moistral-11b-v1-v1
Toredown service thedrummer-moistral-11b-v1-v1
Pipeline stage ISVCDeleter completed in 4.68s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thedrummer-moistral-11b-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key thedrummer-moistral-11b-v1-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key thedrummer-moistral-11b-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thedrummer-moistral-11b-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thedrummer-moistral-11b-v1-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key thedrummer-moistral-11b-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thedrummer-moistral-11b-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key thedrummer-moistral-11b-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key thedrummer-moistral-11b-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thedrummer-moistral-11b-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thedrummer-moistral-11b-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thedrummer-moistral-11b-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thedrummer-moistral-11b-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.26s
thedrummer-moistral-11b-v1_v1 status is now torndown due to DeploymentManager action