Running pipeline stage MKMLizer
Starting job with name wespro-ayce-7b-rp-buffet-v1-mkmlizer
Waiting for job on wespro-ayce-7b-rp-buffet-v1-mkmlizer to finish
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.5MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
README.md:   0%|          | 0.00/1.28k [00:00<?, ?B/s]
README.md: 100%|██████████| 1.28k/1.28k [00:00<00:00, 21.2MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
config.json:   0%|          | 0.00/653 [00:00<?, ?B/s]
config.json: 100%|██████████| 653/653 [00:00<00:00, 10.8MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/597 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 597/597 [00:00<00:00, 9.82MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
model-00001-of-00002.safetensors:   0%|          | 0.00/9.98G [00:00<?, ?B/s]
model-00001-of-00002.safetensors:   0%|          | 10.5M/9.98G [00:00<10:20, 16.1MB/s]
model-00001-of-00002.safetensors:   0%|          | 21.0M/9.98G [00:00<06:04, 27.3MB/s]
model-00001-of-00002.safetensors:   0%|          | 31.5M/9.98G [00:01<10:02, 16.5MB/s]
model-00001-of-00002.safetensors:   0%|          | 41.9M/9.98G [00:01<07:12, 23.0MB/s]
model-00001-of-00002.safetensors:   1%|          | 52.4M/9.98G [00:02<05:29, 30.1MB/s]
model-00001-of-00002.safetensors:   1%|          | 62.9M/9.98G [00:02<06:29, 25.4MB/s]
model-00001-of-00002.safetensors:   1%|          | 115M/9.98G [00:02<02:07, 77.3MB/s] 
model-00001-of-00002.safetensors:   2%|▏         | 210M/9.98G [00:02<00:52, 188MB/s] 
model-00001-of-00002.safetensors:   3%|▎         | 315M/9.98G [00:03<00:31, 305MB/s]
model-00001-of-00002.safetensors:   4%|▍         | 377M/9.98G [00:03<00:27, 347MB/s]
model-00001-of-00002.safetensors:   4%|▍         | 430M/9.98G [00:03<00:27, 352MB/s]
model-00001-of-00002.safetensors:   6%|▋         | 640M/9.98G [00:03<00:13, 704MB/s]
model-00001-of-00002.safetensors:  11%|█         | 1.12G/9.98G [00:03<00:07, 1.22GB/s]
model-00001-of-00002.safetensors:  13%|█▎        | 1.25G/9.98G [00:04<00:13, 630MB/s] 
model-00001-of-00002.safetensors:  13%|█▎        | 1.34G/9.98G [00:04<00:13, 626MB/s]
model-00001-of-00002.safetensors:  14%|█▍        | 1.44G/9.98G [00:04<00:13, 641MB/s]
model-00001-of-00002.safetensors:  15%|█▌        | 1.54G/9.98G [00:04<00:11, 706MB/s]
model-00001-of-00002.safetensors:  16%|█▋        | 1.64G/9.98G [00:04<00:12, 685MB/s]
model-00001-of-00002.safetensors:  17%|█▋        | 1.72G/9.98G [00:04<00:13, 623MB/s]
model-00001-of-00002.safetensors:  18%|█▊        | 1.79G/9.98G [00:05<00:13, 603MB/s]
model-00001-of-00002.safetensors:  20%|█▉        | 1.95G/9.98G [00:05<00:10, 802MB/s]
model-00001-of-00002.safetensors:  20%|██        | 2.04G/9.98G [00:05<00:10, 750MB/s]
model-00001-of-00002.safetensors:  21%|██▏       | 2.13G/9.98G [00:05<00:10, 762MB/s]
model-00001-of-00002.safetensors:  22%|██▏       | 2.21G/9.98G [00:05<00:10, 709MB/s]
model-00001-of-00002.safetensors:  23%|██▎       | 2.32G/9.98G [00:05<00:09, 786MB/s]
model-00001-of-00002.safetensors:  27%|██▋       | 2.74G/9.98G [00:05<00:04, 1.65GB/s]
model-00001-of-00002.safetensors:  30%|███       | 3.03G/9.98G [00:05<00:03, 1.83GB/s]
model-00001-of-00002.safetensors:  32%|███▏      | 3.23G/9.98G [00:06<00:04, 1.63GB/s]
model-00001-of-00002.safetensors:  34%|███▍      | 3.41G/9.98G [00:06<00:09, 685MB/s] 
model-00001-of-00002.safetensors:  36%|███▌      | 3.54G/9.98G [00:06<00:09, 704MB/s]
model-00001-of-00002.safetensors:  38%|███▊      | 3.74G/9.98G [00:07<00:07, 875MB/s]
model-00001-of-00002.safetensors:  39%|███▉      | 3.88G/9.98G [00:07<00:06, 911MB/s]
model-00001-of-00002.safetensors:  41%|████      | 4.09G/9.98G [00:07<00:05, 1.13GB/s]
model-00001-of-00002.safetensors:  44%|████▎     | 4.35G/9.98G [00:07<00:04, 1.33GB/s]
model-00001-of-00002.safetensors:  45%|████▌     | 4.52G/9.98G [00:08<00:08, 624MB/s] 
model-00001-of-00002.safetensors:  47%|████▋     | 4.65G/9.98G [00:08<00:08, 656MB/s]
model-00001-of-00002.safetensors:  48%|████▊     | 4.79G/9.98G [00:08<00:06, 761MB/s]
model-00001-of-00002.safetensors:  49%|████▉     | 4.93G/9.98G [00:08<00:05, 857MB/s]
model-00001-of-00002.safetensors:  51%|█████▏    | 5.13G/9.98G [00:08<00:04, 1.06GB/s]
model-00001-of-00002.safetensors:  53%|█████▎    | 5.33G/9.98G [00:08<00:03, 1.25GB/s]
model-00001-of-00002.safetensors:  55%|█████▍    | 5.48G/9.98G [00:09<00:06, 665MB/s] 
model-00001-of-00002.safetensors:  56%|█████▌    | 5.61G/9.98G [00:09<00:07, 605MB/s]
model-00001-of-00002.safetensors:  57%|█████▋    | 5.71G/9.98G [00:09<00:07, 607MB/s]
model-00001-of-00002.safetensors:  59%|█████▉    | 5.88G/9.98G [00:09<00:05, 759MB/s]
model-00001-of-00002.safetensors:  60%|██████    | 6.01G/9.98G [00:09<00:04, 839MB/s]
model-00001-of-00002.safetensors:  62%|██████▏   | 6.20G/9.98G [00:09<00:03, 1.05GB/s]
model-00001-of-00002.safetensors:  63%|██████▎   | 6.33G/9.98G [00:10<00:03, 1.07GB/s]
model-00001-of-00002.safetensors:  65%|██████▍   | 6.47G/9.98G [00:10<00:03, 1.01GB/s]
model-00001-of-00002.safetensors:  66%|██████▌   | 6.59G/9.98G [00:10<00:05, 648MB/s] 
model-00001-of-00002.safetensors:  67%|██████▋   | 6.68G/9.98G [00:10<00:05, 602MB/s]
model-00001-of-00002.safetensors:  68%|██████▊   | 6.76G/9.98G [00:10<00:05, 626MB/s]
model-00001-of-00002.safetensors:  69%|██████▉   | 6.87G/9.98G [00:10<00:04, 703MB/s]
model-00001-of-00002.safetensors:  70%|██████▉   | 6.98G/9.98G [00:11<00:03, 767MB/s]
model-00001-of-00002.safetensors:  73%|███████▎  | 7.25G/9.98G [00:11<00:02, 1.13GB/s]
model-00001-of-00002.safetensors:  74%|███████▍  | 7.37G/9.98G [00:11<00:02, 1.16GB/s]
model-00001-of-00002.safetensors:  75%|███████▌  | 7.51G/9.98G [00:11<00:02, 1.19GB/s]
model-00001-of-00002.safetensors:  77%|███████▋  | 7.64G/9.98G [00:11<00:03, 754MB/s] 
model-00001-of-00002.safetensors:  78%|███████▊  | 7.75G/9.98G [00:12<00:03, 557MB/s]
model-00001-of-00002.safetensors:  79%|███████▊  | 7.83G/9.98G [00:12<00:03, 563MB/s]
model-00001-of-00002.safetensors:  80%|███████▉  | 7.96G/9.98G [00:12<00:02, 681MB/s]
model-00001-of-00002.safetensors:  81%|████████  | 8.06G/9.98G [00:12<00:02, 752MB/s]
model-00001-of-00002.safetensors:  83%|████████▎ | 8.23G/9.98G [00:12<00:01, 951MB/s]
model-00001-of-00002.safetensors:  85%|████████▌ | 8.48G/9.98G [00:12<00:01, 1.31GB/s]
model-00001-of-00002.safetensors:  87%|████████▋ | 8.64G/9.98G [00:12<00:01, 1.27GB/s]
model-00001-of-00002.safetensors:  88%|████████▊ | 8.79G/9.98G [00:13<00:01, 910MB/s] 
model-00001-of-00002.safetensors:  89%|████████▉ | 8.91G/9.98G [00:13<00:01, 653MB/s]
model-00001-of-00002.safetensors:  90%|█████████ | 9.01G/9.98G [00:13<00:01, 672MB/s]
model-00001-of-00002.safetensors:  91%|█████████ | 9.10G/9.98G [00:13<00:01, 692MB/s]
model-00001-of-00002.safetensors:  93%|█████████▎| 9.26G/9.98G [00:13<00:00, 842MB/s]
model-00001-of-00002.safetensors:  94%|█████████▍| 9.42G/9.98G [00:13<00:00, 988MB/s]
model-00001-of-00002.safetensors:  96%|█████████▋| 9.61G/9.98G [00:14<00:00, 1.18GB/s]
model-00001-of-00002.safetensors:  99%|█████████▉| 9.90G/9.98G [00:14<00:00, 1.61GB/s]
model-00001-of-00002.safetensors: 100%|█████████▉| 9.98G/9.98G [00:14<00:00, 697MB/s] 
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
model-00002-of-00002.safetensors:   0%|          | 0.00/4.51G [00:00<?, ?B/s]
model-00002-of-00002.safetensors:   0%|          | 10.5M/4.51G [00:02<14:44, 5.09MB/s]
model-00002-of-00002.safetensors:   0%|          | 21.0M/4.51G [00:02<07:25, 10.1MB/s]
model-00002-of-00002.safetensors:   2%|▏         | 83.9M/4.51G [00:02<01:19, 55.7MB/s]
model-00002-of-00002.safetensors:   4%|▎         | 168M/4.51G [00:02<00:33, 129MB/s]  
model-00002-of-00002.safetensors:   7%|▋         | 336M/4.51G [00:02<00:13, 313MB/s]
model-00002-of-00002.safetensors:  10%|█         | 451M/4.51G [00:02<00:09, 429MB/s]
model-00002-of-00002.safetensors:  12%|█▏        | 556M/4.51G [00:03<00:08, 472MB/s]
model-00002-of-00002.safetensors:  23%|██▎       | 1.06G/4.51G [00:03<00:03, 910MB/s]
model-00002-of-00002.safetensors:  26%|██▌       | 1.17G/4.51G [00:03<00:05, 559MB/s]
model-00002-of-00002.safetensors:  28%|██▊       | 1.26G/4.51G [00:03<00:05, 591MB/s]
model-00002-of-00002.safetensors:  31%|███       | 1.39G/4.51G [00:04<00:04, 688MB/s]
model-00002-of-00002.safetensors:  37%|███▋      | 1.66G/4.51G [00:04<00:03, 950MB/s]
model-00002-of-00002.safetensors:  40%|███▉      | 1.78G/4.51G [00:04<00:02, 930MB/s]
model-00002-of-00002.safetensors:  42%|████▏     | 1.90G/4.51G [00:04<00:02, 889MB/s]
model-00002-of-00002.safetensors:  44%|████▍     | 2.00G/4.51G [00:04<00:02, 905MB/s]
model-00002-of-00002.safetensors:  49%|████▉     | 2.20G/4.51G [00:04<00:02, 1.08GB/s]
model-00002-of-00002.safetensors:  52%|█████▏    | 2.33G/4.51G [00:04<00:02, 1.01GB/s]
model-00002-of-00002.safetensors:  54%|█████▍    | 2.44G/4.51G [00:05<00:02, 899MB/s] 
model-00002-of-00002.safetensors:  57%|█████▋    | 2.55G/4.51G [00:05<00:02, 883MB/s]
model-00002-of-00002.safetensors:  61%|██████    | 2.75G/4.51G [00:05<00:01, 1.11GB/s]
model-00002-of-00002.safetensors:  64%|██████▎   | 2.87G/4.51G [00:05<00:02, 788MB/s] 
model-00002-of-00002.safetensors:  66%|██████▌   | 2.98G/4.51G [00:05<00:02, 734MB/s]
model-00002-of-00002.safetensors:  68%|██████▊   | 3.07G/4.51G [00:05<00:02, 705MB/s]
model-00002-of-00002.safetensors:  70%|███████   | 3.18G/4.51G [00:06<00:01, 755MB/s]
model-00002-of-00002.safetensors:  73%|███████▎  | 3.28G/4.51G [00:06<00:01, 773MB/s]
model-00002-of-00002.safetensors:  75%|███████▌  | 3.39G/4.51G [00:06<00:01, 827MB/s]
model-00002-of-00002.safetensors:  77%|███████▋  | 3.48G/4.51G [00:06<00:01, 623MB/s]
model-00002-of-00002.safetensors:  80%|████████  | 3.61G/4.51G [00:06<00:01, 748MB/s]
model-00002-of-00002.safetensors:  82%|████████▏ | 3.70G/4.51G [00:06<00:01, 791MB/s]
model-00002-of-00002.safetensors:  86%|████████▌ | 3.87G/4.51G [00:06<00:00, 978MB/s]
model-00002-of-00002.safetensors:  88%|████████▊ | 3.98G/4.51G [00:06<00:00, 934MB/s]
model-00002-of-00002.safetensors:  92%|█████████▏| 4.16G/4.51G [00:07<00:00, 1.14GB/s]
model-00002-of-00002.safetensors:  95%|█████████▌| 4.30G/4.51G [00:07<00:00, 1.19GB/s]
model-00002-of-00002.safetensors: 100%|█████████▉| 4.51G/4.51G [00:07<00:00, 618MB/s] 
wespro-ayce-7b-rp-buffet-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, 124MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.34MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.80M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 10.5MB/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 10.4MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 51.8MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/1.46k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 1.46k/1.46k [00:00<00:00, 24.0MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Downloaded to shared memory in 23.549s
wespro-ayce-7b-rp-buffet-v1-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Reading /tmp/tmp3qt79brw/model.safetensors.index.json
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:01<06:20,  1.31s/it]
Profiling:   4%|▍         | 12/291 [00:01<00:24, 11.32it/s]
Profiling:   8%|▊         | 22/291 [00:01<00:12, 21.63it/s]
Profiling:  11%|█         | 32/291 [00:01<00:07, 32.64it/s]
Profiling:  16%|█▋        | 48/291 [00:01<00:04, 52.65it/s]
Profiling:  20%|█▉        | 58/291 [00:01<00:03, 59.21it/s]
Profiling:  23%|██▎       | 68/291 [00:02<00:03, 65.76it/s]
Profiling:  29%|██▉       | 84/291 [00:02<00:02, 83.27it/s]
Profiling:  33%|███▎      | 95/291 [00:02<00:02, 87.09it/s]
Profiling:  38%|███▊      | 111/291 [00:02<00:01, 103.58it/s]
Profiling:  42%|████▏     | 123/291 [00:02<00:01, 102.36it/s]
Profiling:  47%|████▋     | 136/291 [00:02<00:01, 108.14it/s]
Profiling:  51%|█████     | 148/291 [00:02<00:01, 107.77it/s]
Profiling:  55%|█████▌    | 161/291 [00:02<00:01, 113.41it/s]
Profiling:  60%|█████▉    | 174/291 [00:02<00:00, 117.55it/s]
Profiling:  64%|██████▍   | 187/291 [00:03<00:00, 115.05it/s]
Profiling:  69%|██████▉   | 201/291 [00:04<00:04, 20.74it/s] 
Profiling:  73%|███████▎  | 211/291 [00:04<00:03, 25.73it/s]
Profiling:  76%|███████▋  | 222/291 [00:05<00:02, 32.51it/s]
Profiling:  80%|███████▉  | 232/291 [00:05<00:01, 39.49it/s]
Profiling:  83%|████████▎ | 242/291 [00:05<00:01, 47.05it/s]
Profiling:  87%|████████▋ | 253/291 [00:05<00:00, 55.28it/s]
Profiling:  90%|█████████ | 263/291 [00:05<00:00, 61.55it/s]
Profiling:  96%|█████████▌| 279/291 [00:05<00:00, 78.87it/s]
Profiling: 100%|██████████| 291/291 [00:05<00:00, 49.37it/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: quantized model in 16.442s
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Processed model WesPro/Ayce-7B-RP-Buffet in 40.902s
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/wespro-ayce-7b-rp-buffet-v1/mkml_model.tensors
wespro-ayce-7b-rp-buffet-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-ayce-7b-rp-buffet-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.
wespro-ayce-7b-rp-buffet-v1-mkmlizer:   warnings.warn(
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.1MB/s]
wespro-ayce-7b-rp-buffet-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.
wespro-ayce-7b-rp-buffet-v1-mkmlizer:   warnings.warn(
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.86MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 56.1MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 45.1MB/s]
wespro-ayce-7b-rp-buffet-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.
wespro-ayce-7b-rp-buffet-v1-mkmlizer:   warnings.warn(
wespro-ayce-7b-rp-buffet-v1-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:07, 194MB/s]
pytorch_model.bin:   6%|▌         | 83.9M/1.44G [00:00<00:03, 427MB/s]
pytorch_model.bin:  16%|█▌        | 231M/1.44G [00:00<00:01, 842MB/s] 
pytorch_model.bin:  27%|██▋       | 388M/1.44G [00:00<00:01, 1.05GB/s]
pytorch_model.bin:  34%|███▍      | 493M/1.44G [00:00<00:01, 767MB/s] 
pytorch_model.bin:  43%|████▎     | 627M/1.44G [00:00<00:00, 901MB/s]
pytorch_model.bin:  57%|█████▋    | 826M/1.44G [00:00<00:00, 1.19GB/s]
pytorch_model.bin:  67%|██████▋   | 962M/1.44G [00:00<00:00, 1.23GB/s]
pytorch_model.bin:  83%|████████▎ | 1.20G/1.44G [00:01<00:00, 1.53GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 563MB/s] 
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 279MB/s]
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Saving duration: 0.307s
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.085s
wespro-ayce-7b-rp-buffet-v1-mkmlizer: creating bucket guanaco-reward-models
wespro-ayce-7b-rp-buffet-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-ayce-7b-rp-buffet-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/config.json
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/special_tokens_map.json
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/vocab.json
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/merges.txt
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/tokenizer_config.json
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/tokenizer.json
wespro-ayce-7b-rp-buffet-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-ayce-7b-rp-buffet-v1_reward/reward.tensors
Job wespro-ayce-7b-rp-buffet-v1-mkmlizer completed after 94.42s with status: succeeded
Stopping job with name wespro-ayce-7b-rp-buffet-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service wespro-ayce-7b-rp-buffet-v1
Waiting for inference service wespro-ayce-7b-rp-buffet-v1 to be ready
Inference service wespro-ayce-7b-rp-buffet-v1 ready after 30.188968420028687s
Pipeline stage ISVCDeployer completed in 37.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4598445892333984s
Received healthy response to inference request in 0.9147109985351562s
Received healthy response to inference request in 1.0198054313659668s
Received healthy response to inference request in 0.7044346332550049s
Received healthy response to inference request in 0.5417306423187256s
5 requests
0 failed requests
5th percentile: 0.5742714405059814
10th percentile: 0.6068122386932373
20th percentile: 0.671893835067749
30th percentile: 0.7464899063110352
40th percentile: 0.8306004524230958
50th percentile: 0.9147109985351562
60th percentile: 0.9567487716674805
70th percentile: 0.9987865447998047
80th percentile: 1.1078132629394533
90th percentile: 1.2838289260864257
95th percentile: 1.371836757659912
99th percentile: 1.442243022918701
mean time: 0.9281052589416504
Pipeline stage StressChecker completed in 5.99s
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
wespro-ayce-7b-rp-buffet_v1 status is now deployed due to DeploymentManager action
wespro-ayce-7b-rp-buffet_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-ayce-7b-rp-buffet_v1
Running pipeline stage ISVCDeleter
Checking if service wespro-ayce-7b-rp-buffet-v1 is running
Tearing down inference service wespro-ayce-7b-rp-buffet-v1
Toredown service wespro-ayce-7b-rp-buffet-v1
Pipeline stage ISVCDeleter completed in 3.91s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-ayce-7b-rp-buffet-v1/config.json from bucket guanaco-mkml-models
Deleting key wespro-ayce-7b-rp-buffet-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key wespro-ayce-7b-rp-buffet-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-ayce-7b-rp-buffet-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-ayce-7b-rp-buffet-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key wespro-ayce-7b-rp-buffet-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-ayce-7b-rp-buffet-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.95s
wespro-ayce-7b-rp-buffet_v1 status is now torndown due to DeploymentManager action