submission_id: nitral-ai-infinite-stant_3029_v2
developer_uid: chai_backend_admin
status: inactive
model_repo: Nitral-AI/Infinite-Stanta-Laylelemon-Maid-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-04-02T17:58:30+00:00
model_name: auto_submit_ricum_koloyudova
model_eval_status: success
safety_score: 0.95
entertaining: 6.78
stay_in_character: 8.33
user_preference: 7.44
double_thumbs_up: 257
thumbs_up: 395
thumbs_down: 209
num_battles: 23314
num_wins: 10320
win_ratio: 0.44265248348631725
celo_rating: 1113.64
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-infinite-stant-3029-v2-mkmlizer
Waiting for job on nitral-ai-infinite-stant-3029-v2-mkmlizer to finish
nitral-ai-infinite-stant-3029-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ _____ __ __ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ /___/ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ Version: 0.6.11 ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ belonging to: ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ║ ║
nitral-ai-infinite-stant-3029-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-infinite-stant-3029-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.58k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.58k/1.58k [00:00<00:00, 16.3MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: README.md: 0%| | 0.00/949 [00:00<?, ?B/s] README.md: 100%|██████████| 949/949 [00:00<00:00, 7.10MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: config.json: 0%| | 0.00/649 [00:00<?, ?B/s] config.json: 100%|██████████| 649/649 [00:00<00:00, 10.6MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: mergekit_config.yml: 0%| | 0.00/404 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 404/404 [00:00<00:00, 6.54MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: mmproj-model-f16.gguf: 0%| | 0.00/624M [00:00<?, ?B/s] mmproj-model-f16.gguf: 2%|▏ | 10.5M/624M [00:00<00:14, 42.1MB/s] mmproj-model-f16.gguf: 5%|▌ | 31.5M/624M [00:00<00:06, 95.6MB/s] mmproj-model-f16.gguf: 8%|▊ | 47.7M/624M [00:00<00:05, 104MB/s] mmproj-model-f16.gguf: 23%|██▎ | 142M/624M [00:00<00:01, 335MB/s] mmproj-model-f16.gguf: 100%|█████████▉| 624M/624M [00:00<00:00, 844MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<01:19, 24.8MB/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:00<00:50, 38.4MB/s] model-00001-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:00<00:13, 146MB/s] model-00001-of-00008.safetensors: 5%|▌ | 105M/1.98G [00:01<00:15, 117MB/s] model-00001-of-00008.safetensors: 20%|██ | 398M/1.98G [00:01<00:02, 619MB/s] model-00001-of-00008.safetensors: 58%|█████▊ | 1.14G/1.98G [00:01<00:00, 1.93GB/s] model-00001-of-00008.safetensors: 73%|███████▎ | 1.44G/1.98G [00:01<00:00, 1.92GB/s] model-00001-of-00008.safetensors: 86%|████████▌ | 1.70G/1.98G [00:01<00:00, 1.50GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.13GB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00002-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00002-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:17, 24.9MB/s] model-00002-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:00<00:16, 117MB/s] model-00002-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:17, 108MB/s] model-00002-of-00008.safetensors: 6%|▋ | 126M/1.95G [00:01<00:15, 115MB/s] model-00002-of-00008.safetensors: 8%|▊ | 147M/1.95G [00:01<00:15, 118MB/s] model-00002-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:01<00:12, 142MB/s] model-00002-of-00008.safetensors: 12%|█▏ | 231M/1.95G [00:01<00:10, 160MB/s] model-00002-of-00008.safetensors: 13%|█▎ | 252M/1.95G [00:02<00:12, 133MB/s] model-00002-of-00008.safetensors: 14%|█▍ | 273M/1.95G [00:02<00:12, 132MB/s] model-00002-of-00008.safetensors: 15%|█▌ | 294M/1.95G [00:02<00:14, 111MB/s] model-00002-of-00008.safetensors: 16%|█▌ | 315M/1.95G [00:02<00:15, 107MB/s] model-00002-of-00008.safetensors: 17%|█▋ | 336M/1.95G [00:02<00:16, 97.9MB/s] model-00002-of-00008.safetensors: 20%|█▉ | 388M/1.95G [00:03<00:14, 105MB/s] model-00002-of-00008.safetensors: 24%|██▍ | 472M/1.95G [00:03<00:07, 194MB/s] model-00002-of-00008.safetensors: 44%|████▍ | 860M/1.95G [00:03<00:01, 742MB/s] model-00002-of-00008.safetensors: 71%|███████ | 1.38G/1.95G [00:03<00:00, 1.53GB/s] model-00002-of-00008.safetensors: 85%|████████▍ | 1.65G/1.95G [00:03<00:00, 1.74GB/s] model-00002-of-00008.safetensors: 98%|█████████▊| 1.91G/1.95G [00:04<00:00, 1.29GB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 462MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<01:49, 17.9MB/s] model-00003-of-00008.safetensors: 4%|▍ | 83.9M/1.98G [00:00<00:16, 115MB/s] model-00003-of-00008.safetensors: 6%|▋ | 126M/1.98G [00:00<00:11, 161MB/s] model-00003-of-00008.safetensors: 8%|▊ | 157M/1.98G [00:01<00:10, 168MB/s] model-00003-of-00008.safetensors: 18%|█▊ | 357M/1.98G [00:01<00:03, 504MB/s] model-00003-of-00008.safetensors: 56%|█████▌ | 1.11G/1.98G [00:01<00:00, 1.98GB/s] model-00003-of-00008.safetensors: 72%|███████▏ | 1.42G/1.98G [00:01<00:00, 2.15GB/s] model-00003-of-00008.safetensors: 86%|████████▌ | 1.71G/1.98G [00:01<00:00, 1.68GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.09GB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00004-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00004-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:13, 26.4MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:49, 38.8MB/s] model-00004-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:00<00:13, 142MB/s] model-00004-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:01<00:14, 126MB/s] model-00004-of-00008.safetensors: 23%|██▎ | 451M/1.95G [00:01<00:02, 712MB/s] model-00004-of-00008.safetensors: 59%|█████▉ | 1.15G/1.95G [00:01<00:00, 1.99GB/s] model-00004-of-00008.safetensors: 75%|███████▌ | 1.46G/1.95G [00:01<00:00, 1.71GB/s] model-00004-of-00008.safetensors: 88%|████████▊ | 1.72G/1.95G [00:01<00:00, 1.63GB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.10GB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<01:09, 28.2MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.98G [00:00<00:47, 40.8MB/s] model-00005-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:00<00:22, 85.2MB/s] model-00005-of-00008.safetensors: 5%|▌ | 105M/1.98G [00:01<00:14, 131MB/s] model-00005-of-00008.safetensors: 10%|█ | 199M/1.98G [00:01<00:06, 278MB/s] model-00005-of-00008.safetensors: 32%|███▏ | 640M/1.98G [00:01<00:01, 1.14GB/s] model-00005-of-00008.safetensors: 56%|█████▌ | 1.11G/1.98G [00:01<00:00, 1.94GB/s] model-00005-of-00008.safetensors: 70%|██████▉ | 1.38G/1.98G [00:01<00:00, 2.07GB/s] model-00005-of-00008.safetensors: 83%|████████▎ | 1.64G/1.98G [00:01<00:00, 1.64GB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.12GB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00006-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00006-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:22, 23.4MB/s] model-00006-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:47, 40.6MB/s] model-00006-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:14, 129MB/s] model-00006-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:01<00:14, 127MB/s] model-00006-of-00008.safetensors: 15%|█▌ | 294M/1.95G [00:01<00:03, 475MB/s] model-00006-of-00008.safetensors: 59%|█████▊ | 1.14G/1.95G [00:01<00:00, 2.24GB/s] model-00006-of-00008.safetensors: 76%|███████▋ | 1.49G/1.95G [00:01<00:00, 1.41GB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.09GB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:27, 22.1MB/s] model-00007-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:52, 37.0MB/s] model-00007-of-00008.safetensors: 10%|█ | 199M/1.95G [00:00<00:05, 345MB/s] model-00007-of-00008.safetensors: 12%|█▏ | 241M/1.95G [00:01<00:05, 292MB/s] model-00007-of-00008.safetensors: 17%|█▋ | 325M/1.95G [00:01<00:05, 323MB/s] model-00007-of-00008.safetensors: 19%|█▉ | 367M/1.95G [00:01<00:04, 325MB/s] model-00007-of-00008.safetensors: 21%|██ | 409M/1.95G [00:01<00:05, 270MB/s] model-00007-of-00008.safetensors: 23%|██▎ | 440M/1.95G [00:01<00:06, 250MB/s] model-00007-of-00008.safetensors: 24%|██▍ | 472M/1.95G [00:02<00:07, 194MB/s] model-00007-of-00008.safetensors: 26%|██▋ | 514M/1.95G [00:02<00:06, 216MB/s] model-00007-of-00008.safetensors: 28%|██▊ | 545M/1.95G [00:02<00:10, 139MB/s] model-00007-of-00008.safetensors: 30%|███ | 587M/1.95G [00:03<00:12, 106MB/s] model-00007-of-00008.safetensors: 35%|███▌ | 682M/1.95G [00:03<00:06, 189MB/s] model-00007-of-00008.safetensors: 49%|████▉ | 954M/1.95G [00:03<00:01, 509MB/s] model-00007-of-00008.safetensors: 84%|████████▍ | 1.63G/1.95G [00:03<00:00, 1.41GB/s] model-00007-of-00008.safetensors: 97%|█████████▋| 1.88G/1.95G [00:03<00:00, 1.58GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 509MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/755M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%|▏ | 10.5M/755M [00:00<00:15, 48.8MB/s] model-00008-of-00008.safetensors: 3%|▎ | 21.0M/755M [00:00<00:12, 59.7MB/s] model-00008-of-00008.safetensors: 15%|█▌ | 115M/755M [00:00<00:01, 331MB/s] model-00008-of-00008.safetensors: 42%|████▏ | 315M/755M [00:00<00:00, 827MB/s] model-00008-of-00008.safetensors: 63%|██████▎ | 472M/755M [00:01<00:00, 464MB/s] model-00008-of-00008.safetensors: 74%|███████▎ | 556M/755M [00:01<00:00, 502MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 755M/755M [00:01<00:00, 593MB/s]
nitral-ai-infinite-stant-3029-v2-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, 156MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 5.60MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 16.8MB/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 16.7MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 55.5MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 7.91MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: Downloaded to shared memory in 26.359s
nitral-ai-infinite-stant-3029-v2-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-infinite-stant-3029-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
nitral-ai-infinite-stant-3029-v2-mkmlizer: Reading /tmp/tmpt804uoku/model.safetensors.index.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:58, 4.93it/s] Profiling: 4%|▍ | 13/291 [00:00<00:05, 52.18it/s] Profiling: 11%|█ | 31/291 [00:00<00:02, 95.14it/s] Profiling: 15%|█▍ | 43/291 [00:00<00:02, 83.24it/s] Profiling: 20%|██ | 59/291 [00:00<00:02, 101.66it/s] Profiling: 27%|██▋ | 79/291 [00:00<00:02, 104.60it/s] Profiling: 32%|███▏ | 92/291 [00:00<00:01, 110.09it/s] Profiling: 37%|███▋ | 109/291 [00:01<00:01, 125.29it/s] Profiling: 42%|████▏ | 123/291 [00:01<00:01, 104.00it/s] Profiling: 48%|████▊ | 140/291 [00:01<00:01, 116.53it/s] Profiling: 55%|█████▌ | 161/291 [00:01<00:01, 119.95it/s] Profiling: 60%|█████▉ | 174/291 [00:01<00:00, 122.20it/s] Profiling: 66%|██████▋ | 193/291 [00:01<00:00, 138.61it/s] Profiling: 71%|███████▏ | 208/291 [00:04<00:04, 18.86it/s] Profiling: 77%|███████▋ | 225/291 [00:04<00:02, 26.03it/s] Profiling: 82%|████████▏ | 238/291 [00:04<00:01, 31.15it/s] Profiling: 87%|████████▋ | 254/291 [00:04<00:00, 41.26it/s] Profiling: 95%|█████████▍| 275/291 [00:04<00:00, 53.79it/s] Profiling: 100%|█████████▉| 290/291 [00:05<00:00, 65.10it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 57.71it/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: quantized model in 17.095s
nitral-ai-infinite-stant-3029-v2-mkmlizer: Processed model Nitral-AI/Infinite-Stanta-Laylelemon-Maid-7B in 44.388s
nitral-ai-infinite-stant-3029-v2-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-infinite-stant-3029-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-infinite-stant-3029-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2/config.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2/special_tokens_map.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2/tokenizer_config.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2/tokenizer.model
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2/tokenizer.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/nitral-ai-infinite-stant-3029-v2/mkml_model.tensors
nitral-ai-infinite-stant-3029-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-infinite-stant-3029-v2-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.
nitral-ai-infinite-stant-3029-v2-mkmlizer: warnings.warn(
nitral-ai-infinite-stant-3029-v2-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.0MB/s]
nitral-ai-infinite-stant-3029-v2-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.
nitral-ai-infinite-stant-3029-v2-mkmlizer: warnings.warn(
nitral-ai-infinite-stant-3029-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.72MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 1.25MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 1.24MB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 13.0MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 12.9MB/s]
nitral-ai-infinite-stant-3029-v2-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.
nitral-ai-infinite-stant-3029-v2-mkmlizer: warnings.warn(
nitral-ai-infinite-stant-3029-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:08, 173MB/s] pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:03, 407MB/s] pytorch_model.bin: 9%|▉ | 136M/1.44G [00:00<00:07, 172MB/s] pytorch_model.bin: 15%|█▍ | 210M/1.44G [00:00<00:04, 266MB/s] pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:00<00:04, 294MB/s] pytorch_model.bin: 23%|██▎ | 325M/1.44G [00:01<00:02, 390MB/s] pytorch_model.bin: 38%|███▊ | 556M/1.44G [00:01<00:01, 851MB/s] pytorch_model.bin: 73%|███████▎ | 1.05G/1.44G [00:01<00:00, 1.88GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.04GB/s]
nitral-ai-infinite-stant-3029-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-infinite-stant-3029-v2-mkmlizer: Saving duration: 0.289s
nitral-ai-infinite-stant-3029-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.933s
nitral-ai-infinite-stant-3029-v2-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-infinite-stant-3029-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-infinite-stant-3029-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/special_tokens_map.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/config.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/tokenizer_config.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/merges.txt
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/vocab.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/tokenizer.json
nitral-ai-infinite-stant-3029-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-infinite-stant-3029-v2_reward/reward.tensors
Job nitral-ai-infinite-stant-3029-v2-mkmlizer completed after 75.6s with status: succeeded
Stopping job with name nitral-ai-infinite-stant-3029-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-infinite-stant-3029-v2
Waiting for inference service nitral-ai-infinite-stant-3029-v2 to be ready
Inference service nitral-ai-infinite-stant-3029-v2 ready after 40.2681987285614s
Pipeline stage ISVCDeployer completed in 46.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.024000883102417s
Received healthy response to inference request in 0.544109582901001s
Received healthy response to inference request in 0.4781789779663086s
Received healthy response to inference request in 0.7662429809570312s
Received healthy response to inference request in 0.5501587390899658s
5 requests
0 failed requests
5th percentile: 0.4913650989532471
10th percentile: 0.5045512199401856
20th percentile: 0.5309234619140625
30th percentile: 0.5453194141387939
40th percentile: 0.5477390766143799
50th percentile: 0.5501587390899658
60th percentile: 0.6365924358367919
70th percentile: 0.7230261325836181
80th percentile: 0.8177945613861084
90th percentile: 0.9208977222442627
95th percentile: 0.9724493026733398
99th percentile: 1.0136905670166017
mean time: 0.6725382328033447
Pipeline stage StressChecker completed in 4.30s
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 0.08s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-infinite-stant_3029_v2 status is now deployed due to DeploymentManager action
nitral-ai-infinite-stant_3029_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics