submission_id: inv-konstanta-7b_v3
developer_uid: Inv
status: inactive
model_repo: Inv/Konstanta-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': 'This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}.\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: 2024-03-23T18:43:39+00:00
model_name: inv-konstanta-7b_v3
model_eval_status: success
safety_score: 0.96
entertaining: 7.02
stay_in_character: 8.81
user_preference: 7.3
double_thumbs_up: 481
thumbs_up: 740
thumbs_down: 340
num_battles: 67167
num_wins: 34779
win_ratio: 0.517798919112064
celo_rating: 1169.59
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-konstanta-7b-v3-mkmlizer
Waiting for job on inv-konstanta-7b-v3-mkmlizer to finish
inv-konstanta-7b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-konstanta-7b-v3-mkmlizer: ║ _____ __ __ ║
inv-konstanta-7b-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-konstanta-7b-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-konstanta-7b-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-konstanta-7b-v3-mkmlizer: ║ /___/ ║
inv-konstanta-7b-v3-mkmlizer: ║ ║
inv-konstanta-7b-v3-mkmlizer: ║ Version: 0.6.11 ║
inv-konstanta-7b-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-konstanta-7b-v3-mkmlizer: ║ ║
inv-konstanta-7b-v3-mkmlizer: ║ The license key for the current software has been verified as ║
inv-konstanta-7b-v3-mkmlizer: ║ belonging to: ║
inv-konstanta-7b-v3-mkmlizer: ║ ║
inv-konstanta-7b-v3-mkmlizer: ║ Chai Research Corp. ║
inv-konstanta-7b-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-konstanta-7b-v3-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
inv-konstanta-7b-v3-mkmlizer: ║ ║
inv-konstanta-7b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-konstanta-7b-v3-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.1MB/s]
inv-konstanta-7b-v3-mkmlizer: README.md: 0%| | 0.00/5.13k [00:00<?, ?B/s] README.md: 100%|██████████| 5.13k/5.13k [00:00<00:00, 51.5MB/s]
inv-konstanta-7b-v3-mkmlizer: config.json: 0%| | 0.00/647 [00:00<?, ?B/s] config.json: 100%|██████████| 647/647 [00:00<00:00, 7.82MB/s]
inv-konstanta-7b-v3-mkmlizer: mergekit_config.yml: 0%| | 0.00/355 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 355/355 [00:00<00:00, 4.80MB/s]
inv-konstanta-7b-v3-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<00:37, 52.0MB/s] model-00001-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:00<00:30, 62.5MB/s] model-00001-of-00008.safetensors: 10%|█ | 199M/1.95G [00:00<00:03, 449MB/s] model-00001-of-00008.safetensors: 18%|█▊ | 346M/1.95G [00:00<00:02, 707MB/s] model-00001-of-00008.safetensors: 30%|██▉ | 577M/1.95G [00:00<00:01, 1.12GB/s] model-00001-of-00008.safetensors: 38%|███▊ | 734M/1.95G [00:01<00:01, 684MB/s] model-00001-of-00008.safetensors: 44%|████▎ | 849M/1.95G [00:01<00:02, 474MB/s] model-00001-of-00008.safetensors: 48%|████▊ | 933M/1.95G [00:01<00:02, 491MB/s] model-00001-of-00008.safetensors: 52%|█████▏ | 1.01G/1.95G [00:02<00:03, 236MB/s] model-00001-of-00008.safetensors: 55%|█████▌ | 1.08G/1.95G [00:02<00:03, 262MB/s] model-00001-of-00008.safetensors: 75%|███████▍ | 1.45G/1.95G [00:02<00:00, 639MB/s] model-00001-of-00008.safetensors: 83%|████████▎ | 1.61G/1.95G [00:03<00:00, 708MB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 597MB/s]
inv-konstanta-7b-v3-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<01:04, 29.9MB/s] model-00002-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:00<00:23, 80.2MB/s] model-00002-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:00<00:07, 263MB/s] model-00002-of-00008.safetensors: 18%|█▊ | 346M/1.95G [00:00<00:01, 874MB/s] model-00002-of-00008.safetensors: 30%|██▉ | 577M/1.95G [00:00<00:01, 954MB/s] model-00002-of-00008.safetensors: 36%|███▌ | 692M/1.95G [00:01<00:04, 306MB/s] model-00002-of-00008.safetensors: 40%|███▉ | 776M/1.95G [00:02<00:03, 304MB/s] model-00002-of-00008.safetensors: 43%|████▎ | 839M/1.95G [00:02<00:04, 273MB/s] model-00002-of-00008.safetensors: 46%|████▌ | 891M/1.95G [00:02<00:03, 264MB/s] model-00002-of-00008.safetensors: 72%|███████▏ | 1.39G/1.95G [00:02<00:00, 822MB/s] model-00002-of-00008.safetensors: 81%|████████ | 1.58G/1.95G [00:03<00:00, 819MB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 602MB/s]
inv-konstanta-7b-v3-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.89G [00:00<00:57, 32.9MB/s] model-00003-of-00008.safetensors: 1%| | 21.0M/1.89G [00:00<00:36, 51.3MB/s] model-00003-of-00008.safetensors: 7%|▋ | 136M/1.89G [00:00<00:04, 370MB/s] model-00003-of-00008.safetensors: 16%|█▌ | 294M/1.89G [00:00<00:02, 704MB/s] model-00003-of-00008.safetensors: 33%|███▎ | 629M/1.89G [00:00<00:00, 1.46GB/s] model-00003-of-00008.safetensors: 43%|████▎ | 807M/1.89G [00:01<00:01, 717MB/s] model-00003-of-00008.safetensors: 50%|█████ | 946M/1.89G [00:02<00:03, 276MB/s] model-00003-of-00008.safetensors: 64%|██████▍ | 1.22G/1.89G [00:02<00:01, 375MB/s] model-00003-of-00008.safetensors: 69%|██████▉ | 1.31G/1.89G [00:03<00:01, 415MB/s] model-00003-of-00008.safetensors: 81%|████████ | 1.52G/1.89G [00:03<00:00, 581MB/s] model-00003-of-00008.safetensors: 87%|████████▋ | 1.65G/1.89G [00:03<00:00, 629MB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 555MB/s]
inv-konstanta-7b-v3-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<01:16, 25.2MB/s] model-00004-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:00<00:07, 232MB/s] model-00004-of-00008.safetensors: 12%|█▏ | 241M/1.95G [00:00<00:03, 547MB/s] model-00004-of-00008.safetensors: 19%|█▉ | 377M/1.95G [00:00<00:02, 735MB/s] model-00004-of-00008.safetensors: 33%|███▎ | 640M/1.95G [00:00<00:01, 1.22GB/s] model-00004-of-00008.safetensors: 41%|████ | 797M/1.95G [00:01<00:01, 1.13GB/s] model-00004-of-00008.safetensors: 48%|████▊ | 933M/1.95G [00:01<00:01, 975MB/s] model-00004-of-00008.safetensors: 54%|█████▍ | 1.05G/1.95G [00:01<00:00, 977MB/s] model-00004-of-00008.safetensors: 60%|█████▉ | 1.16G/1.95G [00:01<00:00, 887MB/s] model-00004-of-00008.safetensors: 65%|██████▍ | 1.26G/1.95G [00:02<00:02, 311MB/s] model-00004-of-00008.safetensors: 73%|███████▎ | 1.42G/1.95G [00:02<00:01, 427MB/s] model-00004-of-00008.safetensors: 78%|███████▊ | 1.52G/1.95G [00:02<00:01, 427MB/s] model-00004-of-00008.safetensors: 87%|████████▋ | 1.68G/1.95G [00:02<00:00, 581MB/s] model-00004-of-00008.safetensors: 97%|█████████▋| 1.89G/1.95G [00:02<00:00, 817MB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 643MB/s]
inv-konstanta-7b-v3-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<00:52, 37.9MB/s] model-00005-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:00<00:07, 239MB/s] model-00005-of-00008.safetensors: 8%|▊ | 157M/1.98G [00:00<00:04, 429MB/s] model-00005-of-00008.safetensors: 18%|█▊ | 357M/1.98G [00:00<00:01, 894MB/s] model-00005-of-00008.safetensors: 37%|███▋ | 724M/1.98G [00:00<00:00, 1.57GB/s] model-00005-of-00008.safetensors: 45%|████▌ | 891M/1.98G [00:02<00:03, 296MB/s] model-00005-of-00008.safetensors: 51%|█████ | 1.01G/1.98G [00:02<00:02, 329MB/s] model-00005-of-00008.safetensors: 63%|██████▎ | 1.25G/1.98G [00:02<00:01, 487MB/s] model-00005-of-00008.safetensors: 69%|██████▉ | 1.37G/1.98G [00:02<00:01, 500MB/s] model-00005-of-00008.safetensors: 75%|███████▍ | 1.48G/1.98G [00:03<00:01, 474MB/s] model-00005-of-00008.safetensors: 86%|████████▌ | 1.71G/1.98G [00:03<00:00, 698MB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:03<00:00, 583MB/s]
inv-konstanta-7b-v3-mkmlizer: model-00006-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00006-of-00008.safetensors: 1%| | 10.5M/1.89G [00:00<01:06, 28.4MB/s] model-00006-of-00008.safetensors: 7%|▋ | 126M/1.89G [00:00<00:05, 339MB/s] model-00006-of-00008.safetensors: 13%|█▎ | 241M/1.89G [00:00<00:02, 566MB/s] model-00006-of-00008.safetensors: 19%|█▉ | 367M/1.89G [00:00<00:02, 759MB/s] model-00006-of-00008.safetensors: 33%|███▎ | 629M/1.89G [00:00<00:00, 1.30GB/s] model-00006-of-00008.safetensors: 42%|████▏ | 797M/1.89G [00:00<00:01, 1.05GB/s] model-00006-of-00008.safetensors: 49%|████▉ | 933M/1.89G [00:01<00:00, 1.06GB/s] model-00006-of-00008.safetensors: 56%|█████▌ | 1.06G/1.89G [00:01<00:02, 398MB/s] model-00006-of-00008.safetensors: 66%|██████▌ | 1.25G/1.89G [00:02<00:01, 557MB/s] model-00006-of-00008.safetensors: 73%|███████▎ | 1.38G/1.89G [00:02<00:01, 480MB/s] model-00006-of-00008.safetensors: 78%|███████▊ | 1.48G/1.89G [00:02<00:00, 546MB/s] model-00006-of-00008.safetensors: 84%|████████▍ | 1.60G/1.89G [00:02<00:00, 635MB/s] model-00006-of-00008.safetensors: 96%|█████████▌| 1.81G/1.89G [00:02<00:00, 892MB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:02<00:00, 674MB/s]
inv-konstanta-7b-v3-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<01:05, 30.2MB/s] model-00007-of-00008.safetensors: 4%|▍ | 83.9M/1.98G [00:00<00:08, 222MB/s] model-00007-of-00008.safetensors: 11%|█ | 210M/1.98G [00:00<00:03, 512MB/s] model-00007-of-00008.safetensors: 19%|█▊ | 367M/1.98G [00:00<00:02, 803MB/s] model-00007-of-00008.safetensors: 35%|███▍ | 692M/1.98G [00:00<00:00, 1.50GB/s] model-00007-of-00008.safetensors: 44%|████▍ | 881M/1.98G [00:00<00:00, 1.20GB/s] model-00007-of-00008.safetensors: 52%|█████▏ | 1.04G/1.98G [00:01<00:00, 1.15GB/s] model-00007-of-00008.safetensors: 59%|█████▉ | 1.17G/1.98G [00:01<00:00, 1.18GB/s] model-00007-of-00008.safetensors: 66%|██████▌ | 1.31G/1.98G [00:02<00:01, 421MB/s] model-00007-of-00008.safetensors: 74%|███████▎ | 1.46G/1.98G [00:02<00:00, 528MB/s] model-00007-of-00008.safetensors: 79%|███████▉ | 1.57G/1.98G [00:02<00:00, 479MB/s] model-00007-of-00008.safetensors: 85%|████████▌ | 1.69G/1.98G [00:02<00:00, 537MB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:02<00:00, 703MB/s]
inv-konstanta-7b-v3-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/906M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/906M [00:00<00:26, 34.2MB/s] model-00008-of-00008.safetensors: 5%|▍ | 41.9M/906M [00:00<00:07, 112MB/s] model-00008-of-00008.safetensors: 9%|▉ | 83.9M/906M [00:00<00:04, 199MB/s] model-00008-of-00008.safetensors: 24%|██▎ | 214M/906M [00:00<00:01, 516MB/s] model-00008-of-00008.safetensors: 44%|████▍ | 403M/906M [00:00<00:00, 899MB/s] model-00008-of-00008.safetensors: 64%|██████▍ | 581M/906M [00:00<00:00, 1.13GB/s] model-00008-of-00008.safetensors: 85%|████████▍ | 770M/906M [00:00<00:00, 1.34GB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 906M/906M [00:01<00:00, 519MB/s]
inv-konstanta-7b-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.70MB/s]
inv-konstanta-7b-v3-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 18.9MB/s]
inv-konstanta-7b-v3-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 24.2MB/s]
inv-konstanta-7b-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/916 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 916/916 [00:00<00:00, 7.17MB/s]
inv-konstanta-7b-v3-mkmlizer: Downloaded to shared memory in 27.836s
inv-konstanta-7b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
inv-konstanta-7b-v3-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-konstanta-7b-v3-mkmlizer: Reading /tmp/tmp_yvqpawz/model.safetensors.index.json
inv-konstanta-7b-v3-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:32, 8.88it/s] Profiling: 4%|▍ | 12/291 [00:00<00:04, 63.38it/s] Profiling: 8%|▊ | 24/291 [00:00<00:03, 85.15it/s] Profiling: 12%|█▏ | 34/291 [00:00<00:02, 88.80it/s] Profiling: 15%|█▍ | 43/291 [00:00<00:03, 79.49it/s] Profiling: 20%|█▉ | 57/291 [00:00<00:02, 91.85it/s] Profiling: 23%|██▎ | 67/291 [00:00<00:02, 90.84it/s] Profiling: 27%|██▋ | 80/291 [00:00<00:02, 102.01it/s] Profiling: 31%|███▏ | 91/291 [00:02<00:09, 21.12it/s] Profiling: 34%|███▍ | 99/291 [00:02<00:07, 25.64it/s] Profiling: 40%|████ | 117/291 [00:02<00:04, 40.95it/s] Profiling: 44%|████▍ | 128/291 [00:02<00:03, 46.17it/s] Profiling: 49%|████▉ | 142/291 [00:02<00:02, 59.44it/s] Profiling: 53%|█████▎ | 153/291 [00:02<00:02, 67.18it/s] Profiling: 56%|█████▋ | 164/291 [00:03<00:01, 67.36it/s] Profiling: 62%|██████▏ | 179/291 [00:03<00:01, 80.78it/s] Profiling: 66%|██████▌ | 192/291 [00:03<00:01, 90.44it/s] Profiling: 70%|███████ | 204/291 [00:04<00:03, 23.25it/s] Profiling: 76%|███████▌ | 220/291 [00:04<00:02, 33.25it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 40.29it/s] Profiling: 83%|████████▎ | 242/291 [00:05<00:01, 46.24it/s] Profiling: 88%|████████▊ | 256/291 [00:05<00:00, 58.03it/s] Profiling: 93%|█████████▎| 270/291 [00:05<00:00, 71.21it/s] Profiling: 97%|█████████▋| 282/291 [00:05<00:00, 65.22it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 51.16it/s]
inv-konstanta-7b-v3-mkmlizer: quantized model in 16.334s
inv-konstanta-7b-v3-mkmlizer: Processed model Inv/Konstanta-7B in 45.074s
inv-konstanta-7b-v3-mkmlizer: creating bucket guanaco-mkml-models
inv-konstanta-7b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-konstanta-7b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-konstanta-7b-v3
inv-konstanta-7b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-konstanta-7b-v3/tokenizer.model
inv-konstanta-7b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-konstanta-7b-v3/tokenizer.json
inv-konstanta-7b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-konstanta-7b-v3/config.json
inv-konstanta-7b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-konstanta-7b-v3/special_tokens_map.json
inv-konstanta-7b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-konstanta-7b-v3/tokenizer_config.json
inv-konstanta-7b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-konstanta-7b-v3-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.
inv-konstanta-7b-v3-mkmlizer: warnings.warn(
inv-konstanta-7b-v3-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]
inv-konstanta-7b-v3-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.
inv-konstanta-7b-v3-mkmlizer: warnings.warn(
inv-konstanta-7b-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.58MB/s]
inv-konstanta-7b-v3-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 14.2MB/s]
inv-konstanta-7b-v3-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.1MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.0MB/s]
inv-konstanta-7b-v3-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.
inv-konstanta-7b-v3-mkmlizer: warnings.warn(
inv-konstanta-7b-v3-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:22, 63.3MB/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:28, 50.6MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:05, 242MB/s] pytorch_model.bin: 9%|▉ | 136M/1.44G [00:00<00:04, 286MB/s] pytorch_model.bin: 16%|█▌ | 231M/1.44G [00:00<00:02, 469MB/s] pytorch_model.bin: 21%|██ | 304M/1.44G [00:00<00:02, 456MB/s] pytorch_model.bin: 25%|██▍ | 357M/1.44G [00:01<00:02, 450MB/s] pytorch_model.bin: 38%|███▊ | 545M/1.44G [00:01<00:01, 821MB/s] pytorch_model.bin: 63%|██████▎ | 912M/1.44G [00:01<00:00, 1.59GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.07GB/s]
inv-konstanta-7b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-konstanta-7b-v3-mkmlizer: Saving duration: 0.238s
inv-konstanta-7b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.697s
inv-konstanta-7b-v3-mkmlizer: creating bucket guanaco-reward-models
inv-konstanta-7b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-konstanta-7b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-konstanta-7b-v3_reward
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/config.json
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/tokenizer_config.json
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/merges.txt
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/special_tokens_map.json
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/vocab.json
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/tokenizer.json
inv-konstanta-7b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-konstanta-7b-v3_reward/reward.tensors
Job inv-konstanta-7b-v3-mkmlizer completed after 75.63s with status: succeeded
Stopping job with name inv-konstanta-7b-v3-mkmlizer
Pipeline stage MKMLizer completed in 79.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.33s
Running pipeline stage ISVCDeployer
Creating inference service inv-konstanta-7b-v3
Waiting for inference service inv-konstanta-7b-v3 to be ready
Inference service inv-konstanta-7b-v3 ready after 40.22850751876831s
Pipeline stage ISVCDeployer completed in 47.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.799464464187622s
Received healthy response to inference request in 1.143632173538208s
Received healthy response to inference request in 1.152250051498413s
Received healthy response to inference request in 1.1728789806365967s
Received healthy response to inference request in 1.1791033744812012s
5 requests
0 failed requests
5th percentile: 1.145355749130249
10th percentile: 1.1470793247222901
20th percentile: 1.150526475906372
30th percentile: 1.1563758373260498
40th percentile: 1.1646274089813233
50th percentile: 1.1728789806365967
60th percentile: 1.1753687381744384
70th percentile: 1.1778584957122802
80th percentile: 1.3031755924224855
90th percentile: 1.5513200283050539
95th percentile: 1.6753922462463378
99th percentile: 1.7746500205993652
mean time: 1.2894658088684081
Pipeline stage StressChecker completed in 7.43s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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
inv-konstanta-7b_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics