submission_id: inv-konstanta-v4-alpha-7b_v5
developer_uid: zonemercy
status: inactive
model_repo: Inv/Konstanta-V4-Alpha-7B
reward_repo: rirv938/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', '</s>', '###'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': 'Role-play as {bot_name} based on the Persona: {memory}. Engage user with detailed, creative messages that invite further discussion. Stay in character, keep responses moderately sized for an energetic exchange.', 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-03-27T18:49:09+00:00
model_name: inv-konstanta-v4-alpha-7b_v5
model_eval_status: success
safety_score: 0.98
entertaining: 7.12
stay_in_character: 8.67
user_preference: 7.46
double_thumbs_up: 835
thumbs_up: 1102
thumbs_down: 484
num_battles: 112327
num_wins: 60130
win_ratio: 0.5353120799095498
celo_rating: 1182.6
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-konstanta-v4-alpha-7b-v5-mkmlizer
Waiting for job on inv-konstanta-v4-alpha-7b-v5-mkmlizer to finish
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ _____ __ __ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ /___/ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ Version: 0.6.11 ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ The license key for the current software has been verified as ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ belonging to: ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ Chai Research Corp. ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-konstanta-v4-alpha-7b-v5-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.3MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: README.md: 0%| | 0.00/1.31k [00:00<?, ?B/s] README.md: 100%|██████████| 1.31k/1.31k [00:00<00:00, 20.5MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: config.json: 0%| | 0.00/632 [00:00<?, ?B/s] config.json: 100%|██████████| 632/632 [00:00<00:00, 7.68MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: mergekit_config.yml: 0%| | 0.00/410 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 410/410 [00:00<00:00, 4.48MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:00<00:20, 94.4MB/s] model-00001-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:00<00:04, 409MB/s] model-00001-of-00008.safetensors: 10%|█ | 199M/1.98G [00:00<00:03, 482MB/s] model-00001-of-00008.safetensors: 14%|█▍ | 283M/1.98G [00:00<00:02, 568MB/s] model-00001-of-00008.safetensors: 18%|█▊ | 357M/1.98G [00:00<00:02, 566MB/s] model-00001-of-00008.safetensors: 27%|██▋ | 535M/1.98G [00:00<00:01, 845MB/s] model-00001-of-00008.safetensors: 42%|████▏ | 828M/1.98G [00:00<00:00, 1.38GB/s] model-00001-of-00008.safetensors: 57%|█████▋ | 1.13G/1.98G [00:01<00:00, 1.83GB/s] model-00001-of-00008.safetensors: 68%|██████▊ | 1.34G/1.98G [00:01<00:00, 1.87GB/s] model-00001-of-00008.safetensors: 89%|████████▉ | 1.76G/1.98G [00:01<00:00, 2.50GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.50GB/s]
inv-konstanta-v4-alpha-7b-v5-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<00:33, 58.6MB/s] model-00002-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:05, 338MB/s] model-00002-of-00008.safetensors: 8%|▊ | 157M/1.95G [00:00<00:03, 469MB/s] model-00002-of-00008.safetensors: 16%|█▌ | 315M/1.95G [00:00<00:01, 823MB/s] model-00002-of-00008.safetensors: 23%|██▎ | 440M/1.95G [00:00<00:01, 909MB/s] model-00002-of-00008.safetensors: 31%|███ | 598M/1.95G [00:00<00:01, 1.10GB/s] model-00002-of-00008.safetensors: 43%|████▎ | 828M/1.95G [00:00<00:00, 1.44GB/s] model-00002-of-00008.safetensors: 51%|█████ | 986M/1.95G [00:00<00:00, 1.43GB/s] model-00002-of-00008.safetensors: 66%|██████▋ | 1.29G/1.95G [00:01<00:00, 1.89GB/s] model-00002-of-00008.safetensors: 97%|█████████▋| 1.88G/1.95G [00:01<00:00, 3.05GB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.64GB/s]
inv-konstanta-v4-alpha-7b-v5-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<00:26, 73.3MB/s] model-00003-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:00<00:06, 296MB/s] model-00003-of-00008.safetensors: 8%|▊ | 157M/1.98G [00:00<00:03, 547MB/s] model-00003-of-00008.safetensors: 14%|█▍ | 283M/1.98G [00:00<00:02, 793MB/s] model-00003-of-00008.safetensors: 19%|█▊ | 367M/1.98G [00:00<00:02, 800MB/s] model-00003-of-00008.safetensors: 23%|██▎ | 451M/1.98G [00:00<00:02, 663MB/s] model-00003-of-00008.safetensors: 32%|███▏ | 629M/1.98G [00:00<00:01, 967MB/s] model-00003-of-00008.safetensors: 44%|████▍ | 870M/1.98G [00:00<00:00, 1.32GB/s] model-00003-of-00008.safetensors: 54%|█████▍ | 1.07G/1.98G [00:01<00:00, 1.49GB/s] model-00003-of-00008.safetensors: 73%|███████▎ | 1.45G/1.98G [00:01<00:00, 2.10GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.56GB/s]
inv-konstanta-v4-alpha-7b-v5-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<00:28, 67.3MB/s] model-00004-of-00008.safetensors: 4%|▍ | 73.4M/1.95G [00:00<00:05, 325MB/s] model-00004-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:00<00:02, 635MB/s] model-00004-of-00008.safetensors: 16%|█▌ | 315M/1.95G [00:00<00:01, 826MB/s] model-00004-of-00008.safetensors: 21%|██ | 409M/1.95G [00:00<00:01, 859MB/s] model-00004-of-00008.safetensors: 32%|███▏ | 619M/1.95G [00:00<00:01, 1.24GB/s] model-00004-of-00008.safetensors: 42%|████▏ | 818M/1.95G [00:00<00:00, 1.43GB/s] model-00004-of-00008.safetensors: 50%|████▉ | 965M/1.95G [00:00<00:00, 1.40GB/s] model-00004-of-00008.safetensors: 57%|█████▋ | 1.11G/1.95G [00:01<00:00, 1.36GB/s] model-00004-of-00008.safetensors: 72%|███████▏ | 1.40G/1.95G [00:01<00:00, 1.77GB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.59GB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.89G [00:00<00:32, 57.0MB/s] model-00005-of-00008.safetensors: 3%|▎ | 62.9M/1.89G [00:00<00:08, 222MB/s] model-00005-of-00008.safetensors: 6%|▌ | 115M/1.89G [00:00<00:06, 276MB/s] model-00005-of-00008.safetensors: 9%|▉ | 168M/1.89G [00:00<00:05, 344MB/s] model-00005-of-00008.safetensors: 16%|█▌ | 304M/1.89G [00:00<00:02, 633MB/s] model-00005-of-00008.safetensors: 31%|███ | 577M/1.89G [00:00<00:01, 1.23GB/s] model-00005-of-00008.safetensors: 48%|████▊ | 912M/1.89G [00:00<00:00, 1.85GB/s] model-00005-of-00008.safetensors: 59%|█████▉ | 1.12G/1.89G [00:01<00:00, 1.83GB/s] model-00005-of-00008.safetensors: 73%|███████▎ | 1.39G/1.89G [00:01<00:00, 2.03GB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:01<00:00, 1.54GB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: model-00006-of-00008.safetensors: 0%| | 0.00/1.92G [00:00<?, ?B/s] model-00006-of-00008.safetensors: 1%| | 10.5M/1.92G [00:00<00:39, 48.8MB/s] model-00006-of-00008.safetensors: 4%|▍ | 73.4M/1.92G [00:00<00:06, 267MB/s] model-00006-of-00008.safetensors: 8%|▊ | 147M/1.92G [00:00<00:04, 416MB/s] model-00006-of-00008.safetensors: 11%|█ | 210M/1.92G [00:00<00:03, 483MB/s] model-00006-of-00008.safetensors: 17%|█▋ | 336M/1.92G [00:00<00:02, 686MB/s] model-00006-of-00008.safetensors: 29%|██▉ | 556M/1.92G [00:00<00:01, 1.13GB/s] model-00006-of-00008.safetensors: 41%|████ | 786M/1.92G [00:00<00:00, 1.47GB/s] model-00006-of-00008.safetensors: 62%|██████▏ | 1.18G/1.92G [00:00<00:00, 2.17GB/s] model-00006-of-00008.safetensors: 73%|███████▎ | 1.41G/1.92G [00:01<00:00, 2.07GB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:01<00:00, 1.59GB/s]
inv-konstanta-v4-alpha-7b-v5-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<00:27, 69.9MB/s] model-00007-of-00008.safetensors: 2%|▏ | 41.9M/1.95G [00:00<00:10, 187MB/s] model-00007-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:00<00:05, 360MB/s] model-00007-of-00008.safetensors: 8%|▊ | 147M/1.95G [00:00<00:05, 354MB/s] model-00007-of-00008.safetensors: 13%|█▎ | 252M/1.95G [00:00<00:03, 561MB/s] model-00007-of-00008.safetensors: 18%|█▊ | 357M/1.95G [00:00<00:02, 710MB/s] model-00007-of-00008.safetensors: 33%|███▎ | 640M/1.95G [00:00<00:00, 1.34GB/s] model-00007-of-00008.safetensors: 53%|█████▎ | 1.03G/1.95G [00:00<00:00, 2.10GB/s] model-00007-of-00008.safetensors: 64%|██████▍ | 1.25G/1.95G [00:01<00:00, 1.91GB/s] model-00007-of-00008.safetensors: 81%|████████ | 1.57G/1.95G [00:01<00:00, 2.25GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.62GB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/872M [00:00<00:17, 49.1MB/s] model-00008-of-00008.safetensors: 8%|▊ | 73.4M/872M [00:00<00:02, 281MB/s] model-00008-of-00008.safetensors: 16%|█▌ | 136M/872M [00:00<00:01, 405MB/s] model-00008-of-00008.safetensors: 43%|████▎ | 377M/872M [00:00<00:00, 1.08GB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:00<00:00, 2.29GB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:00<00:00, 1.35GB/s]
inv-konstanta-v4-alpha-7b-v5-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, 134MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 5.73MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 44.9MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 58.7MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 13.4MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: Downloaded to shared memory in 13.389s
inv-konstanta-v4-alpha-7b-v5-mkmlizer: quantizing model to /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v5-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v5-mkmlizer: Reading /tmp/tmpmy4jxjiv/model.safetensors.index.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:37, 7.77it/s] Profiling: 7%|▋ | 19/291 [00:00<00:02, 93.98it/s] Profiling: 13%|█▎ | 37/291 [00:00<00:02, 96.40it/s] Profiling: 19%|█▉ | 56/291 [00:00<00:01, 122.75it/s] Profiling: 26%|██▋ | 77/291 [00:00<00:01, 148.99it/s] Profiling: 32%|███▏ | 93/291 [00:00<00:01, 123.29it/s] Profiling: 38%|███▊ | 112/291 [00:00<00:01, 138.01it/s] Profiling: 44%|████▎ | 127/291 [00:01<00:01, 121.15it/s] Profiling: 50%|█████ | 146/291 [00:01<00:01, 136.07it/s] Profiling: 55%|█████▌ | 161/291 [00:02<00:03, 32.77it/s] Profiling: 62%|██████▏ | 180/291 [00:02<00:02, 45.06it/s] Profiling: 68%|██████▊ | 197/291 [00:03<00:03, 27.00it/s] Profiling: 73%|███████▎ | 212/291 [00:03<00:02, 34.78it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 44.87it/s] Profiling: 86%|████████▌ | 250/291 [00:04<00:00, 59.03it/s] Profiling: 93%|█████████▎| 271/291 [00:04<00:00, 77.69it/s] Profiling: 99%|█████████▊| 287/291 [00:04<00:00, 80.28it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 63.35it/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: quantized model in 14.768s
inv-konstanta-v4-alpha-7b-v5-mkmlizer: creating bucket guanaco-mkml-models
inv-konstanta-v4-alpha-7b-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-konstanta-v4-alpha-7b-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5/config.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5/tokenizer.model
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5/tokenizer.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v5/mkml_model.tensors
inv-konstanta-v4-alpha-7b-v5-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
inv-konstanta-v4-alpha-7b-v5-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-v4-alpha-7b-v5-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v5-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.4MB/s]
inv-konstanta-v4-alpha-7b-v5-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-v4-alpha-7b-v5-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v5-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.21MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 23.9MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 26.7MB/s]
inv-konstanta-v4-alpha-7b-v5-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-v4-alpha-7b-v5-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v5-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:09, 144MB/s] pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:16, 84.4MB/s] pytorch_model.bin: 9%|▊ | 126M/1.44G [00:00<00:06, 208MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:00<00:05, 247MB/s] pytorch_model.bin: 16%|█▌ | 231M/1.44G [00:00<00:03, 331MB/s] pytorch_model.bin: 23%|██▎ | 336M/1.44G [00:01<00:02, 508MB/s] pytorch_model.bin: 28%|██▊ | 398M/1.44G [00:01<00:01, 535MB/s] pytorch_model.bin: 47%|████▋ | 682M/1.44G [00:01<00:00, 1.15GB/s] pytorch_model.bin: 70%|██████▉ | 1.01G/1.44G [00:01<00:00, 1.73GB/s] pytorch_model.bin: 95%|█████████▍| 1.37G/1.44G [00:01<00:00, 2.27GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 951MB/s]
inv-konstanta-v4-alpha-7b-v5-mkmlizer: creating bucket guanaco-reward-models
inv-konstanta-v4-alpha-7b-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-konstanta-v4-alpha-7b-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/config.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/merges.txt
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/vocab.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/tokenizer.json
inv-konstanta-v4-alpha-7b-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v5_reward/reward.tensors
Job inv-konstanta-v4-alpha-7b-v5-mkmlizer completed after 137.08s with status: succeeded
Stopping job with name inv-konstanta-v4-alpha-7b-v5-mkmlizer
Pipeline stage MKMLizer completed in 143.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service inv-konstanta-v4-alpha-7b-v5
Waiting for inference service inv-konstanta-v4-alpha-7b-v5 to be ready
Inference service inv-konstanta-v4-alpha-7b-v5 ready after 40.26906156539917s
Pipeline stage ISVCDeployer completed in 48.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6544055938720703s
Received healthy response to inference request in 1.1885488033294678s
Received healthy response to inference request in 1.1748442649841309s
Received healthy response to inference request in 1.194946050643921s
Received healthy response to inference request in 1.2074804306030273s
5 requests
0 failed requests
5th percentile: 1.1775851726531983
10th percentile: 1.1803260803222657
20th percentile: 1.1858078956604003
30th percentile: 1.1898282527923585
40th percentile: 1.1923871517181397
50th percentile: 1.194946050643921
60th percentile: 1.1999598026275635
70th percentile: 1.2049735546112061
80th percentile: 1.296865463256836
90th percentile: 1.4756355285644531
95th percentile: 1.5650205612182617
99th percentile: 1.6365285873413087
mean time: 1.2840450286865235
Pipeline stage StressChecker completed in 7.32s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.08s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
inv-konstanta-v4-alpha-7b_v5 status is now deployed due to DeploymentManager action
inv-konstanta-v4-alpha-7b_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics