submission_id: inv-elbrus-7b_v1
developer_uid: Inv
status: inactive
model_repo: Inv/Elbrus-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}. Put actions in asterisks.', '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: 2024-03-26T18:12:42+00:00
model_name: inv-elbrus-7b_v1
model_eval_status: success
safety_score: 0.78
entertaining: 6.86
stay_in_character: 8.33
user_preference: 6.7
double_thumbs_up: 340
thumbs_up: 523
thumbs_down: 318
num_battles: 67836
num_wins: 33423
win_ratio: 0.49270298956306385
celo_rating: 1152.28
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-elbrus-7b-v1-mkmlizer
Waiting for job on inv-elbrus-7b-v1-mkmlizer to finish
inv-elbrus-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-elbrus-7b-v1-mkmlizer: ║ _____ __ __ ║
inv-elbrus-7b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-elbrus-7b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-elbrus-7b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-elbrus-7b-v1-mkmlizer: ║ /___/ ║
inv-elbrus-7b-v1-mkmlizer: ║ ║
inv-elbrus-7b-v1-mkmlizer: ║ Version: 0.6.11 ║
inv-elbrus-7b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-elbrus-7b-v1-mkmlizer: ║ ║
inv-elbrus-7b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
inv-elbrus-7b-v1-mkmlizer: ║ belonging to: ║
inv-elbrus-7b-v1-mkmlizer: ║ ║
inv-elbrus-7b-v1-mkmlizer: ║ Chai Research Corp. ║
inv-elbrus-7b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-elbrus-7b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
inv-elbrus-7b-v1-mkmlizer: ║ ║
inv-elbrus-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-elbrus-7b-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 20.2MB/s]
inv-elbrus-7b-v1-mkmlizer: README.md: 0%| | 0.00/933 [00:00<?, ?B/s] README.md: 100%|██████████| 933/933 [00:00<00:00, 8.45MB/s]
inv-elbrus-7b-v1-mkmlizer: config.json: 0%| | 0.00/628 [00:00<?, ?B/s] config.json: 100%|██████████| 628/628 [00:00<00:00, 6.82MB/s]
inv-elbrus-7b-v1-mkmlizer: mergekit_config.yml: 0%| | 0.00/254 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 254/254 [00:00<00:00, 2.77MB/s]
inv-elbrus-7b-v1-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 [00:01<03:38, 8.99MB/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<02:15, 14.4MB/s] model-00001-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:01<00:59, 32.4MB/s] model-00001-of-00008.safetensors: 3%|▎ | 52.4M/1.98G [00:02<00:58, 32.9MB/s] model-00001-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:02<00:50, 38.2MB/s] model-00001-of-00008.safetensors: 4%|▍ | 83.9M/1.98G [00:02<00:37, 50.8MB/s] model-00001-of-00008.safetensors: 5%|▍ | 94.4M/1.98G [00:02<00:35, 52.8MB/s] model-00001-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:03<00:33, 54.9MB/s] model-00001-of-00008.safetensors: 19%|█▉ | 377M/1.98G [00:03<00:04, 398MB/s] model-00001-of-00008.safetensors: 60%|█████▉ | 1.18G/1.98G [00:03<00:00, 1.44GB/s] model-00001-of-00008.safetensors: 70%|██████▉ | 1.38G/1.98G [00:04<00:00, 684MB/s] model-00001-of-00008.safetensors: 77%|███████▋ | 1.53G/1.98G [00:04<00:00, 650MB/s] model-00001-of-00008.safetensors: 83%|████████▎ | 1.64G/1.98G [00:04<00:00, 693MB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 431MB/s]
inv-elbrus-7b-v1-mkmlizer: model-00002-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00002-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<00:58, 33.9MB/s] model-00002-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<03:10, 10.3MB/s] model-00002-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:53, 17.1MB/s] model-00002-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:02<00:34, 55.3MB/s] model-00002-of-00008.safetensors: 7%|▋ | 136M/1.98G [00:02<00:15, 120MB/s] model-00002-of-00008.safetensors: 8%|▊ | 168M/1.98G [00:02<00:13, 134MB/s] model-00002-of-00008.safetensors: 10%|█ | 199M/1.98G [00:02<00:12, 145MB/s] model-00002-of-00008.safetensors: 14%|█▍ | 273M/1.98G [00:02<00:07, 224MB/s] model-00002-of-00008.safetensors: 16%|█▌ | 315M/1.98G [00:02<00:06, 258MB/s] model-00002-of-00008.safetensors: 55%|█████▌ | 1.09G/1.98G [00:02<00:00, 1.78GB/s] model-00002-of-00008.safetensors: 68%|██████▊ | 1.35G/1.98G [00:03<00:00, 1.17GB/s] model-00002-of-00008.safetensors: 79%|███████▉ | 1.56G/1.98G [00:03<00:00, 674MB/s] model-00002-of-00008.safetensors: 87%|████████▋ | 1.72G/1.98G [00:04<00:00, 740MB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 471MB/s]
inv-elbrus-7b-v1-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.95G [00:01<05:03, 6.38MB/s] model-00003-of-00008.safetensors: 1%| | 21.0M/1.95G [00:02<02:45, 11.6MB/s] model-00003-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:02<00:50, 37.5MB/s] model-00003-of-00008.safetensors: 7%|▋ | 136M/1.95G [00:02<00:18, 96.0MB/s] model-00003-of-00008.safetensors: 9%|▊ | 168M/1.95G [00:02<00:15, 115MB/s] model-00003-of-00008.safetensors: 15%|█▌ | 294M/1.95G [00:02<00:06, 262MB/s] model-00003-of-00008.safetensors: 34%|███▍ | 671M/1.95G [00:02<00:01, 804MB/s] model-00003-of-00008.safetensors: 65%|██████▌ | 1.27G/1.95G [00:03<00:00, 1.57GB/s] model-00003-of-00008.safetensors: 77%|███████▋ | 1.50G/1.95G [00:03<00:00, 946MB/s] model-00003-of-00008.safetensors: 87%|████████▋ | 1.68G/1.95G [00:03<00:00, 1.06GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 519MB/s]
inv-elbrus-7b-v1-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 [00:02<06:40, 4.83MB/s] model-00004-of-00008.safetensors: 4%|▍ | 73.4M/1.95G [00:02<00:46, 40.5MB/s] model-00004-of-00008.safetensors: 9%|▉ | 178M/1.95G [00:02<00:15, 117MB/s] model-00004-of-00008.safetensors: 14%|█▍ | 273M/1.95G [00:02<00:08, 197MB/s] model-00004-of-00008.safetensors: 19%|█▉ | 377M/1.95G [00:02<00:05, 301MB/s] model-00004-of-00008.safetensors: 31%|███ | 598M/1.95G [00:02<00:02, 582MB/s] model-00004-of-00008.safetensors: 56%|█████▌ | 1.09G/1.95G [00:03<00:00, 1.04GB/s] model-00004-of-00008.safetensors: 64%|██████▍ | 1.25G/1.95G [00:03<00:01, 697MB/s] model-00004-of-00008.safetensors: 70%|███████ | 1.36G/1.95G [00:03<00:00, 663MB/s] model-00004-of-00008.safetensors: 75%|███████▌ | 1.46G/1.95G [00:03<00:00, 675MB/s] model-00004-of-00008.safetensors: 80%|████████ | 1.56G/1.95G [00:04<00:00, 612MB/s] model-00004-of-00008.safetensors: 88%|████████▊ | 1.71G/1.95G [00:04<00:00, 736MB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 454MB/s]
inv-elbrus-7b-v1-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 [00:01<04:40, 6.71MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.89G [00:01<02:09, 14.5MB/s] model-00005-of-00008.safetensors: 2%|▏ | 31.5M/1.89G [00:01<01:20, 23.1MB/s] model-00005-of-00008.safetensors: 3%|▎ | 52.4M/1.89G [00:01<00:39, 46.3MB/s] model-00005-of-00008.safetensors: 4%|▍ | 73.4M/1.89G [00:02<00:25, 70.7MB/s] model-00005-of-00008.safetensors: 7%|▋ | 126M/1.89G [00:02<00:12, 137MB/s] model-00005-of-00008.safetensors: 8%|▊ | 157M/1.89G [00:02<00:10, 165MB/s] model-00005-of-00008.safetensors: 13%|█▎ | 241M/1.89G [00:02<00:05, 303MB/s] model-00005-of-00008.safetensors: 20%|█▉ | 377M/1.89G [00:02<00:03, 491MB/s] model-00005-of-00008.safetensors: 24%|██▍ | 451M/1.89G [00:02<00:03, 475MB/s] model-00005-of-00008.safetensors: 43%|████▎ | 818M/1.89G [00:02<00:00, 1.17GB/s] model-00005-of-00008.safetensors: 66%|██████▌ | 1.25G/1.89G [00:02<00:00, 1.82GB/s] model-00005-of-00008.safetensors: 77%|███████▋ | 1.46G/1.89G [00:03<00:00, 1.26GB/s] model-00005-of-00008.safetensors: 86%|████████▌ | 1.63G/1.89G [00:03<00:00, 1.08GB/s] model-00005-of-00008.safetensors: 94%|█████████▍| 1.77G/1.89G [00:03<00:00, 982MB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 506MB/s]
inv-elbrus-7b-v1-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 [00:02<07:11, 4.43MB/s] model-00006-of-00008.safetensors: 2%|▏ | 31.5M/1.92G [00:02<01:57, 16.1MB/s] model-00006-of-00008.safetensors: 12%|█▏ | 231M/1.92G [00:02<00:10, 164MB/s] model-00006-of-00008.safetensors: 17%|█▋ | 336M/1.92G [00:02<00:06, 234MB/s] model-00006-of-00008.safetensors: 22%|██▏ | 430M/1.92G [00:02<00:04, 303MB/s] model-00006-of-00008.safetensors: 27%|██▋ | 514M/1.92G [00:02<00:03, 365MB/s] model-00006-of-00008.safetensors: 61%|██████ | 1.16G/1.92G [00:03<00:00, 1.29GB/s] model-00006-of-00008.safetensors: 72%|███████▏ | 1.39G/1.92G [00:03<00:00, 736MB/s] model-00006-of-00008.safetensors: 84%|████████▎ | 1.61G/1.92G [00:03<00:00, 900MB/s] model-00006-of-00008.safetensors: 93%|█████████▎| 1.80G/1.92G [00:04<00:00, 918MB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:04<00:00, 466MB/s]
inv-elbrus-7b-v1-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 [00:02<07:33, 4.27MB/s] model-00007-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:02<00:17, 102MB/s] model-00007-of-00008.safetensors: 15%|█▌ | 294M/1.95G [00:02<00:10, 163MB/s] model-00007-of-00008.safetensors: 22%|██▏ | 430M/1.95G [00:02<00:05, 271MB/s] model-00007-of-00008.safetensors: 27%|██▋ | 535M/1.95G [00:03<00:04, 318MB/s] model-00007-of-00008.safetensors: 59%|█████▊ | 1.14G/1.95G [00:03<00:00, 936MB/s] model-00007-of-00008.safetensors: 67%|██████▋ | 1.31G/1.95G [00:03<00:00, 767MB/s] model-00007-of-00008.safetensors: 74%|███████▍ | 1.44G/1.95G [00:03<00:00, 665MB/s] model-00007-of-00008.safetensors: 90%|████████▉ | 1.75G/1.95G [00:04<00:00, 953MB/s] model-00007-of-00008.safetensors: 98%|█████████▊| 1.90G/1.95G [00:04<00:00, 1.03GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 469MB/s]
inv-elbrus-7b-v1-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 0%| | 2.13M/872M [00:00<05:53, 2.46MB/s] model-00008-of-00008.safetensors: 1%|▏ | 12.6M/872M [00:01<01:59, 7.17MB/s] model-00008-of-00008.safetensors: 15%|█▍ | 128M/872M [00:02<00:07, 97.3MB/s] model-00008-of-00008.safetensors: 25%|██▌ | 222M/872M [00:02<00:03, 182MB/s] model-00008-of-00008.safetensors: 34%|███▍ | 296M/872M [00:02<00:02, 247MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 369MB/s]
inv-elbrus-7b-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, 161MB/s]
inv-elbrus-7b-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, 5.33MB/s]
inv-elbrus-7b-v1-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 38.1MB/s]
inv-elbrus-7b-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 64.1MB/s]
inv-elbrus-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.18k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.18k/1.18k [00:00<00:00, 18.8MB/s]
inv-elbrus-7b-v1-mkmlizer: Downloaded to shared memory in 35.156s
inv-elbrus-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
inv-elbrus-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-elbrus-7b-v1-mkmlizer: Reading /tmp/tmp1o_9pbcj/model.safetensors.index.json
inv-elbrus-7b-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<01:10, 4.09it/s] Profiling: 6%|▌ | 18/291 [00:00<00:04, 64.13it/s] Profiling: 13%|█▎ | 37/291 [00:00<00:03, 80.57it/s] Profiling: 18%|█▊ | 53/291 [00:00<00:02, 99.20it/s] Profiling: 26%|██▌ | 76/291 [00:00<00:01, 112.40it/s] Profiling: 33%|███▎ | 97/291 [00:00<00:01, 132.17it/s] Profiling: 41%|████ | 118/291 [00:01<00:01, 129.80it/s] Profiling: 48%|████▊ | 139/291 [00:01<00:01, 148.66it/s] Profiling: 55%|█████▍ | 160/291 [00:02<00:03, 38.76it/s] Profiling: 62%|██████▏ | 181/291 [00:02<00:02, 51.99it/s] Profiling: 68%|██████▊ | 197/291 [00:03<00:03, 30.08it/s] Profiling: 74%|███████▍ | 215/291 [00:03<00:01, 39.63it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 47.98it/s] Profiling: 86%|████████▋ | 251/291 [00:04<00:00, 63.07it/s] Profiling: 94%|█████████▍| 274/291 [00:04<00:00, 77.82it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 64.29it/s]
inv-elbrus-7b-v1-mkmlizer: quantized model in 14.798s
inv-elbrus-7b-v1-mkmlizer: Processed model Inv/Elbrus-7B in 50.824s
inv-elbrus-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
inv-elbrus-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-elbrus-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-elbrus-7b-v1
inv-elbrus-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-elbrus-7b-v1/config.json
inv-elbrus-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-elbrus-7b-v1/special_tokens_map.json
inv-elbrus-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-elbrus-7b-v1/tokenizer_config.json
inv-elbrus-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-elbrus-7b-v1/tokenizer.model
inv-elbrus-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-elbrus-7b-v1/tokenizer.json
inv-elbrus-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-elbrus-7b-v1/mkml_model.tensors
inv-elbrus-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-elbrus-7b-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.
inv-elbrus-7b-v1-mkmlizer: warnings.warn(
inv-elbrus-7b-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.4MB/s]
inv-elbrus-7b-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.
inv-elbrus-7b-v1-mkmlizer: warnings.warn(
inv-elbrus-7b-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, 202MB/s] pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:00<00:10, 134MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:04, 295MB/s] pytorch_model.bin: 10%|█ | 147M/1.44G [00:00<00:09, 142MB/s] pytorch_model.bin: 15%|█▌ | 220M/1.44G [00:01<00:05, 233MB/s] pytorch_model.bin: 29%|██▉ | 419M/1.44G [00:01<00:01, 560MB/s] pytorch_model.bin: 75%|███████▌ | 1.09G/1.44G [00:01<00:00, 1.85GB/s] pytorch_model.bin: 96%|█████████▌| 1.38G/1.44G [00:01<00:00, 2.08GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.02GB/s]
inv-elbrus-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-elbrus-7b-v1-mkmlizer: Saving duration: 0.237s
inv-elbrus-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.971s
inv-elbrus-7b-v1-mkmlizer: creating bucket guanaco-reward-models
inv-elbrus-7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-elbrus-7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-elbrus-7b-v1_reward
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/tokenizer_config.json
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/config.json
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/special_tokens_map.json
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/merges.txt
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/vocab.json
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/tokenizer.json
inv-elbrus-7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-elbrus-7b-v1_reward/reward.tensors
Job inv-elbrus-7b-v1-mkmlizer completed after 86.27s with status: succeeded
Stopping job with name inv-elbrus-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service inv-elbrus-7b-v1
Waiting for inference service inv-elbrus-7b-v1 to be ready
Inference service inv-elbrus-7b-v1 ready after 40.38399338722229s
Pipeline stage ISVCDeployer completed in 48.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6793959140777588s
Received healthy response to inference request in 1.183462381362915s
Received healthy response to inference request in 1.0537617206573486s
Received healthy response to inference request in 0.8857302665710449s
Received healthy response to inference request in 0.912132978439331s
5 requests
0 failed requests
5th percentile: 0.8910108089447022
10th percentile: 0.8962913513183594
20th percentile: 0.9068524360656738
30th percentile: 0.9404587268829345
40th percentile: 0.9971102237701416
50th percentile: 1.0537617206573486
60th percentile: 1.105641984939575
70th percentile: 1.1575222492218018
80th percentile: 1.2826490879058838
90th percentile: 1.4810225009918214
95th percentile: 1.58020920753479
99th percentile: 1.659558572769165
mean time: 1.1428966522216797
Pipeline stage StressChecker completed in 6.67s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
inv-elbrus-7b_v1 status is now deployed due to DeploymentManager action
inv-elbrus-7b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics