submission_id: seyf1elislam-kutrix-7b_v1
developer_uid: seyf1elislam
status: torndown
model_repo: seyf1elislam/KuTrix-7b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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}:', 'truncate_by_message': False}
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}:', 'truncate_by_message': False}
timestamp: 2024-04-10T23:27:02+00:00
model_name: seyf1elislam-kutrix-7b_v1
model_eval_status: success
model_group: seyf1elislam/KuTrix-7b
num_battles: 5828
num_wins: 2726
celo_rating: 1140.21
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: seyf1elislam-kutrix-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: seyf1elislam/KuTrix-7b
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-10
win_ratio: 0.46774193548387094
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name seyf1elislam-kutrix-7b-v1-mkmlizer
Waiting for job on seyf1elislam-kutrix-7b-v1-mkmlizer to finish
seyf1elislam-kutrix-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ _____ __ __ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ /___/ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ Version: 0.6.11 ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ belonging to: ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ Chai Research Corp. ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ║ ║
seyf1elislam-kutrix-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
seyf1elislam-kutrix-7b-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.8MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: README.md: 0%| | 0.00/5.13k [00:00<?, ?B/s] README.md: 100%|██████████| 5.13k/5.13k [00:00<00:00, 68.3MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: config.json: 0%| | 0.00/614 [00:00<?, ?B/s] config.json: 100%|██████████| 614/614 [00:00<00:00, 5.49MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: mergekit_config.yml: 0%| | 0.00/386 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 386/386 [00:00<00:00, 5.60MB/s]
seyf1elislam-kutrix-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 [00:00<01:33, 21.1MB/s] model-00001-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:24, 23.0MB/s] model-00001-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:01<01:18, 24.7MB/s] model-00001-of-00008.safetensors: 3%|▎ | 52.4M/1.98G [00:02<01:15, 25.5MB/s] model-00001-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:02<00:58, 33.0MB/s] model-00001-of-00008.safetensors: 5%|▍ | 94.4M/1.98G [00:02<00:27, 67.6MB/s] model-00001-of-00008.safetensors: 7%|▋ | 147M/1.98G [00:02<00:13, 132MB/s] model-00001-of-00008.safetensors: 13%|█▎ | 252M/1.98G [00:02<00:06, 285MB/s] model-00001-of-00008.safetensors: 17%|█▋ | 346M/1.98G [00:02<00:04, 400MB/s] model-00001-of-00008.safetensors: 21%|██ | 409M/1.98G [00:02<00:04, 349MB/s] model-00001-of-00008.safetensors: 34%|███▍ | 682M/1.98G [00:03<00:01, 799MB/s] model-00001-of-00008.safetensors: 59%|█████▉ | 1.16G/1.98G [00:03<00:00, 1.59GB/s] model-00001-of-00008.safetensors: 69%|██████▉ | 1.37G/1.98G [00:03<00:00, 857MB/s] model-00001-of-00008.safetensors: 77%|███████▋ | 1.53G/1.98G [00:03<00:00, 882MB/s] model-00001-of-00008.safetensors: 85%|████████▍ | 1.68G/1.98G [00:03<00:00, 966MB/s] model-00001-of-00008.safetensors: 92%|█████████▏| 1.82G/1.98G [00:04<00:00, 961MB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 473MB/s]
seyf1elislam-kutrix-7b-v1-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 [00:01<05:35, 5.77MB/s] model-00002-of-00008.safetensors: 1%| | 21.0M/1.95G [00:02<02:58, 10.8MB/s] model-00002-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:02<00:54, 34.6MB/s] model-00002-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:02<00:29, 62.6MB/s] model-00002-of-00008.safetensors: 11%|█ | 210M/1.95G [00:02<00:08, 212MB/s] model-00002-of-00008.safetensors: 18%|█▊ | 357M/1.95G [00:02<00:04, 379MB/s] model-00002-of-00008.safetensors: 22%|██▏ | 430M/1.95G [00:02<00:03, 428MB/s] model-00002-of-00008.safetensors: 26%|██▌ | 503M/1.95G [00:02<00:02, 485MB/s] model-00002-of-00008.safetensors: 54%|█████▍ | 1.06G/1.95G [00:03<00:00, 1.38GB/s] model-00002-of-00008.safetensors: 63%|██████▎ | 1.22G/1.95G [00:03<00:00, 853MB/s] model-00002-of-00008.safetensors: 69%|██████▉ | 1.35G/1.95G [00:03<00:00, 903MB/s] model-00002-of-00008.safetensors: 76%|███████▌ | 1.47G/1.95G [00:03<00:00, 820MB/s] model-00002-of-00008.safetensors: 81%|████████ | 1.58G/1.95G [00:03<00:00, 838MB/s] model-00002-of-00008.safetensors: 87%|████████▋ | 1.68G/1.95G [00:04<00:00, 765MB/s] model-00002-of-00008.safetensors: 91%|█████████▏| 1.78G/1.95G [00:04<00:00, 791MB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 459MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.97G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.97G [00:00<02:51, 11.5MB/s] model-00003-of-00008.safetensors: 1%| | 21.0M/1.97G [00:01<01:33, 20.8MB/s] model-00003-of-00008.safetensors: 2%|▏ | 31.5M/1.97G [00:01<01:31, 21.3MB/s] model-00003-of-00008.safetensors: 2%|▏ | 41.9M/1.97G [00:01<01:06, 29.1MB/s] model-00003-of-00008.safetensors: 3%|▎ | 52.4M/1.97G [00:02<01:02, 30.9MB/s] model-00003-of-00008.safetensors: 4%|▎ | 73.4M/1.97G [00:02<00:40, 47.2MB/s] model-00003-of-00008.safetensors: 5%|▌ | 105M/1.97G [00:02<00:22, 83.5MB/s] model-00003-of-00008.safetensors: 7%|▋ | 147M/1.97G [00:02<00:13, 135MB/s] model-00003-of-00008.safetensors: 14%|█▍ | 273M/1.97G [00:02<00:05, 322MB/s] model-00003-of-00008.safetensors: 17%|█▋ | 336M/1.97G [00:02<00:04, 382MB/s] model-00003-of-00008.safetensors: 20%|█▉ | 388M/1.97G [00:02<00:04, 369MB/s] model-00003-of-00008.safetensors: 55%|█████▌ | 1.09G/1.97G [00:03<00:00, 1.82GB/s] model-00003-of-00008.safetensors: 68%|██████▊ | 1.33G/1.97G [00:03<00:00, 1.15GB/s] model-00003-of-00008.safetensors: 77%|███████▋ | 1.52G/1.97G [00:03<00:00, 1.03GB/s] model-00003-of-00008.safetensors: 85%|████████▌ | 1.68G/1.97G [00:03<00:00, 1.03GB/s] model-00003-of-00008.safetensors: 93%|█████████▎| 1.83G/1.97G [00:03<00:00, 1.04GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.97G/1.97G [00:04<00:00, 489MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: model-00004-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00004-of-00008.safetensors: 1%| | 10.5M/1.98G [00:01<05:14, 6.25MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<02:22, 13.7MB/s] model-00004-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:02<01:04, 30.0MB/s] model-00004-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:02<00:42, 44.6MB/s] model-00004-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:02<00:37, 50.8MB/s] model-00004-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:02<00:17, 104MB/s] model-00004-of-00008.safetensors: 10%|█ | 199M/1.98G [00:02<00:07, 228MB/s] model-00004-of-00008.safetensors: 16%|█▌ | 315M/1.98G [00:02<00:04, 373MB/s] model-00004-of-00008.safetensors: 20%|██ | 398M/1.98G [00:02<00:03, 456MB/s] model-00004-of-00008.safetensors: 29%|██▉ | 577M/1.98G [00:02<00:01, 748MB/s] model-00004-of-00008.safetensors: 60%|█████▉ | 1.18G/1.98G [00:03<00:00, 1.87GB/s] model-00004-of-00008.safetensors: 70%|███████ | 1.39G/1.98G [00:03<00:00, 1.07GB/s] model-00004-of-00008.safetensors: 79%|███████▉ | 1.56G/1.98G [00:03<00:00, 979MB/s] model-00004-of-00008.safetensors: 86%|████████▌ | 1.70G/1.98G [00:03<00:00, 969MB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:03<00:00, 500MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.95G [00:01<05:05, 6.34MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.95G [00:01<02:25, 13.3MB/s] model-00005-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:02<01:36, 19.8MB/s] model-00005-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:02<00:36, 51.2MB/s] model-00005-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:02<00:16, 114MB/s] model-00005-of-00008.safetensors: 12%|█▏ | 231M/1.95G [00:02<00:06, 276MB/s] model-00005-of-00008.safetensors: 19%|█▉ | 377M/1.95G [00:02<00:03, 486MB/s] model-00005-of-00008.safetensors: 24%|██▎ | 461M/1.95G [00:02<00:02, 495MB/s] model-00005-of-00008.safetensors: 39%|███▉ | 755M/1.95G [00:02<00:01, 998MB/s] model-00005-of-00008.safetensors: 55%|█████▍ | 1.07G/1.95G [00:02<00:00, 1.39GB/s] model-00005-of-00008.safetensors: 64%|██████▍ | 1.24G/1.95G [00:03<00:00, 755MB/s] model-00005-of-00008.safetensors: 71%|███████ | 1.38G/1.95G [00:03<00:00, 825MB/s] model-00005-of-00008.safetensors: 78%|███████▊ | 1.52G/1.95G [00:03<00:00, 745MB/s] model-00005-of-00008.safetensors: 84%|████████▍ | 1.63G/1.95G [00:03<00:00, 767MB/s] model-00005-of-00008.safetensors: 89%|████████▉ | 1.74G/1.95G [00:03<00:00, 809MB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 477MB/s]
seyf1elislam-kutrix-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 [00:01<03:32, 9.01MB/s] model-00006-of-00008.safetensors: 1%| | 21.0M/1.92G [00:01<02:07, 15.0MB/s] model-00006-of-00008.safetensors: 2%|▏ | 31.5M/1.92G [00:02<02:13, 14.2MB/s] model-00006-of-00008.safetensors: 2%|▏ | 41.9M/1.92G [00:02<01:28, 21.2MB/s] model-00006-of-00008.safetensors: 6%|▌ | 115M/1.92G [00:02<00:19, 93.4MB/s] model-00006-of-00008.safetensors: 13%|█▎ | 241M/1.92G [00:02<00:07, 240MB/s] model-00006-of-00008.safetensors: 17%|█▋ | 325M/1.92G [00:02<00:05, 308MB/s] model-00006-of-00008.safetensors: 21%|██▏ | 409M/1.92G [00:02<00:03, 382MB/s] model-00006-of-00008.safetensors: 39%|███▊ | 744M/1.92G [00:03<00:01, 938MB/s] model-00006-of-00008.safetensors: 57%|█████▋ | 1.10G/1.92G [00:03<00:00, 1.31GB/s] model-00006-of-00008.safetensors: 66%|██████▌ | 1.27G/1.92G [00:03<00:00, 819MB/s] model-00006-of-00008.safetensors: 73%|███████▎ | 1.41G/1.92G [00:03<00:00, 678MB/s] model-00006-of-00008.safetensors: 80%|████████ | 1.55G/1.92G [00:04<00:00, 761MB/s] model-00006-of-00008.safetensors: 86%|████████▋ | 1.66G/1.92G [00:04<00:00, 790MB/s] model-00006-of-00008.safetensors: 93%|█████████▎| 1.80G/1.92G [00:04<00:00, 894MB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:04<00:00, 439MB/s]
seyf1elislam-kutrix-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 [00:00<01:02, 31.1MB/s] model-00007-of-00008.safetensors: 1%| | 21.0M/1.95G [00:01<02:17, 14.0MB/s] model-00007-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:02<02:33, 12.5MB/s] model-00007-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:02<01:16, 24.7MB/s] model-00007-of-00008.safetensors: 8%|▊ | 157M/1.95G [00:02<00:15, 113MB/s] model-00007-of-00008.safetensors: 13%|█▎ | 262M/1.95G [00:02<00:07, 211MB/s] model-00007-of-00008.safetensors: 17%|█▋ | 325M/1.95G [00:02<00:06, 258MB/s] model-00007-of-00008.safetensors: 20%|██ | 398M/1.95G [00:02<00:04, 331MB/s] model-00007-of-00008.safetensors: 36%|███▌ | 692M/1.95G [00:03<00:01, 801MB/s] model-00007-of-00008.safetensors: 61%|██████ | 1.18G/1.95G [00:03<00:00, 1.62GB/s] model-00007-of-00008.safetensors: 73%|███████▎ | 1.42G/1.95G [00:03<00:00, 831MB/s] model-00007-of-00008.safetensors: 82%|████████▏ | 1.59G/1.95G [00:03<00:00, 920MB/s] model-00007-of-00008.safetensors: 90%|█████████ | 1.76G/1.95G [00:04<00:00, 930MB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 460MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/789M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%|▏ | 10.5M/789M [00:00<01:09, 11.1MB/s] model-00008-of-00008.safetensors: 3%|▎ | 23.1M/789M [00:01<00:48, 15.7MB/s] model-00008-of-00008.safetensors: 6%|▌ | 44.1M/789M [00:01<00:22, 33.5MB/s] model-00008-of-00008.safetensors: 7%|▋ | 54.6M/789M [00:01<00:18, 40.4MB/s] model-00008-of-00008.safetensors: 15%|█▍ | 117M/789M [00:01<00:05, 122MB/s] model-00008-of-00008.safetensors: 40%|████ | 317M/789M [00:02<00:01, 432MB/s] model-00008-of-00008.safetensors: 51%|█████ | 401M/789M [00:02<00:00, 465MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 789M/789M [00:02<00:00, 338MB/s]
seyf1elislam-kutrix-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, 156MB/s]
seyf1elislam-kutrix-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, 4.46MB/s]
seyf1elislam-kutrix-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, 19.1MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 62.9MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/916 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 916/916 [00:00<00:00, 11.9MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: Downloaded to shared memory in 35.395s
seyf1elislam-kutrix-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
seyf1elislam-kutrix-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
seyf1elislam-kutrix-7b-v1-mkmlizer: Reading /tmp/tmplln_mhnp/model.safetensors.index.json
seyf1elislam-kutrix-7b-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:35, 8.19it/s] Profiling: 3%|▎ | 9/291 [00:00<00:06, 44.71it/s] Profiling: 7%|▋ | 21/291 [00:00<00:03, 73.57it/s] Profiling: 11%|█ | 31/291 [00:00<00:03, 83.01it/s] Profiling: 14%|█▎ | 40/291 [00:00<00:03, 64.87it/s] Profiling: 17%|█▋ | 50/291 [00:00<00:03, 74.03it/s] Profiling: 22%|██▏ | 63/291 [00:00<00:02, 88.91it/s] Profiling: 26%|██▋ | 77/291 [00:00<00:02, 102.46it/s] Profiling: 30%|███ | 88/291 [00:02<00:09, 21.67it/s] Profiling: 34%|███▍ | 100/291 [00:02<00:06, 29.17it/s] Profiling: 38%|███▊ | 110/291 [00:02<00:05, 36.19it/s] Profiling: 41%|████ | 120/291 [00:02<00:04, 41.74it/s] Profiling: 44%|████▍ | 129/291 [00:02<00:03, 48.63it/s] Profiling: 48%|████▊ | 141/291 [00:02<00:02, 60.75it/s] Profiling: 52%|█████▏ | 152/291 [00:03<00:02, 67.67it/s] Profiling: 56%|█████▌ | 162/291 [00:03<00:02, 64.18it/s] Profiling: 61%|██████ | 177/291 [00:03<00:01, 80.11it/s] Profiling: 65%|██████▍ | 188/291 [00:03<00:01, 81.89it/s] Profiling: 69%|██████▉ | 201/291 [00:04<00:04, 22.15it/s] Profiling: 72%|███████▏ | 209/291 [00:05<00:03, 26.12it/s] Profiling: 75%|███████▌ | 219/291 [00:05<00:02, 32.85it/s] Profiling: 81%|████████ | 235/291 [00:05<00:01, 43.04it/s] Profiling: 84%|████████▍ | 245/291 [00:05<00:00, 49.80it/s] Profiling: 88%|████████▊ | 255/291 [00:05<00:00, 57.36it/s] Profiling: 91%|█████████▏| 266/291 [00:05<00:00, 66.86it/s] Profiling: 96%|█████████▌| 278/291 [00:05<00:00, 69.96it/s] Profiling: 99%|█████████▊| 287/291 [00:05<00:00, 69.02it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 48.29it/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: quantized model in 17.307s
seyf1elislam-kutrix-7b-v1-mkmlizer: Processed model seyf1elislam/KuTrix-7b in 53.635s
seyf1elislam-kutrix-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
seyf1elislam-kutrix-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
seyf1elislam-kutrix-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1/tokenizer.model
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1/config.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1/tokenizer.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1/special_tokens_map.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1/tokenizer_config.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/seyf1elislam-kutrix-7b-v1/mkml_model.tensors
seyf1elislam-kutrix-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
seyf1elislam-kutrix-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.
seyf1elislam-kutrix-7b-v1-mkmlizer: warnings.warn(
seyf1elislam-kutrix-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, 12.5MB/s]
seyf1elislam-kutrix-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.
seyf1elislam-kutrix-7b-v1-mkmlizer: warnings.warn(
seyf1elislam-kutrix-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.34MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 11.2MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.9MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.8MB/s]
seyf1elislam-kutrix-7b-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.
seyf1elislam-kutrix-7b-v1-mkmlizer: warnings.warn(
seyf1elislam-kutrix-7b-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:04, 291MB/s] pytorch_model.bin: 4%|▍ | 62.9M/1.44G [00:00<00:13, 99.0MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:13, 99.8MB/s] pytorch_model.bin: 8%|▊ | 115M/1.44G [00:01<00:12, 103MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:01<00:09, 138MB/s] pytorch_model.bin: 23%|██▎ | 325M/1.44G [00:01<00:02, 402MB/s] pytorch_model.bin: 58%|█████▊ | 839M/1.44G [00:01<00:00, 1.34GB/s] pytorch_model.bin: 81%|████████ | 1.16G/1.44G [00:01<00:00, 1.74GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 855MB/s]
seyf1elislam-kutrix-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
seyf1elislam-kutrix-7b-v1-mkmlizer: Saving duration: 0.294s
seyf1elislam-kutrix-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.427s
seyf1elislam-kutrix-7b-v1-mkmlizer: creating bucket guanaco-reward-models
seyf1elislam-kutrix-7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
seyf1elislam-kutrix-7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/config.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/tokenizer_config.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/special_tokens_map.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/vocab.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/merges.txt
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/tokenizer.json
seyf1elislam-kutrix-7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/seyf1elislam-kutrix-7b-v1_reward/reward.tensors
Job seyf1elislam-kutrix-7b-v1-mkmlizer completed after 87.47s with status: succeeded
Stopping job with name seyf1elislam-kutrix-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 92.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service seyf1elislam-kutrix-7b-v1
Failed to get response for submission arlineka-nyan-test-esp1_v1: ('http://arlineka-nyan-test-esp1-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38418->127.0.0.1:8080: read: connection reset by peer\n')
Waiting for inference service seyf1elislam-kutrix-7b-v1 to be ready
Inference service seyf1elislam-kutrix-7b-v1 ready after 40.44210600852966s
Pipeline stage ISVCDeployer completed in 48.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4925084114074707s
Received healthy response to inference request in 0.710756778717041s
Received healthy response to inference request in 1.1038568019866943s
Received healthy response to inference request in 1.1030046939849854s
Received healthy response to inference request in 1.0920188426971436s
5 requests
0 failed requests
5th percentile: 0.7870091915130615
10th percentile: 0.863261604309082
20th percentile: 1.015766429901123
30th percentile: 1.0942160129547118
40th percentile: 1.0986103534698486
50th percentile: 1.1030046939849854
60th percentile: 1.1033455371856689
70th percentile: 1.1036863803863526
80th percentile: 1.1815871238708497
90th percentile: 1.3370477676391601
95th percentile: 1.4147780895233153
99th percentile: 1.4769623470306397
mean time: 1.100429105758667
Pipeline stage StressChecker completed in 6.34s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.08s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.08s
seyf1elislam-kutrix-7b_v1 status is now deployed due to DeploymentManager action
seyf1elislam-kutrix-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of seyf1elislam-kutrix-7b_v1
Running pipeline stage ISVCDeleter
Checking if service seyf1elislam-kutrix-7b-v1 is running
Tearing down inference service seyf1elislam-kutrix-7b-v1
Toredown service seyf1elislam-kutrix-7b-v1
Pipeline stage ISVCDeleter completed in 4.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key seyf1elislam-kutrix-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key seyf1elislam-kutrix-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key seyf1elislam-kutrix-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key seyf1elislam-kutrix-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key seyf1elislam-kutrix-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key seyf1elislam-kutrix-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key seyf1elislam-kutrix-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key seyf1elislam-kutrix-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key seyf1elislam-kutrix-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key seyf1elislam-kutrix-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key seyf1elislam-kutrix-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key seyf1elislam-kutrix-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key seyf1elislam-kutrix-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.41s
seyf1elislam-kutrix-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics