submission_id: thanhdaonguyen-once-upon-a-t_v21
developer_uid: robert_irvine
status: deployed
model_repo: thanhdaonguyen/once-upon-a-time
reward_repo: rirv938/reward_gpt2_preference_24m_e2
generation_params: {'temperature': 0.72, 'top_p': 0.73, 'top_k': 1000, 'presence_penalty': 0.7, 'frequency_penalty': 0.3, 'stopping_words': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\n\n{bot_name}'s Persona: {memory}.\n\nPlay the role of {bot_name}. Engage in a chat with {user_name} while stay in character. Do not write dialogues and narration for {user_name}. {bot_name} should response with engaging messages of medium length that encourage responses.", 'prompt_template': '{prompt}\n\n', 'bot_template': '### Response:\n\n{bot_name}: {message}\n\n', 'user_template': '### Input:\n\n{user_name}: {message}\n\n', 'response_template': '### Response:\n\n{bot_name}:'}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:'}
timestamp: 2024-02-13T22:03:46+00:00
model_name: thanhdaonguyen-once-upon-a-t_v21
model_eval_status: success
safety_score: 0.94
entertaining: 6.96
stay_in_character: 8.65
user_preference: 7.48
double_thumbs_up: 4117
thumbs_up: 6040
thumbs_down: 2717
num_battles: 183402
num_wins: 91711
win_ratio: 0.5000545250324424
celo_rating: 1153.7
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thanhdaonguyen-once-upon-a-t-v21-mkmlizer
Waiting for job on thanhdaonguyen-once-upon-a-t-v21-mkmlizer to finish
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ _____ __ __ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ /___/ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ Version: 0.6.11 ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ The license key for the current software has been verified as ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ belonging to: ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ Chai Research Corp. ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.9MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: added_tokens.json: 0%| | 0.00/21.0 [00:00<?, ?B/s] added_tokens.json: 100%|██████████| 21.0/21.0 [00:00<00:00, 350kB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 6.38MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: generation_config.json: 0%| | 0.00/154 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 154/154 [00:00<00:00, 2.53MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/9.95G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 10.5M/9.95G [00:00<07:03, 23.5MB/s] pytorch_model-00001-of-00003.bin: 0%| | 41.9M/9.95G [00:00<01:58, 83.8MB/s] pytorch_model-00001-of-00003.bin: 1%| | 115M/9.95G [00:00<00:41, 235MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 283M/9.95G [00:00<00:16, 588MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 419M/9.95G [00:00<00:12, 790MB/s] pytorch_model-00001-of-00003.bin: 5%|▌ | 524M/9.95G [00:01<00:12, 768MB/s] pytorch_model-00001-of-00003.bin: 6%|▋ | 640M/9.95G [00:01<00:10, 862MB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 744M/9.95G [00:01<00:13, 677MB/s] pytorch_model-00001-of-00003.bin: 8%|▊ | 828M/9.95G [00:01<00:13, 655MB/s] pytorch_model-00001-of-00003.bin: 9%|▉ | 944M/9.95G [00:01<00:12, 735MB/s] pytorch_model-00001-of-00003.bin: 11%|█▏ | 1.12G/9.95G [00:01<00:09, 967MB/s] pytorch_model-00001-of-00003.bin: 13%|█▎ | 1.27G/9.95G [00:01<00:07, 1.09GB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 1.39G/9.95G [00:02<00:08, 975MB/s] pytorch_model-00001-of-00003.bin: 15%|█▌ | 1.51G/9.95G [00:02<00:11, 704MB/s] pytorch_model-00001-of-00003.bin: 16%|█▌ | 1.60G/9.95G [00:02<00:11, 704MB/s] pytorch_model-00001-of-00003.bin: 17%|█▋ | 1.73G/9.95G [00:02<00:10, 806MB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.82G/9.95G [00:02<00:10, 810MB/s] pytorch_model-00001-of-00003.bin: 20%|██ | 1.99G/9.95G [00:02<00:08, 956MB/s] pytorch_model-00001-of-00003.bin: 21%|██ | 2.10G/9.95G [00:02<00:09, 792MB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 2.19G/9.95G [00:03<00:10, 766MB/s] pytorch_model-00001-of-00003.bin: 23%|██▎ | 2.33G/9.95G [00:03<00:08, 864MB/s] pytorch_model-00001-of-00003.bin: 24%|██▍ | 2.42G/9.95G [00:03<00:10, 738MB/s] pytorch_model-00001-of-00003.bin: 25%|██▌ | 2.51G/9.95G [00:03<00:13, 560MB/s] pytorch_model-00001-of-00003.bin: 27%|██▋ | 2.69G/9.95G [00:03<00:09, 805MB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.80G/9.95G [00:03<00:09, 735MB/s] pytorch_model-00001-of-00003.bin: 29%|██▉ | 2.89G/9.95G [00:04<00:18, 386MB/s] pytorch_model-00001-of-00003.bin: 30%|██▉ | 2.97G/9.95G [00:04<00:18, 376MB/s] pytorch_model-00001-of-00003.bin: 30%|███ | 3.03G/9.95G [00:05<00:20, 333MB/s] pytorch_model-00001-of-00003.bin: 31%|███ | 3.08G/9.95G [00:05<00:26, 256MB/s] pytorch_model-00001-of-00003.bin: 31%|███▏ | 3.12G/9.95G [00:05<00:24, 275MB/s] pytorch_model-00001-of-00003.bin: 32%|███▏ | 3.18G/9.95G [00:05<00:23, 290MB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.24G/9.95G [00:05<00:19, 341MB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.29G/9.95G [00:05<00:17, 371MB/s] pytorch_model-00001-of-00003.bin: 34%|███▎ | 3.34G/9.95G [00:06<00:25, 262MB/s] pytorch_model-00001-of-00003.bin: 34%|███▍ | 3.39G/9.95G [00:06<00:27, 237MB/s] pytorch_model-00001-of-00003.bin: 34%|███▍ | 3.42G/9.95G [00:06<00:28, 229MB/s] pytorch_model-00001-of-00003.bin: 35%|███▍ | 3.45G/9.95G [00:06<00:27, 239MB/s] pytorch_model-00001-of-00003.bin: 35%|███▍ | 3.48G/9.95G [00:06<00:26, 243MB/s] pytorch_model-00001-of-00003.bin: 35%|███▌ | 3.51G/9.95G [00:07<00:36, 178MB/s] pytorch_model-00001-of-00003.bin: 36%|███▌ | 3.54G/9.95G [00:07<00:39, 164MB/s] pytorch_model-00001-of-00003.bin: 36%|███▌ | 3.60G/9.95G [00:07<00:32, 193MB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 3.65G/9.95G [00:07<00:27, 231MB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 3.68G/9.95G [00:07<00:30, 203MB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 3.71G/9.95G [00:08<00:29, 214MB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.74G/9.95G [00:08<00:40, 154MB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.80G/9.95G [00:08<00:32, 190MB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.83G/9.95G [00:08<00:31, 194MB/s] pytorch_model-00001-of-00003.bin: 39%|███▉ | 3.87G/9.95G [00:08<00:27, 223MB/s] pytorch_model-00001-of-00003.bin: 39%|███▉ | 3.90G/9.95G [00:09<00:32, 187MB/s] pytorch_model-00001-of-00003.bin: 40%|███▉ | 3.94G/9.95G [00:09<00:26, 228MB/s] pytorch_model-00001-of-00003.bin: 40%|███▉ | 3.97G/9.95G [00:09<00:24, 243MB/s] pytorch_model-00001-of-00003.bin: 40%|████ | 4.01G/9.95G [00:09<00:28, 208MB/s] pytorch_model-00001-of-00003.bin: 41%|████ | 4.04G/9.95G [00:09<00:26, 225MB/s] pytorch_model-00001-of-00003.bin: 41%|████ | 4.09G/9.95G [00:09<00:21, 273MB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 4.19G/9.95G [00:09<00:12, 445MB/s] pytorch_model-00001-of-00003.bin: 43%|████▎ | 4.25G/9.95G [00:10<00:12, 446MB/s] pytorch_model-00001-of-00003.bin: 44%|████▎ | 4.33G/9.95G [00:10<00:11, 497MB/s] pytorch_model-00001-of-00003.bin: 45%|████▍ | 4.44G/9.95G [00:10<00:09, 612MB/s] pytorch_model-00001-of-00003.bin: 45%|████▌ | 4.51G/9.95G [00:10<00:09, 569MB/s] pytorch_model-00001-of-00003.bin: 46%|████▋ | 4.62G/9.95G [00:10<00:08, 625MB/s] pytorch_model-00001-of-00003.bin: 47%|████▋ | 4.72G/9.95G [00:10<00:07, 690MB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 4.79G/9.95G [00:10<00:08, 621MB/s] pytorch_model-00001-of-00003.bin: 49%|████▉ | 4.90G/9.95G [00:10<00:07, 703MB/s] pytorch_model-00001-of-00003.bin: 50%|█████ | 4.98G/9.95G [00:11<00:06, 727MB/s] pytorch_model-00001-of-00003.bin: 51%|█████▏ | 5.11G/9.95G [00:11<00:05, 848MB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 5.24G/9.95G [00:11<00:05, 918MB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 5.36G/9.95G [00:11<00:04, 964MB/s] pytorch_model-00001-of-00003.bin: 55%|█████▍ | 5.46G/9.95G [00:11<00:04, 968MB/s] pytorch_model-00001-of-00003.bin: 57%|█████▋ | 5.64G/9.95G [00:11<00:03, 1.18GB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 5.77G/9.95G [00:11<00:03, 1.20GB/s] pytorch_model-00001-of-00003.bin: 60%|█████▉ | 5.92G/9.95G [00:11<00:03, 1.27GB/s] pytorch_model-00001-of-00003.bin: 61%|██████ | 6.06G/9.95G [00:11<00:03, 1.19GB/s] pytorch_model-00001-of-00003.bin: 63%|██████▎ | 6.28G/9.95G [00:12<00:02, 1.45GB/s] pytorch_model-00001-of-00003.bin: 65%|██████▍ | 6.44G/9.95G [00:12<00:02, 1.37GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▌ | 6.59G/9.95G [00:12<00:02, 1.36GB/s] pytorch_model-00001-of-00003.bin: 68%|██████▊ | 6.78G/9.95G [00:12<00:02, 1.52GB/s] pytorch_model-00001-of-00003.bin: 70%|██████▉ | 6.94G/9.95G [00:12<00:02, 1.42GB/s] pytorch_model-00001-of-00003.bin: 71%|███████ | 7.09G/9.95G [00:12<00:02, 1.39GB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 7.31G/9.95G [00:12<00:01, 1.59GB/s] pytorch_model-00001-of-00003.bin: 75%|███████▌ | 7.49G/9.95G [00:12<00:01, 1.64GB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 7.70G/9.95G [00:12<00:01, 1.74GB/s] pytorch_model-00001-of-00003.bin: 79%|███████▉ | 7.87G/9.95G [00:13<00:01, 1.52GB/s] pytorch_model-00001-of-00003.bin: 81%|████████▏ | 8.08G/9.95G [00:13<00:01, 1.66GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 8.30G/9.95G [00:13<00:00, 1.79GB/s] pytorch_model-00001-of-00003.bin: 85%|████████▌ | 8.49G/9.95G [00:13<00:00, 1.64GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 8.67G/9.95G [00:13<00:01, 1.24GB/s] pytorch_model-00001-of-00003.bin: 90%|████████▉ | 8.92G/9.95G [00:13<00:00, 1.46GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.24G/9.95G [00:13<00:00, 1.84GB/s] pytorch_model-00001-of-00003.bin: 95%|█████████▌| 9.50G/9.95G [00:14<00:00, 1.99GB/s] pytorch_model-00001-of-00003.bin: 98%|█████████▊| 9.72G/9.95G [00:14<00:00, 1.52GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.91G/9.95G [00:14<00:00, 698MB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.94G/9.95G [01:04<00:00, 698MB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [01:04<00:00, 11.2MB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [01:04<00:00, 154MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: pytorch_model-00002-of-00003.bin: 0%| | 0.00/9.90G [00:00<?, ?B/s] pytorch_model-00002-of-00003.bin: 0%| | 10.5M/9.90G [00:00<09:59, 16.5MB/s] pytorch_model-00002-of-00003.bin: 1%| | 83.9M/9.90G [00:00<01:12, 135MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 189M/9.90G [00:00<00:31, 310MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 262M/9.90G [00:01<00:27, 353MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 336M/9.90G [00:01<00:22, 429MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 398M/9.90G [00:01<00:25, 371MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 472M/9.90G [00:01<00:21, 433MB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 587M/9.90G [00:01<00:16, 575MB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 724M/9.90G [00:01<00:12, 759MB/s] pytorch_model-00002-of-00003.bin: 9%|▊ | 860M/9.90G [00:01<00:10, 884MB/s] pytorch_model-00002-of-00003.bin: 10%|▉ | 965M/9.90G [00:01<00:11, 811MB/s] pytorch_model-00002-of-00003.bin: 11%|█ | 1.06G/9.90G [00:02<00:11, 767MB/s] pytorch_model-00002-of-00003.bin: 12%|█▏ | 1.14G/9.90G [00:02<00:15, 582MB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 1.28G/9.90G [00:02<00:12, 718MB/s] pytorch_model-00002-of-00003.bin: 14%|█▍ | 1.36G/9.90G [00:02<00:11, 729MB/s] pytorch_model-00002-of-00003.bin: 15%|█▍ | 1.45G/9.90G [00:02<00:13, 650MB/s] pytorch_model-00002-of-00003.bin: 15%|█▌ | 1.52G/9.90G [00:02<00:14, 579MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.64G/9.90G [00:03<00:12, 687MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.72G/9.90G [00:03<00:13, 597MB/s] pytorch_model-00002-of-00003.bin: 18%|█▊ | 1.79G/9.90G [00:03<00:13, 591MB/s] pytorch_model-00002-of-00003.bin: 19%|█▉ | 1.91G/9.90G [00:03<00:12, 627MB/s] pytorch_model-00002-of-00003.bin: 20%|██ | 1.99G/9.90G [00:03<00:12, 654MB/s] pytorch_model-00002-of-00003.bin: 21%|██ | 2.09G/9.90G [00:03<00:10, 717MB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 2.17G/9.90G [00:03<00:10, 715MB/s] pytorch_model-00002-of-00003.bin: 23%|██▎ | 2.25G/9.90G [00:04<00:13, 557MB/s] pytorch_model-00002-of-00003.bin: 24%|██▎ | 2.35G/9.90G [00:04<00:11, 630MB/s] pytorch_model-00002-of-00003.bin: 24%|██▍ | 2.42G/9.90G [00:04<00:12, 611MB/s] pytorch_model-00002-of-00003.bin: 25%|██▌ | 2.50G/9.90G [00:04<00:12, 585MB/s] pytorch_model-00002-of-00003.bin: 27%|██▋ | 2.63G/9.90G [00:04<00:09, 747MB/s] pytorch_model-00002-of-00003.bin: 28%|██▊ | 2.75G/9.90G [00:04<00:08, 824MB/s] pytorch_model-00002-of-00003.bin: 29%|██▉ | 2.90G/9.90G [00:04<00:06, 1.01GB/s] pytorch_model-00002-of-00003.bin: 31%|███ | 3.06G/9.90G [00:04<00:06, 1.14GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.24G/9.90G [00:04<00:05, 1.31GB/s] pytorch_model-00002-of-00003.bin: 34%|███▍ | 3.39G/9.90G [00:05<00:04, 1.32GB/s] pytorch_model-00002-of-00003.bin: 36%|███▌ | 3.59G/9.90G [00:05<00:04, 1.47GB/s] pytorch_model-00002-of-00003.bin: 39%|███▊ | 3.84G/9.90G [00:05<00:03, 1.75GB/s] pytorch_model-00002-of-00003.bin: 41%|████ | 4.03G/9.90G [00:05<00:06, 874MB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 4.17G/9.90G [00:05<00:06, 954MB/s] pytorch_model-00002-of-00003.bin: 44%|████▎ | 4.31G/9.90G [00:06<00:05, 989MB/s] pytorch_model-00002-of-00003.bin: 45%|████▍ | 4.45G/9.90G [00:06<00:06, 868MB/s] pytorch_model-00002-of-00003.bin: 46%|████▌ | 4.56G/9.90G [00:06<00:05, 920MB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 4.68G/9.90G [00:06<00:05, 930MB/s] pytorch_model-00002-of-00003.bin: 48%|████▊ | 4.79G/9.90G [00:06<00:06, 805MB/s] pytorch_model-00002-of-00003.bin: 49%|████▉ | 4.89G/9.90G [00:06<00:06, 754MB/s] pytorch_model-00002-of-00003.bin: 50%|█████ | 4.97G/9.90G [00:06<00:07, 649MB/s] pytorch_model-00002-of-00003.bin: 51%|█████▏ | 5.09G/9.90G [00:07<00:06, 735MB/s] pytorch_model-00002-of-00003.bin: 53%|█████▎ | 5.22G/9.90G [00:07<00:05, 861MB/s] pytorch_model-00002-of-00003.bin: 54%|█████▍ | 5.33G/9.90G [00:07<00:06, 662MB/s] pytorch_model-00002-of-00003.bin: 55%|█████▍ | 5.42G/9.90G [00:07<00:06, 693MB/s] pytorch_model-00002-of-00003.bin: 56%|█████▌ | 5.51G/9.90G [00:07<00:06, 699MB/s] pytorch_model-00002-of-00003.bin: 57%|█████▋ | 5.60G/9.90G [00:07<00:05, 747MB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 5.75G/9.90G [00:07<00:04, 922MB/s] pytorch_model-00002-of-00003.bin: 60%|██████ | 5.95G/9.90G [00:08<00:03, 1.18GB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 6.11G/9.90G [00:08<00:03, 1.18GB/s] pytorch_model-00002-of-00003.bin: 63%|██████▎ | 6.24G/9.90G [00:08<00:03, 958MB/s] pytorch_model-00002-of-00003.bin: 64%|██████▍ | 6.35G/9.90G [00:08<00:04, 725MB/s] pytorch_model-00002-of-00003.bin: 65%|██████▌ | 6.45G/9.90G [00:08<00:04, 696MB/s] pytorch_model-00002-of-00003.bin: 66%|██████▋ | 6.57G/9.90G [00:08<00:04, 737MB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 6.71G/9.90G [00:09<00:04, 772MB/s] pytorch_model-00002-of-00003.bin: 69%|██████▊ | 6.79G/9.90G [00:09<00:04, 716MB/s] pytorch_model-00002-of-00003.bin: 69%|██████▉ | 6.88G/9.90G [00:09<00:04, 692MB/s] pytorch_model-00002-of-00003.bin: 71%|███████ | 7.05G/9.90G [00:09<00:03, 904MB/s] pytorch_model-00002-of-00003.bin: 73%|███████▎ | 7.25G/9.90G [00:09<00:02, 1.16GB/s] pytorch_model-00002-of-00003.bin: 75%|███████▍ | 7.40G/9.90G [00:09<00:02, 1.10GB/s] pytorch_model-00002-of-00003.bin: 76%|███████▌ | 7.53G/9.90G [00:10<00:02, 795MB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.63G/9.90G [00:10<00:03, 722MB/s] pytorch_model-00002-of-00003.bin: 78%|███████▊ | 7.73G/9.90G [00:10<00:03, 678MB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 7.81G/9.90G [00:10<00:03, 685MB/s] pytorch_model-00002-of-00003.bin: 80%|████████ | 7.95G/9.90G [00:10<00:02, 822MB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 8.11G/9.90G [00:10<00:01, 974MB/s] pytorch_model-00002-of-00003.bin: 83%|████████▎ | 8.22G/9.90G [00:10<00:02, 818MB/s] pytorch_model-00002-of-00003.bin: 84%|████████▍ | 8.34G/9.90G [00:11<00:01, 864MB/s] pytorch_model-00002-of-00003.bin: 85%|████████▌ | 8.44G/9.90G [00:11<00:01, 801MB/s] pytorch_model-00002-of-00003.bin: 87%|████████▋ | 8.58G/9.90G [00:11<00:01, 848MB/s] pytorch_model-00002-of-00003.bin: 88%|████████▊ | 8.72G/9.90G [00:11<00:01, 930MB/s] pytorch_model-00002-of-00003.bin: 89%|████████▉ | 8.85G/9.90G [00:11<00:01, 978MB/s] pytorch_model-00002-of-00003.bin: 90%|█████████ | 8.95G/9.90G [00:11<00:01, 787MB/s] pytorch_model-00002-of-00003.bin: 92%|█████████▏| 9.08G/9.90G [00:11<00:00, 879MB/s] pytorch_model-00002-of-00003.bin: 93%|█████████▎| 9.21G/9.90G [00:11<00:00, 971MB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▍| 9.34G/9.90G [00:12<00:00, 1.03GB/s] pytorch_model-00002-of-00003.bin: 95%|█████████▌| 9.45G/9.90G [00:12<00:00, 1.05GB/s] pytorch_model-00002-of-00003.bin: 97%|█████████▋| 9.57G/9.90G [00:12<00:00, 905MB/s] pytorch_model-00002-of-00003.bin: 98%|█████████▊| 9.67G/9.90G [00:12<00:00, 909MB/s] pytorch_model-00002-of-00003.bin: 99%|█████████▊| 9.78G/9.90G [00:12<00:00, 845MB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.87G/9.90G [00:13<00:00, 259MB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:14<00:00, 701MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: pytorch_model-00003-of-00003.bin: 0%| | 0.00/6.18G [00:00<?, ?B/s] pytorch_model-00003-of-00003.bin: 0%| | 10.5M/6.18G [00:00<03:34, 28.7MB/s] pytorch_model-00003-of-00003.bin: 0%| | 21.0M/6.18G [00:00<02:24, 42.5MB/s] pytorch_model-00003-of-00003.bin: 1%| | 62.9M/6.18G [00:00<00:44, 137MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 105M/6.18G [00:00<00:31, 190MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 178M/6.18G [00:00<00:19, 309MB/s] pytorch_model-00003-of-00003.bin: 5%|▌ | 336M/6.18G [00:01<00:09, 625MB/s] pytorch_model-00003-of-00003.bin: 10%|█ | 629M/6.18G [00:01<00:04, 1.22GB/s] pytorch_model-00003-of-00003.bin: 16%|█▌ | 986M/6.18G [00:01<00:02, 1.81GB/s] pytorch_model-00003-of-00003.bin: 19%|█▉ | 1.20G/6.18G [00:01<00:03, 1.61GB/s] pytorch_model-00003-of-00003.bin: 22%|██▏ | 1.38G/6.18G [00:01<00:04, 997MB/s] pytorch_model-00003-of-00003.bin: 25%|██▍ | 1.53G/6.18G [00:02<00:05, 812MB/s] pytorch_model-00003-of-00003.bin: 28%|██▊ | 1.75G/6.18G [00:02<00:04, 1.03GB/s] pytorch_model-00003-of-00003.bin: 34%|███▎ | 2.08G/6.18G [00:02<00:02, 1.43GB/s] pytorch_model-00003-of-00003.bin: 39%|███▊ | 2.38G/6.18G [00:02<00:02, 1.67GB/s] pytorch_model-00003-of-00003.bin: 42%|████▏ | 2.59G/6.18G [00:02<00:02, 1.61GB/s] pytorch_model-00003-of-00003.bin: 45%|████▌ | 2.79G/6.18G [00:02<00:02, 1.62GB/s] pytorch_model-00003-of-00003.bin: 48%|████▊ | 2.99G/6.18G [00:02<00:01, 1.67GB/s] pytorch_model-00003-of-00003.bin: 51%|█████▏ | 3.18G/6.18G [00:02<00:02, 1.47GB/s] pytorch_model-00003-of-00003.bin: 54%|█████▍ | 3.34G/6.18G [00:03<00:02, 1.41GB/s] pytorch_model-00003-of-00003.bin: 57%|█████▋ | 3.52G/6.18G [00:03<00:01, 1.49GB/s] pytorch_model-00003-of-00003.bin: 61%|██████▏ | 3.80G/6.18G [00:03<00:01, 1.78GB/s] pytorch_model-00003-of-00003.bin: 65%|██████▍ | 4.02G/6.18G [00:03<00:01, 1.84GB/s] pytorch_model-00003-of-00003.bin: 68%|██████▊ | 4.22G/6.18G [00:03<00:01, 1.84GB/s] pytorch_model-00003-of-00003.bin: 71%|███████▏ | 4.41G/6.18G [00:03<00:01, 1.76GB/s] pytorch_model-00003-of-00003.bin: 74%|███████▍ | 4.60G/6.18G [00:03<00:00, 1.75GB/s] pytorch_model-00003-of-00003.bin: 77%|███████▋ | 4.78G/6.18G [00:03<00:00, 1.75GB/s] pytorch_model-00003-of-00003.bin: 81%|████████ | 4.98G/6.18G [00:03<00:00, 1.76GB/s] pytorch_model-00003-of-00003.bin: 83%|████████▎ | 5.16G/6.18G [00:04<00:00, 1.70GB/s] pytorch_model-00003-of-00003.bin: 86%|████████▋ | 5.34G/6.18G [00:04<00:00, 1.66GB/s] pytorch_model-00003-of-00003.bin: 90%|█████████ | 5.59G/6.18G [00:04<00:00, 1.87GB/s] pytorch_model-00003-of-00003.bin: 98%|█████████▊| 6.08G/6.18G [00:04<00:00, 2.00GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:05<00:00, 1.21GB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/29.9k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 29.9k/29.9k [00:00<00:00, 8.98MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: special_tokens_map.json: 0%| | 0.00/438 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 438/438 [00:00<00:00, 6.93MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 13.5MB/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 13.4MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 5.73MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: tokenizer_config.json: 0%| | 0.00/828 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 828/828 [00:00<00:00, 5.10MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Downloaded to shared memory in 87.499s
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: quantizing model to /dev/shm/model_cache
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Saving mkml model at /dev/shm/model_cache
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Reading /tmp/tmpx165l9l_/pytorch_model.bin.index.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:04<29:02, 4.81s/it] Profiling: 38%|███▊ | 139/363 [00:07<00:09, 22.68it/s] Profiling: 77%|███████▋ | 278/363 [00:08<00:02, 41.32it/s] Profiling: 100%|██████████| 363/363 [00:10<00:00, 42.88it/s] Profiling: 100%|██████████| 363/363 [00:10<00:00, 33.52it/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: quantized model in 30.082s
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: creating bucket guanaco-mkml-models
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/config.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/added_tokens.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/tokenizer.model
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/tokenizer.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v21/mkml_model.tensors
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: loading reward model from rirv938/reward_gpt2_preference_24m_e2
thanhdaonguyen-once-upon-a-t-v21-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.
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: config.json: 0%| | 0.00/995 [00:00<?, ?B/s] config.json: 100%|██████████| 995/995 [00:00<00:00, 8.50MB/s]
thanhdaonguyen-once-upon-a-t-v21-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.
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.71MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.62MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.57MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: pytorch_model.bin: 0%| | 0.00/510M [00:00<?, ?B/s] pytorch_model.bin: 2%|▏ | 10.5M/510M [00:00<00:14, 34.6MB/s] pytorch_model.bin: 4%|▍ | 21.0M/510M [00:00<00:09, 50.5MB/s] pytorch_model.bin: 14%|█▍ | 73.4M/510M [00:00<00:02, 166MB/s] pytorch_model.bin: 38%|███▊ | 196M/510M [00:00<00:00, 443MB/s] pytorch_model.bin: 77%|███████▋ | 395M/510M [00:00<00:00, 867MB/s] pytorch_model.bin: 100%|█████████▉| 510M/510M [00:01<00:00, 673MB/s] pytorch_model.bin: 100%|█████████▉| 510M/510M [00:01<00:00, 489MB/s]
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Saving duration: 0.100s
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Processed model rirv938/reward_gpt2_preference_24m_e2 in 4.292s
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: creating bucket guanaco-reward-models
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/config.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/merges.txt
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/vocab.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/tokenizer.json
thanhdaonguyen-once-upon-a-t-v21-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v21_reward/reward.tensors
Job thanhdaonguyen-once-upon-a-t-v21-mkmlizer completed after 148.04s with status: succeeded
Stopping job with name thanhdaonguyen-once-upon-a-t-v21-mkmlizer
Pipeline stage MKMLizer completed in 153.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service thanhdaonguyen-once-upon-a-t-v21
Waiting for inference service thanhdaonguyen-once-upon-a-t-v21 to be ready
Inference service thanhdaonguyen-once-upon-a-t-v21 ready after 50.2904908657074s
Pipeline stage ISVCDeployer completed in 55.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7040395736694336s
Received healthy response to inference request in 1.7906420230865479s
Received healthy response to inference request in 1.7073581218719482s
Received healthy response to inference request in 1.5943987369537354s
Received healthy response to inference request in 1.7503893375396729s
5 requests
0 failed requests
5th percentile: 1.616990613937378
10th percentile: 1.6395824909210206
20th percentile: 1.6847662448883056
30th percentile: 1.7159643650054932
40th percentile: 1.733176851272583
50th percentile: 1.7503893375396729
60th percentile: 1.7664904117584228
70th percentile: 1.7825914859771728
80th percentile: 1.973321533203125
90th percentile: 2.3386805534362796
95th percentile: 2.5213600635528564
99th percentile: 2.6675036716461182
mean time: 1.9093655586242675
Pipeline stage StressChecker completed in 10.49s
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 0.07s
M-Eval Dataset for topic stay_in_character is loaded
AUTO_DEACTIVATION: submission %s deactivated %s
thanhdaonguyen-once-upon-a-t_v21 status is now inactive due to auto deactivation removed underperforming models
thanhdaonguyen-once-upon-a-t_v21 status is now deployed due to admin request

Usage Metrics

Latency Metrics