submission_id: thanhdaonguyen-once-upon-a-t_v38
developer_uid: robert_irvine
status: torndown
model_repo: thanhdaonguyen/once-upon-a-time
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.72, 'top_p': 0.73, 'min_p': 0.0, '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}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-03-05T22:52:58+00:00
model_name: thanhdaonguyen-once-upon-a-t_v38
model_eval_status: success
model_group: thanhdaonguyen/once-upon
num_battles: 176571
num_wins: 89727
celo_rating: 1159.57
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: thanhdaonguyen-once-upon-a-t_v38
ineligible_reason: propriety_total_count < 800
language_model: thanhdaonguyen/once-upon-a-time
model_size: 13B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-05
win_ratio: 0.5081638547666378
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thanhdaonguyen-once-upon-a-t-v38-mkmlizer
Waiting for job on thanhdaonguyen-once-upon-a-t-v38-mkmlizer to finish
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ _____ __ __ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ /___/ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ Version: 0.6.11 ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ The license key for the current software has been verified as ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ belonging to: ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ Chai Research Corp. ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ║ ║
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.6MB/s]
thanhdaonguyen-once-upon-a-t-v38-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, 327kB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 8.48MB/s]
thanhdaonguyen-once-upon-a-t-v38-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-v38-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 [00:01<20:31, 8.07MB/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/9.95G [00:02<19:28, 8.50MB/s] pytorch_model-00001-of-00003.bin: 0%| | 31.5M/9.95G [00:02<12:31, 13.2MB/s] pytorch_model-00001-of-00003.bin: 1%| | 62.9M/9.95G [00:02<04:34, 36.0MB/s] pytorch_model-00001-of-00003.bin: 1%| | 83.9M/9.95G [00:03<03:17, 49.9MB/s] pytorch_model-00001-of-00003.bin: 1%|▏ | 126M/9.95G [00:03<01:46, 92.4MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 252M/9.95G [00:03<00:37, 258MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 346M/9.95G [00:03<00:26, 363MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 419M/9.95G [00:03<00:24, 385MB/s] pytorch_model-00001-of-00003.bin: 5%|▌ | 545M/9.95G [00:03<00:16, 554MB/s] pytorch_model-00001-of-00003.bin: 11%|█▏ | 1.12G/9.95G [00:03<00:05, 1.49GB/s] pytorch_model-00001-of-00003.bin: 13%|█▎ | 1.29G/9.95G [00:04<00:14, 591MB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 1.42G/9.95G [00:04<00:13, 653MB/s] pytorch_model-00001-of-00003.bin: 16%|█▌ | 1.56G/9.95G [00:04<00:11, 737MB/s] pytorch_model-00001-of-00003.bin: 17%|█▋ | 1.69G/9.95G [00:05<00:12, 651MB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.79G/9.95G [00:05<00:13, 591MB/s] pytorch_model-00001-of-00003.bin: 19%|█▉ | 1.88G/9.95G [00:05<00:14, 550MB/s] pytorch_model-00001-of-00003.bin: 20%|██ | 2.00G/9.95G [00:05<00:12, 658MB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 2.17G/9.95G [00:05<00:09, 841MB/s] pytorch_model-00001-of-00003.bin: 23%|██▎ | 2.33G/9.95G [00:05<00:07, 990MB/s] pytorch_model-00001-of-00003.bin: 25%|██▍ | 2.45G/9.95G [00:06<00:09, 804MB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.81G/9.95G [00:06<00:05, 1.35GB/s] pytorch_model-00001-of-00003.bin: 31%|███ | 3.05G/9.95G [00:06<00:04, 1.57GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.25G/9.95G [00:06<00:06, 1.09GB/s] pytorch_model-00001-of-00003.bin: 34%|███▍ | 3.41G/9.95G [00:06<00:08, 790MB/s] pytorch_model-00001-of-00003.bin: 36%|███▌ | 3.53G/9.95G [00:07<00:08, 776MB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 3.65G/9.95G [00:07<00:07, 836MB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.80G/9.95G [00:07<00:06, 928MB/s] pytorch_model-00001-of-00003.bin: 41%|████ | 4.06G/9.95G [00:07<00:04, 1.28GB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 4.23G/9.95G [00:07<00:05, 1.11GB/s] pytorch_model-00001-of-00003.bin: 44%|████▍ | 4.36G/9.95G [00:07<00:04, 1.16GB/s] pytorch_model-00001-of-00003.bin: 46%|████▌ | 4.58G/9.95G [00:07<00:03, 1.39GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 4.76G/9.95G [00:07<00:03, 1.48GB/s] pytorch_model-00001-of-00003.bin: 50%|████▉ | 4.93G/9.95G [00:08<00:04, 1.24GB/s] pytorch_model-00001-of-00003.bin: 51%|█████ | 5.08G/9.95G [00:08<00:03, 1.23GB/s] pytorch_model-00001-of-00003.bin: 52%|█████▏ | 5.22G/9.95G [00:08<00:03, 1.26GB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 5.42G/9.95G [00:08<00:03, 1.43GB/s] pytorch_model-00001-of-00003.bin: 57%|█████▋ | 5.70G/9.95G [00:08<00:02, 1.79GB/s] pytorch_model-00001-of-00003.bin: 59%|█████▉ | 5.90G/9.95G [00:08<00:02, 1.71GB/s] pytorch_model-00001-of-00003.bin: 61%|██████ | 6.09G/9.95G [00:08<00:02, 1.60GB/s] pytorch_model-00001-of-00003.bin: 63%|██████▎ | 6.26G/9.95G [00:09<00:02, 1.26GB/s] pytorch_model-00001-of-00003.bin: 64%|██████▍ | 6.41G/9.95G [00:09<00:03, 1.16GB/s] pytorch_model-00001-of-00003.bin: 67%|██████▋ | 6.66G/9.95G [00:09<00:02, 1.42GB/s] pytorch_model-00001-of-00003.bin: 69%|██████▊ | 6.82G/9.95G [00:09<00:02, 1.26GB/s] pytorch_model-00001-of-00003.bin: 70%|███████ | 7.00G/9.95G [00:09<00:02, 1.38GB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 7.24G/9.95G [00:09<00:01, 1.55GB/s] pytorch_model-00001-of-00003.bin: 76%|███████▌ | 7.52G/9.95G [00:09<00:01, 1.86GB/s] pytorch_model-00001-of-00003.bin: 78%|███████▊ | 7.72G/9.95G [00:10<00:01, 1.53GB/s] pytorch_model-00001-of-00003.bin: 80%|███████▉ | 7.93G/9.95G [00:10<00:01, 1.61GB/s] pytorch_model-00001-of-00003.bin: 81%|████████▏ | 8.11G/9.95G [00:10<00:01, 1.47GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 8.27G/9.95G [00:10<00:01, 1.33GB/s] pytorch_model-00001-of-00003.bin: 85%|████████▍ | 8.43G/9.95G [00:10<00:01, 1.35GB/s] pytorch_model-00001-of-00003.bin: 86%|████████▌ | 8.58G/9.95G [00:10<00:01, 1.22GB/s] pytorch_model-00001-of-00003.bin: 88%|████████▊ | 8.76G/9.95G [00:10<00:00, 1.29GB/s] pytorch_model-00001-of-00003.bin: 90%|████████▉ | 8.91G/9.95G [00:10<00:00, 1.33GB/s] pytorch_model-00001-of-00003.bin: 91%|█████████▏| 9.08G/9.95G [00:11<00:00, 1.39GB/s] pytorch_model-00001-of-00003.bin: 94%|█████████▍| 9.35G/9.95G [00:11<00:00, 1.73GB/s] pytorch_model-00001-of-00003.bin: 96%|█████████▌| 9.54G/9.95G [00:11<00:00, 1.67GB/s] pytorch_model-00001-of-00003.bin: 98%|█████████▊| 9.79G/9.95G [00:11<00:00, 1.89GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:11<00:00, 844MB/s]
thanhdaonguyen-once-upon-a-t-v38-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 [00:01<21:27, 7.68MB/s] pytorch_model-00002-of-00003.bin: 0%| | 21.0M/9.90G [00:01<12:01, 13.7MB/s] pytorch_model-00002-of-00003.bin: 0%| | 31.5M/9.90G [00:01<07:30, 21.9MB/s] pytorch_model-00002-of-00003.bin: 0%| | 41.9M/9.90G [00:02<07:05, 23.2MB/s] pytorch_model-00002-of-00003.bin: 1%| | 52.4M/9.90G [00:02<06:05, 26.9MB/s] pytorch_model-00002-of-00003.bin: 1%| | 62.9M/9.90G [00:02<04:51, 33.7MB/s] pytorch_model-00002-of-00003.bin: 1%| | 73.4M/9.90G [00:02<03:49, 42.9MB/s] pytorch_model-00002-of-00003.bin: 1%| | 94.4M/9.90G [00:02<02:25, 67.6MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 157M/9.90G [00:03<00:57, 169MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 346M/9.90G [00:03<00:18, 506MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 440M/9.90G [00:03<00:19, 495MB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 556M/9.90G [00:03<00:14, 625MB/s] pytorch_model-00002-of-00003.bin: 11%|█ | 1.10G/9.90G [00:03<00:05, 1.48GB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 1.26G/9.90G [00:04<00:11, 730MB/s] pytorch_model-00002-of-00003.bin: 14%|█▍ | 1.37G/9.90G [00:04<00:12, 659MB/s] pytorch_model-00002-of-00003.bin: 15%|█▍ | 1.47G/9.90G [00:04<00:13, 630MB/s] pytorch_model-00002-of-00003.bin: 16%|█▌ | 1.55G/9.90G [00:04<00:14, 585MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.64G/9.90G [00:04<00:13, 607MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.71G/9.90G [00:05<00:13, 594MB/s] pytorch_model-00002-of-00003.bin: 19%|█▉ | 1.88G/9.90G [00:05<00:09, 804MB/s] pytorch_model-00002-of-00003.bin: 20%|██ | 1.98G/9.90G [00:05<00:09, 854MB/s] pytorch_model-00002-of-00003.bin: 21%|██ | 2.09G/9.90G [00:05<00:09, 833MB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 2.18G/9.90G [00:05<00:09, 828MB/s] pytorch_model-00002-of-00003.bin: 23%|██▎ | 2.29G/9.90G [00:05<00:08, 867MB/s] pytorch_model-00002-of-00003.bin: 24%|██▍ | 2.38G/9.90G [00:05<00:09, 795MB/s] pytorch_model-00002-of-00003.bin: 25%|██▍ | 2.46G/9.90G [00:05<00:10, 721MB/s] pytorch_model-00002-of-00003.bin: 27%|██▋ | 2.65G/9.90G [00:06<00:07, 992MB/s] pytorch_model-00002-of-00003.bin: 30%|███ | 2.98G/9.90G [00:06<00:04, 1.55GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.31G/9.90G [00:06<00:03, 2.02GB/s] pytorch_model-00002-of-00003.bin: 36%|███▌ | 3.53G/9.90G [00:06<00:05, 1.23GB/s] pytorch_model-00002-of-00003.bin: 37%|███▋ | 3.71G/9.90G [00:06<00:05, 1.22GB/s] pytorch_model-00002-of-00003.bin: 39%|███▉ | 3.87G/9.90G [00:06<00:05, 1.11GB/s] pytorch_model-00002-of-00003.bin: 41%|████ | 4.04G/9.90G [00:07<00:04, 1.21GB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 4.30G/9.90G [00:07<00:03, 1.52GB/s] pytorch_model-00002-of-00003.bin: 45%|████▌ | 4.49G/9.90G [00:07<00:03, 1.45GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 4.66G/9.90G [00:07<00:03, 1.47GB/s] pytorch_model-00002-of-00003.bin: 49%|████▊ | 4.82G/9.90G [00:07<00:03, 1.32GB/s] pytorch_model-00002-of-00003.bin: 50%|█████ | 4.97G/9.90G [00:07<00:04, 1.20GB/s] pytorch_model-00002-of-00003.bin: 52%|█████▏ | 5.11G/9.90G [00:07<00:03, 1.22GB/s] pytorch_model-00002-of-00003.bin: 53%|█████▎ | 5.24G/9.90G [00:07<00:03, 1.20GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▍ | 5.40G/9.90G [00:08<00:03, 1.29GB/s] pytorch_model-00002-of-00003.bin: 57%|█████▋ | 5.69G/9.90G [00:08<00:02, 1.68GB/s] pytorch_model-00002-of-00003.bin: 59%|█████▉ | 5.87G/9.90G [00:08<00:02, 1.59GB/s] pytorch_model-00002-of-00003.bin: 61%|██████ | 6.06G/9.90G [00:08<00:02, 1.59GB/s] pytorch_model-00002-of-00003.bin: 63%|██████▎ | 6.23G/9.90G [00:08<00:02, 1.37GB/s] pytorch_model-00002-of-00003.bin: 65%|██████▌ | 6.45G/9.90G [00:08<00:02, 1.57GB/s] pytorch_model-00002-of-00003.bin: 67%|██████▋ | 6.63G/9.90G [00:08<00:02, 1.62GB/s] pytorch_model-00002-of-00003.bin: 69%|██████▊ | 6.81G/9.90G [00:08<00:02, 1.47GB/s] pytorch_model-00002-of-00003.bin: 70%|███████ | 6.97G/9.90G [00:08<00:01, 1.48GB/s] pytorch_model-00002-of-00003.bin: 72%|███████▏ | 7.13G/9.90G [00:09<00:01, 1.39GB/s] pytorch_model-00002-of-00003.bin: 74%|███████▎ | 7.29G/9.90G [00:09<00:01, 1.42GB/s] pytorch_model-00002-of-00003.bin: 76%|███████▌ | 7.49G/9.90G [00:09<00:01, 1.52GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.64G/9.90G [00:09<00:01, 1.43GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▊ | 7.79G/9.90G [00:09<00:01, 1.38GB/s] pytorch_model-00002-of-00003.bin: 81%|████████ | 7.99G/9.90G [00:09<00:01, 1.52GB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 8.16G/9.90G [00:09<00:01, 1.55GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▍ | 8.36G/9.90G [00:09<00:00, 1.66GB/s] pytorch_model-00002-of-00003.bin: 86%|████████▌ | 8.54G/9.90G [00:10<00:00, 1.57GB/s] pytorch_model-00002-of-00003.bin: 88%|████████▊ | 8.70G/9.90G [00:10<00:00, 1.59GB/s] pytorch_model-00002-of-00003.bin: 90%|████████▉ | 8.90G/9.90G [00:10<00:00, 1.68GB/s] pytorch_model-00002-of-00003.bin: 92%|█████████▏| 9.13G/9.90G [00:10<00:00, 1.81GB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▍| 9.32G/9.90G [00:10<00:00, 1.66GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 9.50G/9.90G [00:10<00:00, 1.50GB/s] pytorch_model-00002-of-00003.bin: 98%|█████████▊| 9.66G/9.90G [00:10<00:00, 1.41GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.88G/9.90G [00:10<00:00, 1.38GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:11<00:00, 879MB/s]
thanhdaonguyen-once-upon-a-t-v38-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 [00:01<12:55, 7.96MB/s] pytorch_model-00003-of-00003.bin: 0%| | 21.0M/6.18G [00:01<07:04, 14.5MB/s] pytorch_model-00003-of-00003.bin: 1%| | 31.5M/6.18G [00:02<06:00, 17.1MB/s] pytorch_model-00003-of-00003.bin: 1%| | 52.4M/6.18G [00:02<03:30, 29.2MB/s] pytorch_model-00003-of-00003.bin: 1%| | 62.9M/6.18G [00:02<02:48, 36.2MB/s] pytorch_model-00003-of-00003.bin: 1%| | 73.4M/6.18G [00:02<03:14, 31.4MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 115M/6.18G [00:03<01:24, 71.6MB/s] pytorch_model-00003-of-00003.bin: 5%|▌ | 325M/6.18G [00:03<00:18, 315MB/s] pytorch_model-00003-of-00003.bin: 6%|▋ | 398M/6.18G [00:03<00:15, 366MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 482M/6.18G [00:03<00:12, 445MB/s] pytorch_model-00003-of-00003.bin: 18%|█▊ | 1.12G/6.18G [00:03<00:03, 1.32GB/s] pytorch_model-00003-of-00003.bin: 20%|██ | 1.26G/6.18G [00:04<00:08, 606MB/s] pytorch_model-00003-of-00003.bin: 24%|██▍ | 1.49G/6.18G [00:04<00:06, 766MB/s] pytorch_model-00003-of-00003.bin: 26%|██▌ | 1.61G/6.18G [00:04<00:06, 684MB/s] pytorch_model-00003-of-00003.bin: 28%|██▊ | 1.73G/6.18G [00:05<00:06, 689MB/s] pytorch_model-00003-of-00003.bin: 30%|██▉ | 1.82G/6.18G [00:05<00:06, 674MB/s] pytorch_model-00003-of-00003.bin: 31%|███ | 1.91G/6.18G [00:05<00:06, 696MB/s] pytorch_model-00003-of-00003.bin: 33%|███▎ | 2.02G/6.18G [00:05<00:05, 781MB/s] pytorch_model-00003-of-00003.bin: 35%|███▍ | 2.15G/6.18G [00:05<00:04, 871MB/s] pytorch_model-00003-of-00003.bin: 36%|███▋ | 2.25G/6.18G [00:05<00:04, 908MB/s] pytorch_model-00003-of-00003.bin: 39%|███▊ | 2.39G/6.18G [00:05<00:03, 1.01GB/s] pytorch_model-00003-of-00003.bin: 44%|████▍ | 2.72G/6.18G [00:05<00:02, 1.58GB/s] pytorch_model-00003-of-00003.bin: 48%|████▊ | 2.96G/6.18G [00:05<00:01, 1.79GB/s] pytorch_model-00003-of-00003.bin: 51%|█████ | 3.16G/6.18G [00:06<00:02, 1.27GB/s] pytorch_model-00003-of-00003.bin: 54%|█████▎ | 3.31G/6.18G [00:06<00:02, 1.05GB/s] pytorch_model-00003-of-00003.bin: 56%|█████▌ | 3.45G/6.18G [00:06<00:02, 1.04GB/s] pytorch_model-00003-of-00003.bin: 59%|█████▉ | 3.64G/6.18G [00:06<00:02, 1.20GB/s] pytorch_model-00003-of-00003.bin: 62%|██████▏ | 3.81G/6.18G [00:06<00:01, 1.29GB/s] pytorch_model-00003-of-00003.bin: 64%|██████▍ | 3.95G/6.18G [00:06<00:01, 1.31GB/s] pytorch_model-00003-of-00003.bin: 68%|██████▊ | 4.17G/6.18G [00:06<00:01, 1.54GB/s] pytorch_model-00003-of-00003.bin: 70%|███████ | 4.34G/6.18G [00:07<00:01, 1.29GB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 4.49G/6.18G [00:07<00:01, 1.26GB/s] pytorch_model-00003-of-00003.bin: 75%|███████▌ | 4.65G/6.18G [00:07<00:01, 1.25GB/s] pytorch_model-00003-of-00003.bin: 77%|███████▋ | 4.78G/6.18G [00:07<00:01, 1.24GB/s] pytorch_model-00003-of-00003.bin: 80%|███████▉ | 4.92G/6.18G [00:07<00:01, 1.23GB/s] pytorch_model-00003-of-00003.bin: 82%|████████▏ | 5.05G/6.18G [00:07<00:00, 1.24GB/s] pytorch_model-00003-of-00003.bin: 85%|████████▍ | 5.23G/6.18G [00:07<00:00, 1.36GB/s] pytorch_model-00003-of-00003.bin: 88%|████████▊ | 5.41G/6.18G [00:07<00:00, 1.46GB/s] pytorch_model-00003-of-00003.bin: 90%|█████████ | 5.57G/6.18G [00:08<00:00, 1.48GB/s] pytorch_model-00003-of-00003.bin: 93%|█████████▎| 5.76G/6.18G [00:08<00:00, 1.57GB/s] pytorch_model-00003-of-00003.bin: 96%|█████████▌| 5.92G/6.18G [00:08<00:00, 1.35GB/s] pytorch_model-00003-of-00003.bin: 98%|█████████▊| 6.07G/6.18G [00:08<00:00, 1.09GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:08<00:00, 714MB/s]
thanhdaonguyen-once-upon-a-t-v38-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, 102MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: special_tokens_map.json: 0%| | 0.00/438 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 438/438 [00:00<00:00, 6.61MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 29.0MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 11.9MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: tokenizer_config.json: 0%| | 0.00/828 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 828/828 [00:00<00:00, 5.19MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Downloaded to shared memory in 34.602s
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: quantizing model to /dev/shm/model_cache
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Saving mkml model at /dev/shm/model_cache
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Reading /tmp/tmpe1yv6qth/pytorch_model.bin.index.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:04<27:37, 4.58s/it] Profiling: 38%|███▊ | 139/363 [00:06<00:07, 28.01it/s] Profiling: 77%|███████▋ | 278/363 [00:07<00:01, 49.42it/s] Profiling: 100%|██████████| 363/363 [00:09<00:00, 46.50it/s] Profiling: 100%|██████████| 363/363 [00:09<00:00, 37.52it/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: quantized model in 33.252s
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Processed model thanhdaonguyen/once-upon-a-time in 69.826s
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: creating bucket guanaco-mkml-models
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/config.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/added_tokens.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/tokenizer.model
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/tokenizer.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/thanhdaonguyen-once-upon-a-t-v38/mkml_model.tensors
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
thanhdaonguyen-once-upon-a-t-v38-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-v38-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 8.73MB/s]
thanhdaonguyen-once-upon-a-t-v38-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-v38-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.77MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 43.4MB/s]
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 22.5MB/s]
thanhdaonguyen-once-upon-a-t-v38-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.
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: warnings.warn(
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Saving duration: 0.396s
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 9.514s
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: creating bucket guanaco-reward-models
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/config.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/special_tokens_map.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/tokenizer_config.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/merges.txt
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/vocab.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/tokenizer.json
thanhdaonguyen-once-upon-a-t-v38-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thanhdaonguyen-once-upon-a-t-v38_reward/reward.tensors
Job thanhdaonguyen-once-upon-a-t-v38-mkmlizer completed after 124.01s with status: succeeded
Stopping job with name thanhdaonguyen-once-upon-a-t-v38-mkmlizer
Pipeline stage MKMLizer completed in 125.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.18s
Running pipeline stage ISVCDeployer
Creating inference service thanhdaonguyen-once-upon-a-t-v38
Waiting for inference service thanhdaonguyen-once-upon-a-t-v38 to be ready
Inference service thanhdaonguyen-once-upon-a-t-v38 ready after 60.42277979850769s
Pipeline stage ISVCDeployer completed in 67.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.303067922592163s
Received healthy response to inference request in 1.7716705799102783s
Received healthy response to inference request in 1.8014230728149414s
Received healthy response to inference request in 1.8697328567504883s
Received healthy response to inference request in 1.7743511199951172s
5 requests
0 failed requests
5th percentile: 1.772206687927246
10th percentile: 1.772742795944214
20th percentile: 1.7738150119781495
30th percentile: 1.779765510559082
40th percentile: 1.7905942916870117
50th percentile: 1.8014230728149414
60th percentile: 1.8287469863891601
70th percentile: 1.8560708999633788
80th percentile: 1.9563998699188234
90th percentile: 2.1297338962554933
95th percentile: 2.216400909423828
99th percentile: 2.285734519958496
mean time: 1.9040491104125976
Pipeline stage StressChecker completed in 10.53s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
AUTO_DEACTIVATION: submission %s deactivated %s
thanhdaonguyen-once-upon-a-t_v38 status is now inactive due to auto deactivation removed underperforming models
thanhdaonguyen-once-upon-a-t_v38 status is now deployed due to admin request
thanhdaonguyen-once-upon-a-t_v38 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thanhdaonguyen-once-upon-a-t_v38
Running pipeline stage ISVCDeleter
Checking if service thanhdaonguyen-once-upon-a-t-v38 is running
Tearing down inference service thanhdaonguyen-once-upon-a-t-v38
Toredown service thanhdaonguyen-once-upon-a-t-v38
Pipeline stage ISVCDeleter completed in 9.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thanhdaonguyen-once-upon-a-t-v38/added_tokens.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v38/config.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v38/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v38/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v38/tokenizer.json from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v38/tokenizer.model from bucket guanaco-mkml-models
Deleting key thanhdaonguyen-once-upon-a-t-v38/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/config.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/merges.txt from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thanhdaonguyen-once-upon-a-t-v38_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.63s
thanhdaonguyen-once-upon-a-t_v38 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics