submission_id: chaiml-phase2-winner-13b2_v277
developer_uid: chai_backend_admin
status: inactive
model_repo: ChaiML/phase2_winner_13b2
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0733671330918084, 'top_p': 0.6971846333941389, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.312882778758545, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 96}
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}:'}
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: 2024-03-31T01:47:42+00:00
model_name: phase2_winner_13b2-96
model_eval_status: success
safety_score: None
entertaining: 7.06
stay_in_character: 8.58
user_preference: 7.62
double_thumbs_up: 1335
thumbs_up: 1859
thumbs_down: 839
num_battles: 129951
num_wins: 68517
win_ratio: 0.527252579818547
celo_rating: 1171.62
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v277-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v277-mkmlizer to finish
chaiml-phase2-winner-13b2-v277-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ Version: 0.6.11 ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v277-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-phase2-winner-13b2-v277-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.8MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: README.md: 0%| | 0.00/1.53k [00:00<?, ?B/s] README.md: 100%|██████████| 1.53k/1.53k [00:00<00:00, 15.0MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: config.json: 0%| | 0.00/651 [00:00<?, ?B/s] config.json: 100%|██████████| 651/651 [00:00<00:00, 7.09MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: generation_config.json: 0%| | 0.00/170 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 170/170 [00:00<00:00, 2.04MB/s]
chaiml-phase2-winner-13b2-v277-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<02:04, 79.5MB/s] pytorch_model-00001-of-00003.bin: 1%| | 83.9M/9.95G [00:00<00:24, 399MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 199M/9.95G [00:00<00:13, 711MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 294M/9.95G [00:00<00:12, 789MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 398M/9.95G [00:00<00:11, 868MB/s] pytorch_model-00001-of-00003.bin: 5%|▍ | 493M/9.95G [00:00<00:10, 889MB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 661M/9.95G [00:00<00:08, 1.13GB/s] pytorch_model-00001-of-00003.bin: 10%|▉ | 986M/9.95G [00:00<00:05, 1.78GB/s] pytorch_model-00001-of-00003.bin: 12%|█▏ | 1.20G/9.95G [00:00<00:04, 1.86GB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 1.42G/9.95G [00:01<00:04, 1.89GB/s] pytorch_model-00001-of-00003.bin: 16%|█▌ | 1.61G/9.95G [00:01<00:04, 1.69GB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.79G/9.95G [00:01<00:05, 1.62GB/s] pytorch_model-00001-of-00003.bin: 20%|██ | 2.03G/9.95G [00:01<00:04, 1.81GB/s] pytorch_model-00001-of-00003.bin: 23%|██▎ | 2.25G/9.95G [00:01<00:04, 1.92GB/s] pytorch_model-00001-of-00003.bin: 25%|██▍ | 2.47G/9.95G [00:01<00:03, 1.96GB/s] pytorch_model-00001-of-00003.bin: 27%|██▋ | 2.67G/9.95G [00:01<00:04, 1.79GB/s] pytorch_model-00001-of-00003.bin: 29%|██▉ | 2.86G/9.95G [00:01<00:03, 1.79GB/s] pytorch_model-00001-of-00003.bin: 31%|███ | 3.05G/9.95G [00:02<00:03, 1.76GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.24G/9.95G [00:02<00:03, 1.77GB/s] pytorch_model-00001-of-00003.bin: 35%|███▍ | 3.47G/9.95G [00:02<00:03, 1.89GB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 3.67G/9.95G [00:02<00:03, 1.78GB/s] pytorch_model-00001-of-00003.bin: 39%|███▉ | 3.86G/9.95G [00:02<00:03, 1.75GB/s] pytorch_model-00001-of-00003.bin: 41%|████ | 4.08G/9.95G [00:02<00:03, 1.86GB/s] pytorch_model-00001-of-00003.bin: 43%|████▎ | 4.30G/9.95G [00:02<00:02, 1.91GB/s] pytorch_model-00001-of-00003.bin: 45%|████▌ | 4.51G/9.95G [00:02<00:02, 1.89GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 4.74G/9.95G [00:02<00:02, 1.99GB/s] pytorch_model-00001-of-00003.bin: 50%|████▉ | 4.96G/9.95G [00:02<00:02, 2.05GB/s] pytorch_model-00001-of-00003.bin: 52%|█████▏ | 5.17G/9.95G [00:03<00:02, 1.87GB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 5.37G/9.95G [00:03<00:02, 1.79GB/s] pytorch_model-00001-of-00003.bin: 56%|█████▌ | 5.58G/9.95G [00:03<00:02, 1.85GB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 5.77G/9.95G [00:03<00:02, 1.81GB/s] pytorch_model-00001-of-00003.bin: 60%|█████▉ | 5.96G/9.95G [00:03<00:02, 1.81GB/s] pytorch_model-00001-of-00003.bin: 62%|██████▏ | 6.14G/9.95G [00:03<00:02, 1.71GB/s] pytorch_model-00001-of-00003.bin: 64%|██████▍ | 6.36G/9.95G [00:03<00:01, 1.83GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▌ | 6.56G/9.95G [00:03<00:01, 1.86GB/s] pytorch_model-00001-of-00003.bin: 68%|██████▊ | 6.75G/9.95G [00:03<00:01, 1.84GB/s] pytorch_model-00001-of-00003.bin: 70%|██████▉ | 6.94G/9.95G [00:04<00:01, 1.73GB/s] pytorch_model-00001-of-00003.bin: 72%|███████▏ | 7.12G/9.95G [00:04<00:01, 1.73GB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 7.30G/9.95G [00:04<00:01, 1.65GB/s] pytorch_model-00001-of-00003.bin: 75%|███████▌ | 7.47G/9.95G [00:04<00:01, 1.63GB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 7.63G/9.95G [00:04<00:01, 1.64GB/s] pytorch_model-00001-of-00003.bin: 79%|███████▉ | 7.91G/9.95G [00:04<00:01, 1.93GB/s] pytorch_model-00001-of-00003.bin: 81%|████████▏ | 8.11G/9.95G [00:04<00:00, 1.87GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 8.29G/9.95G [00:04<00:00, 1.76GB/s] pytorch_model-00001-of-00003.bin: 85%|████████▌ | 8.47G/9.95G [00:05<00:00, 1.65GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 8.70G/9.95G [00:05<00:00, 1.83GB/s] pytorch_model-00001-of-00003.bin: 89%|████████▉ | 8.89G/9.95G [00:05<00:00, 1.84GB/s] pytorch_model-00001-of-00003.bin: 91%|█████████▏| 9.09G/9.95G [00:05<00:00, 1.88GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.30G/9.95G [00:05<00:00, 1.94GB/s] pytorch_model-00001-of-00003.bin: 96%|█████████▌| 9.51G/9.95G [00:05<00:00, 1.98GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:05<00:00, 2.18GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:05<00:00, 1.74GB/s]
chaiml-phase2-winner-13b2-v277-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<03:18, 50.0MB/s] pytorch_model-00002-of-00003.bin: 0%| | 41.9M/9.90G [00:00<01:03, 155MB/s] pytorch_model-00002-of-00003.bin: 1%|▏ | 147M/9.90G [00:00<00:21, 461MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 210M/9.90G [00:00<00:21, 451MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 283M/9.90G [00:00<00:18, 532MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 398M/9.90G [00:00<00:13, 704MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 493M/9.90G [00:00<00:12, 767MB/s] pytorch_model-00002-of-00003.bin: 8%|▊ | 755M/9.90G [00:00<00:06, 1.31GB/s] pytorch_model-00002-of-00003.bin: 12%|█▏ | 1.18G/9.90G [00:01<00:04, 2.15GB/s] pytorch_model-00002-of-00003.bin: 14%|█▍ | 1.42G/9.90G [00:01<00:04, 2.06GB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.64G/9.90G [00:01<00:04, 1.88GB/s] pytorch_model-00002-of-00003.bin: 19%|█▊ | 1.84G/9.90G [00:01<00:05, 1.48GB/s] pytorch_model-00002-of-00003.bin: 20%|██ | 2.00G/9.90G [00:01<00:05, 1.44GB/s] pytorch_model-00002-of-00003.bin: 23%|██▎ | 2.29G/9.90G [00:01<00:04, 1.72GB/s] pytorch_model-00002-of-00003.bin: 28%|██▊ | 2.75G/9.90G [00:01<00:02, 2.40GB/s] pytorch_model-00002-of-00003.bin: 30%|███ | 3.01G/9.90G [00:02<00:03, 1.87GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.23G/9.90G [00:02<00:04, 1.39GB/s] pytorch_model-00002-of-00003.bin: 35%|███▍ | 3.46G/9.90G [00:02<00:04, 1.54GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 3.79G/9.90G [00:02<00:03, 1.87GB/s] pytorch_model-00002-of-00003.bin: 41%|████ | 4.04G/9.90G [00:02<00:02, 1.99GB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 4.27G/9.90G [00:02<00:02, 1.97GB/s] pytorch_model-00002-of-00003.bin: 45%|████▌ | 4.49G/9.90G [00:03<00:03, 1.76GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 4.69G/9.90G [00:03<00:02, 1.79GB/s] pytorch_model-00002-of-00003.bin: 50%|████▉ | 4.94G/9.90G [00:03<00:02, 1.92GB/s] pytorch_model-00002-of-00003.bin: 53%|█████▎ | 5.23G/9.90G [00:03<00:02, 2.17GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▌ | 5.46G/9.90G [00:03<00:02, 2.20GB/s] pytorch_model-00002-of-00003.bin: 57%|█████▋ | 5.69G/9.90G [00:03<00:02, 2.00GB/s] pytorch_model-00002-of-00003.bin: 60%|█████▉ | 5.90G/9.90G [00:03<00:02, 1.93GB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 6.10G/9.90G [00:03<00:02, 1.63GB/s] pytorch_model-00002-of-00003.bin: 64%|██████▍ | 6.38G/9.90G [00:03<00:01, 1.87GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▋ | 6.59G/9.90G [00:04<00:01, 1.80GB/s] pytorch_model-00002-of-00003.bin: 69%|██████▉ | 6.86G/9.90G [00:04<00:01, 2.01GB/s] pytorch_model-00002-of-00003.bin: 71%|███████▏ | 7.08G/9.90G [00:04<00:01, 1.89GB/s] pytorch_model-00002-of-00003.bin: 73%|███████▎ | 7.28G/9.90G [00:04<00:01, 1.77GB/s] pytorch_model-00002-of-00003.bin: 75%|███████▌ | 7.47G/9.90G [00:04<00:01, 1.67GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.64G/9.90G [00:04<00:01, 1.63GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 7.81G/9.90G [00:04<00:01, 1.62GB/s] pytorch_model-00002-of-00003.bin: 81%|████████ | 8.02G/9.90G [00:04<00:01, 1.74GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▎ | 8.28G/9.90G [00:05<00:00, 1.98GB/s] pytorch_model-00002-of-00003.bin: 86%|████████▌ | 8.49G/9.90G [00:05<00:00, 1.96GB/s] pytorch_model-00002-of-00003.bin: 88%|████████▊ | 8.69G/9.90G [00:05<00:00, 1.93GB/s] pytorch_model-00002-of-00003.bin: 90%|████████▉ | 8.89G/9.90G [00:05<00:00, 1.89GB/s] pytorch_model-00002-of-00003.bin: 92%|█████████▏| 9.14G/9.90G [00:05<00:00, 2.05GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 9.50G/9.90G [00:05<00:00, 2.46GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:05<00:00, 1.76GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:05<00:00, 1.67GB/s]
chaiml-phase2-winner-13b2-v277-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<01:12, 85.4MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 105M/6.18G [00:00<00:11, 538MB/s] pytorch_model-00003-of-00003.bin: 4%|▎ | 231M/6.18G [00:00<00:07, 841MB/s] pytorch_model-00003-of-00003.bin: 5%|▌ | 325M/6.18G [00:00<00:06, 853MB/s] pytorch_model-00003-of-00003.bin: 7%|▋ | 440M/6.18G [00:00<00:06, 955MB/s] pytorch_model-00003-of-00003.bin: 9%|▉ | 577M/6.18G [00:00<00:05, 1.06GB/s] pytorch_model-00003-of-00003.bin: 12%|█▏ | 755M/6.18G [00:00<00:04, 1.25GB/s] pytorch_model-00003-of-00003.bin: 16%|█▋ | 1.01G/6.18G [00:00<00:03, 1.62GB/s] pytorch_model-00003-of-00003.bin: 21%|██ | 1.29G/6.18G [00:00<00:02, 1.94GB/s] pytorch_model-00003-of-00003.bin: 24%|██▍ | 1.49G/6.18G [00:01<00:02, 1.91GB/s] pytorch_model-00003-of-00003.bin: 27%|██▋ | 1.69G/6.18G [00:01<00:02, 1.91GB/s] pytorch_model-00003-of-00003.bin: 31%|███ | 1.90G/6.18G [00:01<00:02, 1.88GB/s] pytorch_model-00003-of-00003.bin: 35%|███▌ | 2.19G/6.18G [00:01<00:01, 2.08GB/s] pytorch_model-00003-of-00003.bin: 39%|███▉ | 2.41G/6.18G [00:01<00:01, 2.03GB/s] pytorch_model-00003-of-00003.bin: 42%|████▏ | 2.62G/6.18G [00:01<00:01, 1.93GB/s] pytorch_model-00003-of-00003.bin: 46%|████▌ | 2.83G/6.18G [00:01<00:01, 1.95GB/s] pytorch_model-00003-of-00003.bin: 49%|████▉ | 3.03G/6.18G [00:01<00:01, 1.94GB/s] pytorch_model-00003-of-00003.bin: 53%|█████▎ | 3.26G/6.18G [00:01<00:01, 2.01GB/s] pytorch_model-00003-of-00003.bin: 57%|█████▋ | 3.49G/6.18G [00:02<00:01, 2.09GB/s] pytorch_model-00003-of-00003.bin: 60%|█████▉ | 3.70G/6.18G [00:02<00:01, 1.96GB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 3.91G/6.18G [00:02<00:01, 1.96GB/s] pytorch_model-00003-of-00003.bin: 67%|██████▋ | 4.11G/6.18G [00:02<00:01, 1.74GB/s] pytorch_model-00003-of-00003.bin: 71%|███████▏ | 4.40G/6.18G [00:02<00:00, 2.04GB/s] pytorch_model-00003-of-00003.bin: 75%|███████▍ | 4.62G/6.18G [00:02<00:00, 1.94GB/s] pytorch_model-00003-of-00003.bin: 79%|███████▊ | 4.87G/6.18G [00:02<00:00, 2.06GB/s] pytorch_model-00003-of-00003.bin: 82%|████████▏ | 5.09G/6.18G [00:02<00:00, 2.00GB/s] pytorch_model-00003-of-00003.bin: 86%|████████▌ | 5.30G/6.18G [00:02<00:00, 1.99GB/s] pytorch_model-00003-of-00003.bin: 91%|█████████ | 5.60G/6.18G [00:03<00:00, 2.28GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.17G/6.18G [00:03<00:00, 2.05GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:03<00:00, 1.72GB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/33.4k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 33.4k/33.4k [00:00<00:00, 45.3MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.84MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 18.3MB/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 18.2MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 52.9MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: tokenizer_config.json: 0%| | 0.00/725 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 6.34MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: Downloaded to shared memory in 17.097s
chaiml-phase2-winner-13b2-v277-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v277-mkmlizer: Saving mkml model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v277-mkmlizer: Reading /tmp/tmpdju6gmeu/pytorch_model.bin.index.json
chaiml-phase2-winner-13b2-v277-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:03<18:50, 3.12s/it] Profiling: 38%|███▊ | 139/363 [00:04<00:06, 36.29it/s] Profiling: 77%|███████▋ | 278/363 [00:05<00:01, 63.09it/s] Profiling: 100%|██████████| 363/363 [00:07<00:00, 59.95it/s] Profiling: 100%|██████████| 363/363 [00:07<00:00, 49.18it/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: quantized model in 27.461s
chaiml-phase2-winner-13b2-v277-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 46.447s
chaiml-phase2-winner-13b2-v277-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v277-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v277-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277/config.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277/tokenizer.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277/tokenizer.model
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277/special_tokens_map.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277/tokenizer_config.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v277/mkml_model.tensors
chaiml-phase2-winner-13b2-v277-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
chaiml-phase2-winner-13b2-v277-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.
chaiml-phase2-winner-13b2-v277-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v277-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 8.18MB/s]
chaiml-phase2-winner-13b2-v277-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.
chaiml-phase2-winner-13b2-v277-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v277-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.99MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 8.71MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 8.67MB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 21.0MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 20.8MB/s]
chaiml-phase2-winner-13b2-v277-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.
chaiml-phase2-winner-13b2-v277-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v277-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:09, 155MB/s] pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:06, 217MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:00<00:02, 573MB/s] pytorch_model.bin: 16%|█▌ | 231M/1.44G [00:00<00:02, 544MB/s] pytorch_model.bin: 20%|██ | 294M/1.44G [00:00<00:02, 514MB/s] pytorch_model.bin: 27%|██▋ | 388M/1.44G [00:00<00:01, 582MB/s] pytorch_model.bin: 32%|███▏ | 461M/1.44G [00:00<00:01, 570MB/s] pytorch_model.bin: 40%|███▉ | 577M/1.44G [00:00<00:01, 718MB/s] pytorch_model.bin: 54%|█████▎ | 776M/1.44G [00:01<00:00, 1.06GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.18GB/s]
chaiml-phase2-winner-13b2-v277-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v277-mkmlizer: Saving duration: 0.252s
chaiml-phase2-winner-13b2-v277-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.474s
chaiml-phase2-winner-13b2-v277-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v277-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v277-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/config.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/merges.txt
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/vocab.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/tokenizer.json
chaiml-phase2-winner-13b2-v277-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v277_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v277-mkmlizer completed after 74.69s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v277-mkmlizer
Pipeline stage MKMLizer completed in 79.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v277
Waiting for inference service chaiml-phase2-winner-13b2-v277 to be ready
Inference service chaiml-phase2-winner-13b2-v277 ready after 40.28302979469299s
Pipeline stage ISVCDeployer completed in 47.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.873981952667236s
Received healthy response to inference request in 1.9538609981536865s
Received healthy response to inference request in 2.3761825561523438s
Received healthy response to inference request in 2.4049715995788574s
Received healthy response to inference request in 2.193613052368164s
5 requests
0 failed requests
5th percentile: 2.001811408996582
10th percentile: 2.0497618198394774
20th percentile: 2.1456626415252686
30th percentile: 2.230126953125
40th percentile: 2.3031547546386717
50th percentile: 2.3761825561523438
60th percentile: 2.387698173522949
70th percentile: 2.3992137908935547
80th percentile: 2.8987736701965336
90th percentile: 3.8863778114318848
95th percentile: 4.3801798820495605
99th percentile: 4.775221538543701
mean time: 2.7605220317840575
Pipeline stage StressChecker completed in 14.68s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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 0.10s
chaiml-phase2-winner-13b2_v277 status is now deployed due to DeploymentManager action
chaiml-phase2-winner-13b2_v277 status is now inactive due to auto deactivation removed underperforming models
chaiml-phase2-winner-13b2_v277 status is now deployed due to admin request
chaiml-phase2-winner-13b2_v277 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics