submission_id: chaiml-phase2-winner-13b2_v260
developer_uid: robert_irvine
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': 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}:'}
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: 2024-03-05T22:53:42+00:00
model_name: chaiml-phase2-winner-13b2_v260
model_eval_status: success
safety_score: None
entertaining: 6.98
stay_in_character: 8.48
user_preference: 7.5
double_thumbs_up: 2792
thumbs_up: 4195
thumbs_down: 1799
num_battles: 175877
num_wins: 87340
win_ratio: 0.49659705362270223
celo_rating: 1151.55
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v260-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v260-mkmlizer to finish
chaiml-phase2-winner-13b2-v260-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ Version: 0.6.11 ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v260-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-phase2-winner-13b2-v260-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.5MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: README.md: 0%| | 0.00/1.53k [00:00<?, ?B/s] README.md: 100%|██████████| 1.53k/1.53k [00:00<00:00, 12.5MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: config.json: 0%| | 0.00/651 [00:00<?, ?B/s] config.json: 100%|██████████| 651/651 [00:00<00:00, 8.78MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: generation_config.json: 0%| | 0.00/170 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 170/170 [00:00<00:00, 2.80MB/s]
chaiml-phase2-winner-13b2-v260-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<17:26, 9.50MB/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/9.95G [00:02<20:49, 7.94MB/s] pytorch_model-00001-of-00003.bin: 1%| | 52.4M/9.95G [00:02<06:21, 25.9MB/s] pytorch_model-00001-of-00003.bin: 1%| | 73.4M/9.95G [00:02<04:27, 37.0MB/s] pytorch_model-00001-of-00003.bin: 1%| | 94.4M/9.95G [00:03<03:21, 49.0MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 178M/9.95G [00:03<01:12, 134MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 430M/9.95G [00:03<00:21, 450MB/s] pytorch_model-00001-of-00003.bin: 5%|▌ | 535M/9.95G [00:03<00:19, 487MB/s] pytorch_model-00001-of-00003.bin: 10%|▉ | 975M/9.95G [00:03<00:07, 1.15GB/s] pytorch_model-00001-of-00003.bin: 12%|█▏ | 1.17G/9.95G [00:03<00:08, 1.03GB/s] pytorch_model-00001-of-00003.bin: 13%|█▎ | 1.34G/9.95G [00:04<00:13, 626MB/s] pytorch_model-00001-of-00003.bin: 15%|█▍ | 1.47G/9.95G [00:04<00:15, 552MB/s] pytorch_model-00001-of-00003.bin: 16%|█▌ | 1.57G/9.95G [00:04<00:14, 563MB/s] pytorch_model-00001-of-00003.bin: 17%|█▋ | 1.67G/9.95G [00:05<00:16, 489MB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.75G/9.95G [00:05<00:15, 536MB/s] pytorch_model-00001-of-00003.bin: 19%|█▉ | 1.87G/9.95G [00:05<00:13, 610MB/s] pytorch_model-00001-of-00003.bin: 20%|█▉ | 1.95G/9.95G [00:05<00:12, 647MB/s] pytorch_model-00001-of-00003.bin: 21%|██ | 2.07G/9.95G [00:05<00:10, 735MB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 2.16G/9.95G [00:05<00:11, 700MB/s] pytorch_model-00001-of-00003.bin: 23%|██▎ | 2.32G/9.95G [00:05<00:09, 807MB/s] pytorch_model-00001-of-00003.bin: 25%|██▌ | 2.50G/9.95G [00:06<00:07, 1.01GB/s] pytorch_model-00001-of-00003.bin: 27%|██▋ | 2.67G/9.95G [00:06<00:06, 1.20GB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.81G/9.95G [00:06<00:05, 1.22GB/s] pytorch_model-00001-of-00003.bin: 30%|██▉ | 2.95G/9.95G [00:06<00:06, 1.11GB/s] pytorch_model-00001-of-00003.bin: 31%|███ | 3.07G/9.95G [00:06<00:08, 818MB/s] pytorch_model-00001-of-00003.bin: 32%|███▏ | 3.18G/9.95G [00:06<00:08, 775MB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.27G/9.95G [00:06<00:08, 752MB/s] pytorch_model-00001-of-00003.bin: 34%|███▍ | 3.38G/9.95G [00:07<00:08, 804MB/s] pytorch_model-00001-of-00003.bin: 36%|███▌ | 3.53G/9.95G [00:07<00:06, 973MB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.76G/9.95G [00:07<00:04, 1.30GB/s] pytorch_model-00001-of-00003.bin: 40%|███▉ | 3.93G/9.95G [00:07<00:04, 1.40GB/s] pytorch_model-00001-of-00003.bin: 41%|████ | 4.09G/9.95G [00:07<00:04, 1.26GB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 4.23G/9.95G [00:07<00:06, 852MB/s] pytorch_model-00001-of-00003.bin: 44%|████▎ | 4.34G/9.95G [00:07<00:06, 883MB/s] pytorch_model-00001-of-00003.bin: 45%|████▍ | 4.47G/9.95G [00:08<00:05, 957MB/s] pytorch_model-00001-of-00003.bin: 46%|████▋ | 4.62G/9.95G [00:08<00:04, 1.10GB/s] pytorch_model-00001-of-00003.bin: 49%|████▊ | 4.83G/9.95G [00:08<00:03, 1.32GB/s] pytorch_model-00001-of-00003.bin: 51%|█████ | 5.08G/9.95G [00:08<00:03, 1.60GB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 5.25G/9.95G [00:08<00:03, 1.24GB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 5.40G/9.95G [00:08<00:04, 930MB/s] pytorch_model-00001-of-00003.bin: 56%|█████▌ | 5.53G/9.95G [00:09<00:05, 748MB/s] pytorch_model-00001-of-00003.bin: 57%|█████▋ | 5.64G/9.95G [00:09<00:05, 813MB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 5.75G/9.95G [00:09<00:05, 801MB/s] pytorch_model-00001-of-00003.bin: 59%|█████▊ | 5.84G/9.95G [00:09<00:05, 721MB/s] pytorch_model-00001-of-00003.bin: 61%|██████ | 6.07G/9.95G [00:09<00:03, 1.04GB/s] pytorch_model-00001-of-00003.bin: 64%|██████▍ | 6.39G/9.95G [00:09<00:02, 1.51GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▌ | 6.57G/9.95G [00:09<00:02, 1.58GB/s] pytorch_model-00001-of-00003.bin: 69%|██████▊ | 6.84G/9.95G [00:09<00:01, 1.84GB/s] pytorch_model-00001-of-00003.bin: 71%|███████ | 7.05G/9.95G [00:10<00:03, 794MB/s] pytorch_model-00001-of-00003.bin: 72%|███████▏ | 7.20G/9.95G [00:10<00:03, 895MB/s] pytorch_model-00001-of-00003.bin: 74%|███████▍ | 7.39G/9.95G [00:10<00:02, 1.02GB/s] pytorch_model-00001-of-00003.bin: 76%|███████▌ | 7.55G/9.95G [00:10<00:02, 1.11GB/s] pytorch_model-00001-of-00003.bin: 78%|███████▊ | 7.76G/9.95G [00:10<00:01, 1.28GB/s] pytorch_model-00001-of-00003.bin: 81%|████████ | 8.01G/9.95G [00:11<00:01, 1.54GB/s] pytorch_model-00001-of-00003.bin: 82%|████████▏ | 8.20G/9.95G [00:11<00:01, 1.63GB/s] pytorch_model-00001-of-00003.bin: 85%|████████▌ | 8.46G/9.95G [00:11<00:00, 1.88GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 8.67G/9.95G [00:11<00:01, 1.22GB/s] pytorch_model-00001-of-00003.bin: 89%|████████▉ | 8.84G/9.95G [00:11<00:01, 930MB/s] pytorch_model-00001-of-00003.bin: 90%|█████████ | 8.98G/9.95G [00:12<00:01, 914MB/s] pytorch_model-00001-of-00003.bin: 92%|█████████▏| 9.13G/9.95G [00:12<00:00, 990MB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.26G/9.95G [00:12<00:00, 970MB/s] pytorch_model-00001-of-00003.bin: 96%|█████████▌| 9.52G/9.95G [00:12<00:00, 1.30GB/s] pytorch_model-00001-of-00003.bin: 98%|█████████▊| 9.73G/9.95G [00:12<00:00, 1.47GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.92G/9.95G [00:12<00:00, 1.13GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:12<00:00, 770MB/s]
chaiml-phase2-winner-13b2-v260-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 [00:02<38:29, 4.28MB/s] pytorch_model-00002-of-00003.bin: 0%| | 21.0M/9.90G [00:02<16:53, 9.75MB/s] pytorch_model-00002-of-00003.bin: 0%| | 31.5M/9.90G [00:02<09:55, 16.6MB/s] pytorch_model-00002-of-00003.bin: 0%| | 41.9M/9.90G [00:02<07:36, 21.6MB/s] pytorch_model-00002-of-00003.bin: 1%| | 105M/9.90G [00:03<01:55, 84.5MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 210M/9.90G [00:03<00:47, 203MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 325M/9.90G [00:03<00:29, 324MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 409M/9.90G [00:03<00:23, 408MB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 587M/9.90G [00:03<00:13, 672MB/s] pytorch_model-00002-of-00003.bin: 11%|█ | 1.09G/9.90G [00:03<00:07, 1.25GB/s] pytorch_model-00002-of-00003.bin: 12%|█▏ | 1.23G/9.90G [00:04<00:14, 616MB/s] pytorch_model-00002-of-00003.bin: 14%|█▍ | 1.41G/9.90G [00:04<00:12, 699MB/s] pytorch_model-00002-of-00003.bin: 15%|█▌ | 1.51G/9.90G [00:04<00:13, 619MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.64G/9.90G [00:04<00:11, 704MB/s] pytorch_model-00002-of-00003.bin: 18%|█▊ | 1.74G/9.90G [00:05<00:11, 686MB/s] pytorch_model-00002-of-00003.bin: 19%|█▊ | 1.85G/9.90G [00:05<00:10, 743MB/s] pytorch_model-00002-of-00003.bin: 20%|█▉ | 1.94G/9.90G [00:05<00:10, 778MB/s] pytorch_model-00002-of-00003.bin: 21%|██ | 2.07G/9.90G [00:05<00:09, 870MB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 2.19G/9.90G [00:05<00:08, 956MB/s] pytorch_model-00002-of-00003.bin: 23%|██▎ | 2.31G/9.90G [00:05<00:09, 807MB/s] pytorch_model-00002-of-00003.bin: 25%|██▌ | 2.50G/9.90G [00:05<00:07, 1.04GB/s] pytorch_model-00002-of-00003.bin: 28%|██▊ | 2.82G/9.90G [00:05<00:04, 1.57GB/s] pytorch_model-00002-of-00003.bin: 31%|███▏ | 3.10G/9.90G [00:06<00:03, 1.86GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.31G/9.90G [00:06<00:04, 1.58GB/s] pytorch_model-00002-of-00003.bin: 35%|███▌ | 3.50G/9.90G [00:06<00:05, 1.15GB/s] pytorch_model-00002-of-00003.bin: 37%|███▋ | 3.65G/9.90G [00:06<00:05, 1.13GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 3.79G/9.90G [00:06<00:05, 1.11GB/s] pytorch_model-00002-of-00003.bin: 39%|███▉ | 3.91G/9.90G [00:06<00:06, 996MB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 4.14G/9.90G [00:07<00:04, 1.27GB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 4.29G/9.90G [00:07<00:04, 1.19GB/s] pytorch_model-00002-of-00003.bin: 45%|████▍ | 4.45G/9.90G [00:07<00:04, 1.24GB/s] pytorch_model-00002-of-00003.bin: 46%|████▋ | 4.58G/9.90G [00:07<00:04, 1.19GB/s] pytorch_model-00002-of-00003.bin: 48%|████▊ | 4.78G/9.90G [00:07<00:03, 1.33GB/s] pytorch_model-00002-of-00003.bin: 50%|████▉ | 4.93G/9.90G [00:07<00:04, 1.24GB/s] pytorch_model-00002-of-00003.bin: 51%|█████▏ | 5.09G/9.90G [00:07<00:03, 1.30GB/s] pytorch_model-00002-of-00003.bin: 53%|█████▎ | 5.22G/9.90G [00:07<00:03, 1.17GB/s] pytorch_model-00002-of-00003.bin: 54%|█████▍ | 5.35G/9.90G [00:08<00:04, 1.11GB/s] pytorch_model-00002-of-00003.bin: 56%|█████▌ | 5.55G/9.90G [00:08<00:03, 1.31GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 5.71G/9.90G [00:08<00:02, 1.40GB/s] pytorch_model-00002-of-00003.bin: 60%|██████ | 5.98G/9.90G [00:08<00:02, 1.61GB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 6.14G/9.90G [00:08<00:03, 1.16GB/s] pytorch_model-00002-of-00003.bin: 63%|██████▎ | 6.28G/9.90G [00:08<00:03, 1.10GB/s] pytorch_model-00002-of-00003.bin: 65%|██████▍ | 6.42G/9.90G [00:08<00:03, 1.15GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▌ | 6.55G/9.90G [00:08<00:02, 1.19GB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 6.71G/9.90G [00:09<00:02, 1.28GB/s] pytorch_model-00002-of-00003.bin: 70%|██████▉ | 6.89G/9.90G [00:09<00:02, 1.37GB/s] pytorch_model-00002-of-00003.bin: 72%|███████▏ | 7.09G/9.90G [00:09<00:01, 1.53GB/s] pytorch_model-00002-of-00003.bin: 74%|███████▍ | 7.32G/9.90G [00:09<00:01, 1.57GB/s] pytorch_model-00002-of-00003.bin: 76%|███████▌ | 7.49G/9.90G [00:09<00:01, 1.41GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.64G/9.90G [00:09<00:01, 1.45GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 7.80G/9.90G [00:09<00:01, 1.39GB/s] pytorch_model-00002-of-00003.bin: 81%|████████ | 8.03G/9.90G [00:09<00:01, 1.61GB/s] pytorch_model-00002-of-00003.bin: 83%|████████▎ | 8.24G/9.90G [00:10<00:00, 1.68GB/s] pytorch_model-00002-of-00003.bin: 85%|████████▌ | 8.42G/9.90G [00:10<00:01, 1.40GB/s] pytorch_model-00002-of-00003.bin: 87%|████████▋ | 8.58G/9.90G [00:10<00:01, 1.22GB/s] pytorch_model-00002-of-00003.bin: 89%|████████▊ | 8.77G/9.90G [00:10<00:00, 1.37GB/s] pytorch_model-00002-of-00003.bin: 90%|█████████ | 8.92G/9.90G [00:10<00:00, 1.28GB/s] pytorch_model-00002-of-00003.bin: 91%|█████████▏| 9.06G/9.90G [00:10<00:00, 1.13GB/s] pytorch_model-00002-of-00003.bin: 93%|█████████▎| 9.19G/9.90G [00:10<00:00, 1.13GB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▍| 9.34G/9.90G [00:11<00:00, 1.19GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 9.47G/9.90G [00:11<00:00, 1.21GB/s] pytorch_model-00002-of-00003.bin: 99%|█████████▉| 9.80G/9.90G [00:11<00:00, 1.74GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:11<00:00, 863MB/s]
chaiml-phase2-winner-13b2-v260-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 [00:02<23:35, 4.36MB/s] pytorch_model-00003-of-00003.bin: 0%| | 21.0M/6.18G [00:02<11:36, 8.84MB/s] pytorch_model-00003-of-00003.bin: 1%| | 31.5M/6.18G [00:03<07:35, 13.5MB/s] pytorch_model-00003-of-00003.bin: 1%| | 62.9M/6.18G [00:03<03:10, 32.1MB/s] pytorch_model-00003-of-00003.bin: 4%|▎ | 220M/6.18G [00:03<00:35, 167MB/s] pytorch_model-00003-of-00003.bin: 6%|▌ | 377M/6.18G [00:03<00:18, 321MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 472M/6.18G [00:03<00:15, 378MB/s] pytorch_model-00003-of-00003.bin: 10%|█ | 629M/6.18G [00:03<00:09, 558MB/s] pytorch_model-00003-of-00003.bin: 18%|█▊ | 1.14G/6.18G [00:04<00:06, 832MB/s] pytorch_model-00003-of-00003.bin: 20%|██ | 1.26G/6.18G [00:04<00:07, 636MB/s] pytorch_model-00003-of-00003.bin: 22%|██▏ | 1.35G/6.18G [00:04<00:07, 641MB/s] pytorch_model-00003-of-00003.bin: 23%|██▎ | 1.44G/6.18G [00:05<00:09, 513MB/s] pytorch_model-00003-of-00003.bin: 24%|██▍ | 1.50G/6.18G [00:05<00:08, 520MB/s] pytorch_model-00003-of-00003.bin: 25%|██▌ | 1.56G/6.18G [00:05<00:08, 535MB/s] pytorch_model-00003-of-00003.bin: 26%|██▋ | 1.63G/6.18G [00:05<00:08, 546MB/s] pytorch_model-00003-of-00003.bin: 29%|██▊ | 1.76G/6.18G [00:05<00:06, 690MB/s] pytorch_model-00003-of-00003.bin: 31%|███ | 1.89G/6.18G [00:05<00:05, 770MB/s] pytorch_model-00003-of-00003.bin: 32%|███▏ | 1.98G/6.18G [00:05<00:05, 779MB/s] pytorch_model-00003-of-00003.bin: 34%|███▎ | 2.08G/6.18G [00:05<00:05, 802MB/s] pytorch_model-00003-of-00003.bin: 36%|███▌ | 2.22G/6.18G [00:05<00:04, 968MB/s] pytorch_model-00003-of-00003.bin: 38%|███▊ | 2.34G/6.18G [00:06<00:03, 990MB/s] pytorch_model-00003-of-00003.bin: 40%|███▉ | 2.44G/6.18G [00:06<00:04, 808MB/s] pytorch_model-00003-of-00003.bin: 44%|████▍ | 2.75G/6.18G [00:06<00:02, 1.33GB/s] pytorch_model-00003-of-00003.bin: 49%|████▊ | 3.01G/6.18G [00:06<00:01, 1.59GB/s] pytorch_model-00003-of-00003.bin: 54%|█████▍ | 3.36G/6.18G [00:06<00:01, 1.98GB/s] pytorch_model-00003-of-00003.bin: 58%|█████▊ | 3.58G/6.18G [00:06<00:02, 1.24GB/s] pytorch_model-00003-of-00003.bin: 61%|██████ | 3.74G/6.18G [00:07<00:02, 994MB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 3.88G/6.18G [00:07<00:02, 900MB/s] pytorch_model-00003-of-00003.bin: 65%|██████▍ | 4.00G/6.18G [00:07<00:02, 932MB/s] pytorch_model-00003-of-00003.bin: 67%|██████▋ | 4.15G/6.18G [00:07<00:01, 1.05GB/s] pytorch_model-00003-of-00003.bin: 71%|███████ | 4.36G/6.18G [00:07<00:01, 1.26GB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 4.54G/6.18G [00:07<00:01, 1.36GB/s] pytorch_model-00003-of-00003.bin: 76%|███████▌ | 4.70G/6.18G [00:07<00:01, 1.32GB/s] pytorch_model-00003-of-00003.bin: 78%|███████▊ | 4.84G/6.18G [00:08<00:01, 1.13GB/s] pytorch_model-00003-of-00003.bin: 81%|████████ | 4.98G/6.18G [00:08<00:01, 1.17GB/s] pytorch_model-00003-of-00003.bin: 83%|████████▎ | 5.13G/6.18G [00:08<00:00, 1.23GB/s] pytorch_model-00003-of-00003.bin: 86%|████████▌ | 5.30G/6.18G [00:08<00:00, 1.29GB/s] pytorch_model-00003-of-00003.bin: 88%|████████▊ | 5.43G/6.18G [00:08<00:00, 1.18GB/s] pytorch_model-00003-of-00003.bin: 90%|█████████ | 5.57G/6.18G [00:08<00:00, 1.21GB/s] pytorch_model-00003-of-00003.bin: 93%|█████████▎| 5.77G/6.18G [00:08<00:00, 1.40GB/s] pytorch_model-00003-of-00003.bin: 96%|█████████▋| 5.96G/6.18G [00:08<00:00, 1.52GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.17G/6.18G [00:09<00:00, 1.65GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:09<00:00, 660MB/s]
chaiml-phase2-winner-13b2-v260-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, 20.1MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.76MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 29.8MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 11.9MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: tokenizer_config.json: 0%| | 0.00/725 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 10.9MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: Downloaded to shared memory in 36.267s
chaiml-phase2-winner-13b2-v260-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v260-mkmlizer: Saving mkml model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v260-mkmlizer: Reading /tmp/tmpu5054_6x/pytorch_model.bin.index.json
chaiml-phase2-winner-13b2-v260-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:04<28:16, 4.69s/it] Profiling: 38%|███▊ | 139/363 [00:06<00:08, 25.27it/s] Profiling: 77%|███████▋ | 278/363 [00:08<00:01, 44.37it/s] Profiling: 100%|██████████| 363/363 [00:10<00:00, 45.96it/s] Profiling: 100%|██████████| 363/363 [00:10<00:00, 35.96it/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: quantized model in 29.135s
chaiml-phase2-winner-13b2-v260-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 67.186s
chaiml-phase2-winner-13b2-v260-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v260-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v260-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260/tokenizer_config.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260/special_tokens_map.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260/tokenizer.model
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260/config.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260/tokenizer.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v260/mkml_model.tensors
chaiml-phase2-winner-13b2-v260-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
chaiml-phase2-winner-13b2-v260-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-v260-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v260-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.5MB/s]
chaiml-phase2-winner-13b2-v260-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-v260-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v260-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.22MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 46.8MB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 59.5MB/s]
chaiml-phase2-winner-13b2-v260-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-v260-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v260-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:14, 101MB/s] pytorch_model.bin: 5%|▌ | 73.4M/1.44G [00:00<00:03, 357MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:02, 550MB/s] pytorch_model.bin: 23%|██▎ | 325M/1.44G [00:00<00:01, 893MB/s] pytorch_model.bin: 29%|██▉ | 419M/1.44G [00:00<00:01, 782MB/s] pytorch_model.bin: 35%|███▍ | 503M/1.44G [00:00<00:01, 615MB/s] pytorch_model.bin: 40%|███▉ | 574M/1.44G [00:01<00:01, 497MB/s] pytorch_model.bin: 48%|████▊ | 690M/1.44G [00:01<00:01, 607MB/s] pytorch_model.bin: 69%|██████▉ | 994M/1.44G [00:01<00:00, 1.14GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.06GB/s]
chaiml-phase2-winner-13b2-v260-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v260-mkmlizer: Saving duration: 0.258s
chaiml-phase2-winner-13b2-v260-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.630s
chaiml-phase2-winner-13b2-v260-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v260-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v260-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/merges.txt
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/vocab.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/config.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/tokenizer.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v260-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v260_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v260-mkmlizer completed after 101.86s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v260-mkmlizer
Pipeline stage MKMLizer completed in 105.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v260
Waiting for inference service chaiml-phase2-winner-13b2-v260 to be ready
Inference service chaiml-phase2-winner-13b2-v260 ready after 40.26739716529846s
Pipeline stage ISVCDeployer completed in 48.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.421858072280884s
Received healthy response to inference request in 1.7331218719482422s
Received healthy response to inference request in 1.7288894653320312s
Received healthy response to inference request in 1.752957820892334s
Received healthy response to inference request in 1.75473952293396s
5 requests
0 failed requests
5th percentile: 1.7297359466552735
10th percentile: 1.7305824279785156
20th percentile: 1.732275390625
30th percentile: 1.7370890617370605
40th percentile: 1.7450234413146972
50th percentile: 1.752957820892334
60th percentile: 1.7536705017089844
70th percentile: 1.7543831825256349
80th percentile: 1.8881632328033449
90th percentile: 2.1550106525421144
95th percentile: 2.288434362411499
99th percentile: 2.395173330307007
mean time: 1.8783133506774903
Pipeline stage StressChecker completed in 10.25s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
AUTO_DEACTIVATION: submission %s deactivated %s
chaiml-phase2-winner-13b2_v260 status is now inactive due to auto deactivation removed underperforming models
chaiml-phase2-winner-13b2_v260 status is now deployed due to admin request
chaiml-phase2-winner-13b2_v260 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics