submission_id: chaiml-phase2-winner-13b2_v275
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': 48}
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: 2024-03-31T01:47:03+00:00
model_name: phase2_winner_13b2-48
model_eval_status: success
safety_score: 0.92
entertaining: 6.88
stay_in_character: 8.4
user_preference: 6.98
double_thumbs_up: 1350
thumbs_up: 1862
thumbs_down: 793
num_battles: 129305
num_wins: 57360
win_ratio: 0.4436023355632033
celo_rating: 1113.34
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v275-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v275-mkmlizer to finish
chaiml-phase2-winner-13b2-v275-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ Version: 0.6.11 ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v275-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-phase2-winner-13b2-v275-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 20.6MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: README.md: 0%| | 0.00/1.53k [00:00<?, ?B/s] README.md: 100%|██████████| 1.53k/1.53k [00:00<00:00, 14.7MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: config.json: 0%| | 0.00/651 [00:00<?, ?B/s] config.json: 100%|██████████| 651/651 [00:00<00:00, 11.0MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: generation_config.json: 0%| | 0.00/170 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 170/170 [00:00<00:00, 1.43MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/9.95G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/9.95G [00:00<00:54, 181MB/s] pytorch_model-00001-of-00003.bin: 0%| | 41.9M/9.95G [00:00<00:53, 185MB/s] pytorch_model-00001-of-00003.bin: 1%|▏ | 147M/9.95G [00:00<00:17, 552MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 273M/9.95G [00:00<00:12, 774MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 430M/9.95G [00:00<00:09, 1.03GB/s] pytorch_model-00001-of-00003.bin: 5%|▌ | 545M/9.95G [00:00<00:09, 1.02GB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 724M/9.95G [00:00<00:07, 1.24GB/s] pytorch_model-00001-of-00003.bin: 9%|▉ | 944M/9.95G [00:00<00:05, 1.52GB/s] pytorch_model-00001-of-00003.bin: 12%|█▏ | 1.22G/9.95G [00:00<00:04, 1.88GB/s] pytorch_model-00001-of-00003.bin: 15%|█▍ | 1.49G/9.95G [00:01<00:04, 2.08GB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.76G/9.95G [00:01<00:03, 2.26GB/s] pytorch_model-00001-of-00003.bin: 20%|██ | 1.99G/9.95G [00:01<00:03, 2.25GB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 2.22G/9.95G [00:01<00:03, 2.06GB/s] pytorch_model-00001-of-00003.bin: 24%|██▍ | 2.43G/9.95G [00:01<00:04, 1.76GB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.76G/9.95G [00:01<00:03, 2.13GB/s] pytorch_model-00001-of-00003.bin: 30%|███ | 2.99G/9.95G [00:01<00:03, 2.05GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.25G/9.95G [00:01<00:03, 2.19GB/s] pytorch_model-00001-of-00003.bin: 35%|███▍ | 3.48G/9.95G [00:02<00:02, 2.17GB/s] pytorch_model-00001-of-00003.bin: 37%|███▋ | 3.71G/9.95G [00:02<00:02, 2.21GB/s] pytorch_model-00001-of-00003.bin: 40%|███▉ | 3.95G/9.95G [00:02<00:02, 2.26GB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 4.19G/9.95G [00:02<00:02, 2.30GB/s] pytorch_model-00001-of-00003.bin: 45%|████▍ | 4.44G/9.95G [00:02<00:02, 2.29GB/s] pytorch_model-00001-of-00003.bin: 47%|████▋ | 4.69G/9.95G [00:02<00:02, 2.35GB/s] pytorch_model-00001-of-00003.bin: 50%|████▉ | 4.93G/9.95G [00:02<00:02, 2.31GB/s] pytorch_model-00001-of-00003.bin: 52%|█████▏ | 5.17G/9.95G [00:02<00:02, 2.22GB/s] pytorch_model-00001-of-00003.bin: 54%|█████▍ | 5.42G/9.95G [00:02<00:01, 2.29GB/s] pytorch_model-00001-of-00003.bin: 57%|█████▋ | 5.66G/9.95G [00:02<00:02, 2.10GB/s] pytorch_model-00001-of-00003.bin: 59%|█████▉ | 5.90G/9.95G [00:03<00:01, 2.18GB/s] pytorch_model-00001-of-00003.bin: 62%|██████▏ | 6.13G/9.95G [00:03<00:01, 2.09GB/s] pytorch_model-00001-of-00003.bin: 65%|██████▍ | 6.42G/9.95G [00:03<00:01, 2.23GB/s] pytorch_model-00001-of-00003.bin: 68%|██████▊ | 6.74G/9.95G [00:03<00:01, 2.51GB/s] pytorch_model-00001-of-00003.bin: 70%|███████ | 7.00G/9.95G [00:03<00:01, 2.39GB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 7.26G/9.95G [00:03<00:01, 2.34GB/s] pytorch_model-00001-of-00003.bin: 75%|███████▌ | 7.50G/9.95G [00:03<00:01, 2.28GB/s] pytorch_model-00001-of-00003.bin: 78%|███████▊ | 7.78G/9.95G [00:03<00:00, 2.39GB/s] pytorch_model-00001-of-00003.bin: 81%|████████ | 8.04G/9.95G [00:03<00:00, 2.42GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 8.29G/9.95G [00:04<00:00, 2.06GB/s] pytorch_model-00001-of-00003.bin: 86%|████████▌ | 8.51G/9.95G [00:04<00:00, 1.91GB/s] pytorch_model-00001-of-00003.bin: 88%|████████▊ | 8.71G/9.95G [00:04<00:00, 1.93GB/s] pytorch_model-00001-of-00003.bin: 91%|█████████ | 9.01G/9.95G [00:04<00:00, 2.18GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.24G/9.95G [00:04<00:00, 2.19GB/s] pytorch_model-00001-of-00003.bin: 96%|█████████▋| 9.58G/9.95G [00:04<00:00, 2.54GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.93G/9.95G [00:04<00:00, 2.24GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:04<00:00, 1.99GB/s]
chaiml-phase2-winner-13b2-v275-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<02:38, 62.4MB/s] pytorch_model-00002-of-00003.bin: 1%|▏ | 126M/9.90G [00:00<00:18, 542MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 304M/9.90G [00:00<00:09, 986MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 451M/9.90G [00:00<00:08, 1.15GB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 587M/9.90G [00:00<00:07, 1.22GB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 724M/9.90G [00:00<00:08, 1.12GB/s] pytorch_model-00002-of-00003.bin: 10%|█ | 1.03G/9.90G [00:00<00:05, 1.67GB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 1.31G/9.90G [00:00<00:04, 1.99GB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.64G/9.90G [00:01<00:03, 2.34GB/s] pytorch_model-00002-of-00003.bin: 19%|█▉ | 1.89G/9.90G [00:01<00:04, 1.90GB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 2.20G/9.90G [00:01<00:03, 2.21GB/s] pytorch_model-00002-of-00003.bin: 25%|██▍ | 2.44G/9.90G [00:01<00:03, 2.23GB/s] pytorch_model-00002-of-00003.bin: 28%|██▊ | 2.74G/9.90G [00:01<00:02, 2.41GB/s] pytorch_model-00002-of-00003.bin: 30%|███ | 3.00G/9.90G [00:01<00:03, 2.12GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.29G/9.90G [00:01<00:02, 2.31GB/s] pytorch_model-00002-of-00003.bin: 36%|███▌ | 3.54G/9.90G [00:01<00:02, 2.30GB/s] pytorch_model-00002-of-00003.bin: 39%|███▊ | 3.84G/9.90G [00:02<00:02, 2.47GB/s] pytorch_model-00002-of-00003.bin: 41%|████▏ | 4.10G/9.90G [00:02<00:02, 2.30GB/s] pytorch_model-00002-of-00003.bin: 44%|████▍ | 4.34G/9.90G [00:02<00:02, 2.22GB/s] pytorch_model-00002-of-00003.bin: 46%|████▌ | 4.57G/9.90G [00:02<00:02, 2.17GB/s] pytorch_model-00002-of-00003.bin: 49%|████▉ | 4.89G/9.90G [00:02<00:02, 2.43GB/s] pytorch_model-00002-of-00003.bin: 52%|█████▏ | 5.14G/9.90G [00:02<00:02, 2.33GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▍ | 5.44G/9.90G [00:02<00:01, 2.49GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 5.73G/9.90G [00:02<00:01, 2.54GB/s] pytorch_model-00002-of-00003.bin: 61%|██████ | 6.03G/9.90G [00:02<00:01, 2.67GB/s] pytorch_model-00002-of-00003.bin: 64%|██████▍ | 6.35G/9.90G [00:03<00:01, 2.77GB/s] pytorch_model-00002-of-00003.bin: 67%|██████▋ | 6.64G/9.90G [00:03<00:01, 2.77GB/s] pytorch_model-00002-of-00003.bin: 70%|██████▉ | 6.92G/9.90G [00:03<00:01, 2.48GB/s] pytorch_model-00002-of-00003.bin: 73%|███████▎ | 7.24G/9.90G [00:03<00:01, 2.63GB/s] pytorch_model-00002-of-00003.bin: 76%|███████▌ | 7.51G/9.90G [00:03<00:00, 2.61GB/s] pytorch_model-00002-of-00003.bin: 79%|███████▊ | 7.78G/9.90G [00:03<00:00, 2.33GB/s] pytorch_model-00002-of-00003.bin: 81%|████████ | 8.02G/9.90G [00:03<00:00, 2.09GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▍ | 8.32G/9.90G [00:03<00:00, 2.30GB/s] pytorch_model-00002-of-00003.bin: 86%|████████▋ | 8.56G/9.90G [00:03<00:00, 2.21GB/s] pytorch_model-00002-of-00003.bin: 89%|████████▊ | 8.79G/9.90G [00:04<00:00, 2.10GB/s] pytorch_model-00002-of-00003.bin: 91%|█████████ | 9.01G/9.90G [00:04<00:00, 2.11GB/s] pytorch_model-00002-of-00003.bin: 93%|█████████▎| 9.22G/9.90G [00:04<00:00, 1.83GB/s] pytorch_model-00002-of-00003.bin: 95%|█████████▌| 9.42G/9.90G [00:04<00:00, 1.18GB/s] pytorch_model-00002-of-00003.bin: 97%|█████████▋| 9.58G/9.90G [00:04<00:00, 1.05GB/s] pytorch_model-00002-of-00003.bin: 98%|█████████▊| 9.75G/9.90G [00:05<00:00, 1.16GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:05<00:00, 1.93GB/s]
chaiml-phase2-winner-13b2-v275-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<01:06, 92.4MB/s] pytorch_model-00003-of-00003.bin: 1%| | 52.4M/6.18G [00:00<00:22, 269MB/s] pytorch_model-00003-of-00003.bin: 4%|▍ | 273M/6.18G [00:00<00:05, 1.11GB/s] pytorch_model-00003-of-00003.bin: 6%|▋ | 388M/6.18G [00:00<00:06, 960MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 503M/6.18G [00:00<00:05, 1.02GB/s] pytorch_model-00003-of-00003.bin: 11%|█▏ | 703M/6.18G [00:00<00:04, 1.27GB/s] pytorch_model-00003-of-00003.bin: 16%|█▋ | 1.02G/6.18G [00:00<00:02, 1.83GB/s] pytorch_model-00003-of-00003.bin: 22%|██▏ | 1.37G/6.18G [00:00<00:02, 2.32GB/s] pytorch_model-00003-of-00003.bin: 26%|██▋ | 1.63G/6.18G [00:00<00:01, 2.33GB/s] pytorch_model-00003-of-00003.bin: 30%|███ | 1.87G/6.18G [00:01<00:01, 2.16GB/s] pytorch_model-00003-of-00003.bin: 34%|███▍ | 2.10G/6.18G [00:01<00:01, 2.14GB/s] pytorch_model-00003-of-00003.bin: 38%|███▊ | 2.32G/6.18G [00:01<00:01, 2.01GB/s] pytorch_model-00003-of-00003.bin: 41%|████ | 2.55G/6.18G [00:01<00:01, 2.07GB/s] pytorch_model-00003-of-00003.bin: 47%|████▋ | 2.89G/6.18G [00:01<00:01, 2.44GB/s] pytorch_model-00003-of-00003.bin: 51%|█████ | 3.15G/6.18G [00:01<00:01, 2.45GB/s] pytorch_model-00003-of-00003.bin: 55%|█████▌ | 3.42G/6.18G [00:01<00:01, 2.52GB/s] pytorch_model-00003-of-00003.bin: 60%|█████▉ | 3.68G/6.18G [00:01<00:01, 2.22GB/s] pytorch_model-00003-of-00003.bin: 64%|██████▎ | 3.93G/6.18G [00:02<00:00, 2.27GB/s] pytorch_model-00003-of-00003.bin: 69%|██████▊ | 4.25G/6.18G [00:02<00:00, 2.49GB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 4.53G/6.18G [00:02<00:00, 2.55GB/s] pytorch_model-00003-of-00003.bin: 78%|███████▊ | 4.79G/6.18G [00:02<00:00, 2.42GB/s] pytorch_model-00003-of-00003.bin: 82%|████████▏ | 5.04G/6.18G [00:02<00:00, 2.35GB/s] pytorch_model-00003-of-00003.bin: 87%|████████▋ | 5.37G/6.18G [00:02<00:00, 2.58GB/s] pytorch_model-00003-of-00003.bin: 95%|█████████▌| 5.87G/6.18G [00:02<00:00, 2.93GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.17G/6.18G [00:03<00:00, 1.25GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:05<00:00, 1.23GB/s]
chaiml-phase2-winner-13b2-v275-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, 2.10MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 3.96MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 31.0MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 10.6MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: tokenizer_config.json: 0%| | 0.00/725 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 9.72MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: Downloaded to shared memory in 17.228s
chaiml-phase2-winner-13b2-v275-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v275-mkmlizer: Saving mkml model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v275-mkmlizer: Reading /tmp/tmpnprdyvow/pytorch_model.bin.index.json
chaiml-phase2-winner-13b2-v275-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:03<18:09, 3.01s/it] Profiling: 38%|███▊ | 139/363 [00:04<00:05, 38.86it/s] Profiling: 77%|███████▋ | 278/363 [00:05<00:01, 68.16it/s] Profiling: 100%|██████████| 363/363 [00:06<00:00, 63.69it/s] Profiling: 100%|██████████| 363/363 [00:06<00:00, 52.29it/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: quantized model in 28.096s
chaiml-phase2-winner-13b2-v275-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 47.036s
chaiml-phase2-winner-13b2-v275-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v275-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v275-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275/config.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275/special_tokens_map.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275/tokenizer.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275/tokenizer_config.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275/tokenizer.model
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v275/mkml_model.tensors
chaiml-phase2-winner-13b2-v275-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
chaiml-phase2-winner-13b2-v275-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-v275-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v275-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 13.5MB/s]
chaiml-phase2-winner-13b2-v275-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-v275-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v275-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.82MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 12.6MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 20.0MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 19.9MB/s]
chaiml-phase2-winner-13b2-v275-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-v275-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v275-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<01:00, 23.6MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:05, 246MB/s] pytorch_model.bin: 25%|██▌ | 367M/1.44G [00:00<00:01, 852MB/s] pytorch_model.bin: 36%|███▋ | 524M/1.44G [00:01<00:01, 622MB/s] pytorch_model.bin: 44%|████▍ | 637M/1.44G [00:01<00:01, 514MB/s] pytorch_model.bin: 50%|████▉ | 721M/1.44G [00:02<00:02, 241MB/s] pytorch_model.bin: 54%|█████▍ | 784M/1.44G [00:02<00:02, 268MB/s] pytorch_model.bin: 59%|█████▊ | 847M/1.44G [00:02<00:02, 295MB/s] pytorch_model.bin: 65%|██████▌ | 941M/1.44G [00:02<00:01, 377MB/s] pytorch_model.bin: 75%|███████▍ | 1.08G/1.44G [00:02<00:00, 517MB/s] pytorch_model.bin: 88%|████████▊ | 1.27G/1.44G [00:02<00:00, 761MB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 496MB/s]
chaiml-phase2-winner-13b2-v275-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v275-mkmlizer: Saving duration: 0.274s
chaiml-phase2-winner-13b2-v275-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.266s
chaiml-phase2-winner-13b2-v275-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v275-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v275-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/config.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/merges.txt
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/vocab.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/tokenizer.json
chaiml-phase2-winner-13b2-v275-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v275_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v275-mkmlizer completed after 76.36s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v275-mkmlizer
Pipeline stage MKMLizer completed in 81.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v275
Waiting for inference service chaiml-phase2-winner-13b2-v275 to be ready
Inference service chaiml-phase2-winner-13b2-v275 ready after 50.28466057777405s
Pipeline stage ISVCDeployer completed in 58.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0040297508239746s
Received healthy response to inference request in 1.4405145645141602s
Received healthy response to inference request in 1.4061336517333984s
Received healthy response to inference request in 1.3850796222686768s
Received healthy response to inference request in 1.4384500980377197s
5 requests
0 failed requests
5th percentile: 1.3892904281616212
10th percentile: 1.3935012340545654
20th percentile: 1.401922845840454
30th percentile: 1.4125969409942627
40th percentile: 1.4255235195159912
50th percentile: 1.4384500980377197
60th percentile: 1.4392758846282958
70th percentile: 1.4401016712188721
80th percentile: 1.5532176017761232
90th percentile: 1.778623676300049
95th percentile: 1.8913267135620115
99th percentile: 1.981489143371582
mean time: 1.534841537475586
Pipeline stage StressChecker completed in 8.55s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
chaiml-phase2-winner-13b2_v275 status is now deployed due to DeploymentManager action
chaiml-phase2-winner-13b2_v275 status is now inactive due to auto deactivation removed underperforming models
chaiml-phase2-winner-13b2_v275 status is now deployed due to admin request
chaiml-phase2-winner-13b2_v275 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics