submission_id: chaiml-phase2-winner-13b2_v276
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': 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: 2024-03-31T01:47:25+00:00
model_name: phase2_winner_13b2-64
model_eval_status: success
safety_score: None
entertaining: 6.94
stay_in_character: 8.46
user_preference: 7.52
double_thumbs_up: 1369
thumbs_up: 1898
thumbs_down: 858
num_battles: 129704
num_wins: 64978
win_ratio: 0.5009714426694628
celo_rating: 1153.44
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v276-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v276-mkmlizer to finish
chaiml-phase2-winner-13b2-v276-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ Version: 0.6.11 ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v276-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-phase2-winner-13b2-v276-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.0MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: README.md: 0%| | 0.00/1.53k [00:00<?, ?B/s] README.md: 100%|██████████| 1.53k/1.53k [00:00<00:00, 12.6MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: config.json: 0%| | 0.00/651 [00:00<?, ?B/s] config.json: 100%|██████████| 651/651 [00:00<00:00, 10.7MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: generation_config.json: 0%| | 0.00/170 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 170/170 [00:00<00:00, 1.62MB/s]
chaiml-phase2-winner-13b2-v276-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<00:56, 175MB/s] pytorch_model-00001-of-00003.bin: 1%| | 62.9M/9.95G [00:00<00:34, 287MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 199M/9.95G [00:00<00:13, 725MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 346M/9.95G [00:00<00:09, 999MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 577M/9.95G [00:00<00:06, 1.34GB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 713M/9.95G [00:00<00:06, 1.34GB/s] pytorch_model-00001-of-00003.bin: 9%|▊ | 849M/9.95G [00:00<00:06, 1.31GB/s] pytorch_model-00001-of-00003.bin: 11%|█ | 1.11G/9.95G [00:00<00:05, 1.67GB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 1.44G/9.95G [00:00<00:04, 2.10GB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 1.75G/9.95G [00:01<00:03, 2.40GB/s] pytorch_model-00001-of-00003.bin: 20%|██ | 2.00G/9.95G [00:01<00:03, 2.17GB/s] pytorch_model-00001-of-00003.bin: 22%|██▏ | 2.23G/9.95G [00:01<00:03, 2.15GB/s] pytorch_model-00001-of-00003.bin: 25%|██▍ | 2.45G/9.95G [00:01<00:03, 2.04GB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.78G/9.95G [00:01<00:03, 2.31GB/s] pytorch_model-00001-of-00003.bin: 30%|███ | 3.02G/9.95G [00:01<00:03, 2.28GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.25G/9.95G [00:01<00:03, 2.22GB/s] pytorch_model-00001-of-00003.bin: 35%|███▍ | 3.48G/9.95G [00:01<00:03, 2.07GB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 3.75G/9.95G [00:02<00:02, 2.23GB/s] pytorch_model-00001-of-00003.bin: 40%|████ | 4.00G/9.95G [00:02<00:02, 2.27GB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 4.23G/9.95G [00:02<00:02, 2.27GB/s] pytorch_model-00001-of-00003.bin: 45%|████▌ | 4.48G/9.95G [00:02<00:02, 2.31GB/s] pytorch_model-00001-of-00003.bin: 47%|████▋ | 4.72G/9.95G [00:02<00:02, 2.21GB/s] pytorch_model-00001-of-00003.bin: 50%|████▉ | 4.96G/9.95G [00:02<00:02, 2.26GB/s] pytorch_model-00001-of-00003.bin: 52%|█████▏ | 5.19G/9.95G [00:02<00:02, 2.24GB/s] pytorch_model-00001-of-00003.bin: 55%|█████▌ | 5.49G/9.95G [00:02<00:01, 2.46GB/s] pytorch_model-00001-of-00003.bin: 58%|█████▊ | 5.75G/9.95G [00:02<00:01, 2.26GB/s] pytorch_model-00001-of-00003.bin: 60%|██████ | 5.98G/9.95G [00:03<00:01, 2.09GB/s] pytorch_model-00001-of-00003.bin: 63%|██████▎ | 6.29G/9.95G [00:03<00:01, 2.32GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▋ | 6.60G/9.95G [00:03<00:01, 2.49GB/s] pytorch_model-00001-of-00003.bin: 69%|██████▉ | 6.90G/9.95G [00:03<00:01, 2.64GB/s] pytorch_model-00001-of-00003.bin: 72%|███████▏ | 7.17G/9.95G [00:03<00:01, 2.56GB/s] pytorch_model-00001-of-00003.bin: 75%|███████▍ | 7.43G/9.95G [00:03<00:01, 2.18GB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 7.69G/9.95G [00:03<00:01, 2.24GB/s] pytorch_model-00001-of-00003.bin: 80%|███████▉ | 7.93G/9.95G [00:03<00:00, 2.25GB/s] pytorch_model-00001-of-00003.bin: 84%|████████▍ | 8.34G/9.95G [00:03<00:00, 2.51GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 8.67G/9.95G [00:04<00:00, 2.71GB/s] pytorch_model-00001-of-00003.bin: 90%|█████████ | 8.95G/9.95G [00:04<00:00, 2.47GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.22G/9.95G [00:04<00:00, 2.42GB/s] pytorch_model-00001-of-00003.bin: 97%|█████████▋| 9.70G/9.95G [00:04<00:00, 2.61GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:04<00:00, 2.02GB/s]
chaiml-phase2-winner-13b2-v276-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<02:17, 72.1MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 189M/9.90G [00:00<00:12, 794MB/s] pytorch_model-00002-of-00003.bin: 4%|▎ | 367M/9.90G [00:00<00:08, 1.13GB/s] pytorch_model-00002-of-00003.bin: 5%|▌ | 514M/9.90G [00:00<00:07, 1.23GB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 682M/9.90G [00:00<00:06, 1.37GB/s] pytorch_model-00002-of-00003.bin: 9%|▉ | 891M/9.90G [00:00<00:05, 1.56GB/s] pytorch_model-00002-of-00003.bin: 11%|█▏ | 1.13G/9.90G [00:00<00:04, 1.80GB/s] pytorch_model-00002-of-00003.bin: 15%|█▍ | 1.45G/9.90G [00:00<00:03, 2.21GB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 1.68G/9.90G [00:01<00:03, 2.23GB/s] pytorch_model-00002-of-00003.bin: 20%|█▉ | 1.94G/9.90G [00:01<00:03, 2.35GB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 2.18G/9.90G [00:01<00:03, 2.22GB/s] pytorch_model-00002-of-00003.bin: 24%|██▍ | 2.42G/9.90G [00:01<00:03, 2.24GB/s] pytorch_model-00002-of-00003.bin: 28%|██▊ | 2.74G/9.90G [00:01<00:02, 2.49GB/s] pytorch_model-00002-of-00003.bin: 30%|███ | 3.02G/9.90G [00:01<00:02, 2.58GB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 3.28G/9.90G [00:01<00:02, 2.24GB/s] pytorch_model-00002-of-00003.bin: 36%|███▌ | 3.52G/9.90G [00:01<00:02, 2.27GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 3.76G/9.90G [00:01<00:02, 2.17GB/s] pytorch_model-00002-of-00003.bin: 41%|████ | 4.02G/9.90G [00:02<00:02, 2.25GB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 4.30G/9.90G [00:02<00:02, 2.39GB/s] pytorch_model-00002-of-00003.bin: 46%|████▌ | 4.55G/9.90G [00:02<00:02, 2.36GB/s] pytorch_model-00002-of-00003.bin: 49%|████▉ | 4.83G/9.90G [00:02<00:02, 2.44GB/s] pytorch_model-00002-of-00003.bin: 52%|█████▏ | 5.12G/9.90G [00:02<00:01, 2.53GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▌ | 5.45G/9.90G [00:02<00:01, 2.76GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 5.74G/9.90G [00:02<00:01, 2.25GB/s] pytorch_model-00002-of-00003.bin: 60%|██████ | 5.99G/9.90G [00:02<00:01, 2.22GB/s] pytorch_model-00002-of-00003.bin: 63%|██████▎ | 6.26G/9.90G [00:02<00:01, 2.28GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▌ | 6.50G/9.90G [00:03<00:01, 2.17GB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 6.75G/9.90G [00:03<00:01, 2.25GB/s] pytorch_model-00002-of-00003.bin: 71%|███████▏ | 7.06G/9.90G [00:03<00:01, 2.44GB/s] pytorch_model-00002-of-00003.bin: 74%|███████▍ | 7.37G/9.90G [00:03<00:00, 2.61GB/s] pytorch_model-00002-of-00003.bin: 77%|███████▋ | 7.64G/9.90G [00:03<00:00, 2.35GB/s] pytorch_model-00002-of-00003.bin: 80%|███████▉ | 7.90G/9.90G [00:03<00:00, 2.16GB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 8.13G/9.90G [00:03<00:00, 2.05GB/s] pytorch_model-00002-of-00003.bin: 85%|████████▍ | 8.41G/9.90G [00:03<00:00, 2.23GB/s] pytorch_model-00002-of-00003.bin: 87%|████████▋ | 8.64G/9.90G [00:04<00:00, 2.04GB/s] pytorch_model-00002-of-00003.bin: 89%|████████▉ | 8.86G/9.90G [00:04<00:00, 2.06GB/s] pytorch_model-00002-of-00003.bin: 92%|█████████▏| 9.08G/9.90G [00:04<00:00, 1.97GB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▍| 9.29G/9.90G [00:04<00:00, 1.95GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 9.52G/9.90G [00:04<00:00, 2.03GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.89G/9.90G [00:04<00:00, 2.31GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:04<00:00, 2.09GB/s]
chaiml-phase2-winner-13b2-v276-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<01:34, 65.6MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 136M/6.18G [00:00<00:10, 601MB/s] pytorch_model-00003-of-00003.bin: 4%|▍ | 262M/6.18G [00:00<00:06, 856MB/s] pytorch_model-00003-of-00003.bin: 6%|▌ | 377M/6.18G [00:00<00:06, 909MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 482M/6.18G [00:00<00:07, 715MB/s] pytorch_model-00003-of-00003.bin: 9%|▉ | 566M/6.18G [00:00<00:08, 685MB/s] pytorch_model-00003-of-00003.bin: 12%|█▏ | 734M/6.18G [00:00<00:06, 825MB/s] pytorch_model-00003-of-00003.bin: 16%|█▌ | 996M/6.18G [00:01<00:04, 1.24GB/s] pytorch_model-00003-of-00003.bin: 21%|██ | 1.31G/6.18G [00:01<00:02, 1.71GB/s] pytorch_model-00003-of-00003.bin: 24%|██▍ | 1.51G/6.18G [00:01<00:03, 1.35GB/s] pytorch_model-00003-of-00003.bin: 27%|██▋ | 1.70G/6.18G [00:01<00:03, 1.47GB/s] pytorch_model-00003-of-00003.bin: 30%|███ | 1.88G/6.18G [00:01<00:02, 1.50GB/s] pytorch_model-00003-of-00003.bin: 33%|███▎ | 2.04G/6.18G [00:01<00:03, 1.35GB/s] pytorch_model-00003-of-00003.bin: 36%|███▌ | 2.20G/6.18G [00:01<00:02, 1.39GB/s] pytorch_model-00003-of-00003.bin: 39%|███▉ | 2.41G/6.18G [00:01<00:02, 1.53GB/s] pytorch_model-00003-of-00003.bin: 42%|████▏ | 2.58G/6.18G [00:02<00:02, 1.40GB/s] pytorch_model-00003-of-00003.bin: 45%|████▍ | 2.77G/6.18G [00:02<00:02, 1.51GB/s] pytorch_model-00003-of-00003.bin: 48%|████▊ | 2.94G/6.18G [00:02<00:02, 1.54GB/s] pytorch_model-00003-of-00003.bin: 50%|█████ | 3.10G/6.18G [00:02<00:02, 1.53GB/s] pytorch_model-00003-of-00003.bin: 54%|█████▍ | 3.34G/6.18G [00:02<00:01, 1.72GB/s] pytorch_model-00003-of-00003.bin: 57%|█████▋ | 3.54G/6.18G [00:02<00:01, 1.76GB/s] pytorch_model-00003-of-00003.bin: 60%|██████ | 3.73G/6.18G [00:02<00:01, 1.76GB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 3.92G/6.18G [00:02<00:01, 1.78GB/s] pytorch_model-00003-of-00003.bin: 67%|██████▋ | 4.11G/6.18G [00:03<00:01, 1.60GB/s] pytorch_model-00003-of-00003.bin: 70%|██████▉ | 4.30G/6.18G [00:03<00:01, 1.60GB/s] pytorch_model-00003-of-00003.bin: 72%|███████▏ | 4.47G/6.18G [00:03<00:01, 1.49GB/s] pytorch_model-00003-of-00003.bin: 77%|███████▋ | 4.73G/6.18G [00:03<00:00, 1.77GB/s] pytorch_model-00003-of-00003.bin: 80%|████████ | 4.97G/6.18G [00:03<00:00, 1.92GB/s] pytorch_model-00003-of-00003.bin: 84%|████████▎ | 5.17G/6.18G [00:03<00:00, 1.66GB/s] pytorch_model-00003-of-00003.bin: 87%|████████▋ | 5.36G/6.18G [00:03<00:00, 1.71GB/s] pytorch_model-00003-of-00003.bin: 90%|████████▉ | 5.55G/6.18G [00:03<00:00, 1.62GB/s] pytorch_model-00003-of-00003.bin: 96%|█████████▌| 5.91G/6.18G [00:03<00:00, 2.11GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.17G/6.18G [00:04<00:00, 1.93GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:04<00:00, 1.46GB/s]
chaiml-phase2-winner-13b2-v276-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, 179MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 3.61MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 15.2MB/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 15.2MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 48.2MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: tokenizer_config.json: 0%| | 0.00/725 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 12.0MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: Downloaded to shared memory in 15.617s
chaiml-phase2-winner-13b2-v276-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v276-mkmlizer: Saving mkml model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v276-mkmlizer: Reading /tmp/tmpjz1zjyzf/pytorch_model.bin.index.json
chaiml-phase2-winner-13b2-v276-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:03<22:50, 3.79s/it] Profiling: 38%|███▊ | 139/363 [00:05<00:07, 31.94it/s] Profiling: 77%|███████▋ | 278/363 [00:06<00:01, 54.25it/s] Profiling: 100%|██████████| 363/363 [00:08<00:00, 52.93it/s] Profiling: 100%|██████████| 363/363 [00:08<00:00, 42.84it/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: quantized model in 30.026s
chaiml-phase2-winner-13b2-v276-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 47.654s
chaiml-phase2-winner-13b2-v276-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v276-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v276-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v276
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v276/config.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v276/tokenizer_config.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v276/special_tokens_map.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v276/tokenizer.model
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v276/tokenizer.json
chaiml-phase2-winner-13b2-v276-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
chaiml-phase2-winner-13b2-v276-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-v276-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v276-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.7MB/s]
chaiml-phase2-winner-13b2-v276-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-v276-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v276-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.24MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.28MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.25MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 28.4MB/s]
chaiml-phase2-winner-13b2-v276-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-v276-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v276-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:07, 194MB/s] pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:03, 341MB/s] pytorch_model.bin: 15%|█▍ | 210M/1.44G [00:00<00:01, 692MB/s] pytorch_model.bin: 23%|██▎ | 336M/1.44G [00:00<00:01, 889MB/s] pytorch_model.bin: 35%|███▍ | 503M/1.44G [00:00<00:00, 1.15GB/s] pytorch_model.bin: 51%|█████ | 734M/1.44G [00:00<00:00, 1.52GB/s] pytorch_model.bin: 70%|███████ | 1.02G/1.44G [00:00<00:00, 1.91GB/s] pytorch_model.bin: 84%|████████▍ | 1.22G/1.44G [00:00<00:00, 1.88GB/s] pytorch_model.bin: 98%|█████████▊| 1.41G/1.44G [00:01<00:00, 1.00GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 283MB/s]
chaiml-phase2-winner-13b2-v276-mkmlizer: Saving duration: 0.251s
chaiml-phase2-winner-13b2-v276-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 8.610s
chaiml-phase2-winner-13b2-v276-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v276-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v276-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/config.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/merges.txt
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/vocab.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/tokenizer.json
chaiml-phase2-winner-13b2-v276-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v276_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v276-mkmlizer completed after 85.17s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v276-mkmlizer
Pipeline stage MKMLizer completed in 88.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v276
Waiting for inference service chaiml-phase2-winner-13b2-v276 to be ready
Inference service chaiml-phase2-winner-13b2-v276 ready after 50.296366453170776s
Pipeline stage ISVCDeployer completed in 57.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.252856492996216s
Received healthy response to inference request in 1.7505395412445068s
Received healthy response to inference request in 1.7511086463928223s
Received healthy response to inference request in 1.5421233177185059s
Received healthy response to inference request in 1.7405285835266113s
5 requests
0 failed requests
5th percentile: 1.581804370880127
10th percentile: 1.621485424041748
20th percentile: 1.7008475303649901
30th percentile: 1.7425307750701904
40th percentile: 1.7465351581573487
50th percentile: 1.7505395412445068
60th percentile: 1.750767183303833
70th percentile: 1.750994825363159
80th percentile: 1.851458215713501
90th percentile: 2.0521573543548586
95th percentile: 2.152506923675537
99th percentile: 2.23278657913208
mean time: 1.8074313163757325
Pipeline stage StressChecker completed in 10.01s
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
chaiml-phase2-winner-13b2_v276 status is now deployed due to DeploymentManager action
AUTO_DEACTIVATION: submission %s deactivated %s
chaiml-phase2-winner-13b2_v276 status is now inactive due to auto deactivation removed underperforming models
AUTO_DEACTIVATION: submission %s deactivated %s
chaiml-phase2-winner-13b2_v276 status is now deployed due to admin request
chaiml-phase2-winner-13b2_v276 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics