submission_id: nousresearch-hermes-2-pr_1418_v4
developer_uid: chai_backend_admin
status: torndown
model_repo: NousResearch/Hermes-2-Pro-Mistral-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, '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}:', 'truncate_by_message': False}
reward_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}:', 'truncate_by_message': False}
timestamp: 2024-04-02T17:41:19+00:00
model_name: auto_submit_ricum_mowenonoya
model_eval_status: success
model_group: NousResearch/Hermes-2-Pr
num_battles: 23619
num_wins: 10117
celo_rating: 1103.66
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241994240.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: auto_submit_ricum_mowenonoya
ineligible_reason: propriety_total_count < 800
language_model: NousResearch/Hermes-2-Pro-Mistral-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-02
win_ratio: 0.4283415893983657
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-hermes-2-pr-1418-v4-mkmlizer
Waiting for job on nousresearch-hermes-2-pr-1418-v4-mkmlizer to finish
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ _____ __ __ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ /___/ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ Version: 0.6.11 ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ belonging to: ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ Chai Research Corp. ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-hermes-2-pr-1418-v4-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.5MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: README.md: 0%| | 0.00/18.3k [00:00<?, ?B/s] README.md: 100%|██████████| 18.3k/18.3k [00:00<00:00, 188MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: added_tokens.json: 0%| | 0.00/643 [00:00<?, ?B/s] added_tokens.json: 100%|██████████| 643/643 [00:00<00:00, 4.70MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: config.json: 0%| | 0.00/642 [00:00<?, ?B/s] config.json: 100%|██████████| 642/642 [00:00<00:00, 10.6MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: generation_config.json: 0%| | 0.00/136 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 136/136 [00:00<00:00, 2.25MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: model-00001-of-00004.safetensors: 0%| | 0.00/3.95G [00:00<?, ?B/s] model-00001-of-00004.safetensors: 0%| | 10.5M/3.95G [00:00<01:58, 33.3MB/s] model-00001-of-00004.safetensors: 1%|▏ | 52.4M/3.95G [00:00<00:34, 113MB/s] model-00001-of-00004.safetensors: 2%|▏ | 73.4M/3.95G [00:00<00:34, 112MB/s] model-00001-of-00004.safetensors: 3%|▎ | 136M/3.95G [00:00<00:20, 190MB/s] model-00001-of-00004.safetensors: 5%|▌ | 210M/3.95G [00:01<00:12, 304MB/s] model-00001-of-00004.safetensors: 6%|▋ | 252M/3.95G [00:01<00:12, 289MB/s] model-00001-of-00004.safetensors: 10%|█ | 409M/3.95G [00:01<00:06, 573MB/s] model-00001-of-00004.safetensors: 14%|█▍ | 556M/3.95G [00:01<00:04, 781MB/s] model-00001-of-00004.safetensors: 18%|█▊ | 703M/3.95G [00:01<00:03, 946MB/s] model-00001-of-00004.safetensors: 23%|██▎ | 891M/3.95G [00:01<00:02, 1.16GB/s] model-00001-of-00004.safetensors: 27%|██▋ | 1.06G/3.95G [00:01<00:02, 1.30GB/s] model-00001-of-00004.safetensors: 32%|███▏ | 1.25G/3.95G [00:01<00:01, 1.46GB/s] model-00001-of-00004.safetensors: 37%|███▋ | 1.45G/3.95G [00:01<00:01, 1.61GB/s] model-00001-of-00004.safetensors: 44%|████▍ | 1.74G/3.95G [00:02<00:01, 1.85GB/s] model-00001-of-00004.safetensors: 49%|████▉ | 1.93G/3.95G [00:02<00:01, 1.05GB/s] model-00001-of-00004.safetensors: 53%|█████▎ | 2.08G/3.95G [00:02<00:01, 969MB/s] model-00001-of-00004.safetensors: 56%|█████▌ | 2.20G/3.95G [00:02<00:01, 1.02GB/s] model-00001-of-00004.safetensors: 59%|█████▉ | 2.33G/3.95G [00:03<00:02, 705MB/s] model-00001-of-00004.safetensors: 62%|██████▏ | 2.43G/3.95G [00:03<00:02, 672MB/s] model-00001-of-00004.safetensors: 64%|██████▍ | 2.53G/3.95G [00:03<00:02, 632MB/s] model-00001-of-00004.safetensors: 66%|██████▋ | 2.62G/3.95G [00:03<00:01, 674MB/s] model-00001-of-00004.safetensors: 68%|██████▊ | 2.71G/3.95G [00:03<00:02, 560MB/s] model-00001-of-00004.safetensors: 70%|███████ | 2.78G/3.95G [00:03<00:02, 479MB/s] model-00001-of-00004.safetensors: 74%|███████▍ | 2.93G/3.95G [00:04<00:01, 639MB/s] model-00001-of-00004.safetensors: 76%|███████▌ | 3.01G/3.95G [00:04<00:01, 535MB/s] model-00001-of-00004.safetensors: 78%|███████▊ | 3.08G/3.95G [00:04<00:01, 566MB/s] model-00001-of-00004.safetensors: 81%|████████▏ | 3.22G/3.95G [00:04<00:01, 708MB/s] model-00001-of-00004.safetensors: 87%|████████▋ | 3.44G/3.95G [00:04<00:00, 1.02GB/s] model-00001-of-00004.safetensors: 90%|█████████ | 3.57G/3.95G [00:04<00:00, 1.06GB/s] model-00001-of-00004.safetensors: 96%|█████████▌| 3.79G/3.95G [00:04<00:00, 1.34GB/s] model-00001-of-00004.safetensors: 100%|█████████▉| 3.94G/3.95G [00:04<00:00, 1.34GB/s] model-00001-of-00004.safetensors: 100%|█████████▉| 3.95G/3.95G [00:05<00:00, 738MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: model-00002-of-00004.safetensors: 0%| | 0.00/3.93G [00:00<?, ?B/s] model-00002-of-00004.safetensors: 0%| | 10.5M/3.93G [00:00<01:23, 47.0MB/s] model-00002-of-00004.safetensors: 1%| | 21.0M/3.93G [00:00<00:57, 67.6MB/s] model-00002-of-00004.safetensors: 1%| | 41.9M/3.93G [00:00<00:37, 105MB/s] model-00002-of-00004.safetensors: 6%|▌ | 220M/3.93G [00:00<00:06, 617MB/s] model-00002-of-00004.safetensors: 8%|▊ | 304M/3.93G [00:00<00:05, 618MB/s] model-00002-of-00004.safetensors: 10%|▉ | 388M/3.93G [00:00<00:05, 607MB/s] model-00002-of-00004.safetensors: 12%|█▏ | 461M/3.93G [00:00<00:05, 597MB/s] model-00002-of-00004.safetensors: 16%|█▋ | 640M/3.93G [00:01<00:03, 897MB/s] model-00002-of-00004.safetensors: 19%|█▉ | 744M/3.93G [00:01<00:04, 780MB/s] model-00002-of-00004.safetensors: 21%|██▏ | 839M/3.93G [00:01<00:04, 719MB/s] model-00002-of-00004.safetensors: 24%|██▍ | 933M/3.93G [00:01<00:03, 763MB/s] model-00002-of-00004.safetensors: 26%|██▌ | 1.03G/3.93G [00:01<00:04, 625MB/s] model-00002-of-00004.safetensors: 28%|██▊ | 1.11G/3.93G [00:01<00:04, 655MB/s] model-00002-of-00004.safetensors: 30%|███ | 1.20G/3.93G [00:01<00:04, 682MB/s] model-00002-of-00004.safetensors: 32%|███▏ | 1.27G/3.93G [00:02<00:04, 654MB/s] model-00002-of-00004.safetensors: 35%|███▍ | 1.37G/3.93G [00:02<00:03, 749MB/s] model-00002-of-00004.safetensors: 37%|███▋ | 1.46G/3.93G [00:02<00:03, 677MB/s] model-00002-of-00004.safetensors: 39%|███▉ | 1.54G/3.93G [00:02<00:03, 689MB/s] model-00002-of-00004.safetensors: 41%|████ | 1.61G/3.93G [00:02<00:03, 699MB/s] model-00002-of-00004.safetensors: 43%|████▎ | 1.69G/3.93G [00:02<00:03, 629MB/s] model-00002-of-00004.safetensors: 46%|████▌ | 1.80G/3.93G [00:02<00:02, 733MB/s] model-00002-of-00004.safetensors: 48%|████▊ | 1.89G/3.93G [00:02<00:03, 659MB/s] model-00002-of-00004.safetensors: 50%|████▉ | 1.96G/3.93G [00:03<00:03, 600MB/s] model-00002-of-00004.safetensors: 52%|█████▏ | 2.06G/3.93G [00:03<00:02, 641MB/s] model-00002-of-00004.safetensors: 54%|█████▍ | 2.13G/3.93G [00:03<00:03, 533MB/s] model-00002-of-00004.safetensors: 58%|█████▊ | 2.29G/3.93G [00:03<00:02, 756MB/s] model-00002-of-00004.safetensors: 61%|██████ | 2.38G/3.93G [00:03<00:02, 564MB/s] model-00002-of-00004.safetensors: 63%|██████▎ | 2.49G/3.93G [00:03<00:02, 648MB/s] model-00002-of-00004.safetensors: 66%|██████▌ | 2.58G/3.93G [00:04<00:01, 685MB/s] model-00002-of-00004.safetensors: 68%|██████▊ | 2.66G/3.93G [00:04<00:02, 593MB/s] model-00002-of-00004.safetensors: 71%|███████ | 2.78G/3.93G [00:04<00:01, 707MB/s] model-00002-of-00004.safetensors: 73%|███████▎ | 2.86G/3.93G [00:04<00:01, 685MB/s] model-00002-of-00004.safetensors: 75%|███████▌ | 2.95G/3.93G [00:04<00:01, 678MB/s] model-00002-of-00004.safetensors: 79%|███████▉ | 3.10G/3.93G [00:04<00:00, 885MB/s] model-00002-of-00004.safetensors: 82%|████████▏ | 3.22G/3.93G [00:04<00:00, 934MB/s] model-00002-of-00004.safetensors: 86%|████████▋ | 3.39G/3.93G [00:04<00:00, 1.12GB/s] model-00002-of-00004.safetensors: 90%|█████████ | 3.55G/3.93G [00:05<00:00, 1.24GB/s] model-00002-of-00004.safetensors: 98%|█████████▊| 3.86G/3.93G [00:05<00:00, 1.68GB/s] model-00002-of-00004.safetensors: 100%|█████████▉| 3.93G/3.93G [00:08<00:00, 480MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: model-00003-of-00004.safetensors: 0%| | 0.00/3.93G [00:00<?, ?B/s] model-00003-of-00004.safetensors: 0%| | 10.5M/3.93G [00:00<01:28, 44.5MB/s] model-00003-of-00004.safetensors: 2%|▏ | 83.9M/3.93G [00:00<00:12, 302MB/s] model-00003-of-00004.safetensors: 5%|▌ | 210M/3.93G [00:00<00:06, 585MB/s] model-00003-of-00004.safetensors: 9%|▉ | 367M/3.93G [00:00<00:03, 890MB/s] model-00003-of-00004.safetensors: 14%|█▍ | 545M/3.93G [00:00<00:02, 1.15GB/s] model-00003-of-00004.safetensors: 18%|█▊ | 692M/3.93G [00:00<00:02, 1.23GB/s] model-00003-of-00004.safetensors: 21%|██ | 828M/3.93G [00:00<00:02, 1.24GB/s] model-00003-of-00004.safetensors: 27%|██▋ | 1.06G/3.93G [00:00<00:01, 1.52GB/s] model-00003-of-00004.safetensors: 31%|███ | 1.22G/3.93G [00:01<00:01, 1.53GB/s] model-00003-of-00004.safetensors: 36%|███▌ | 1.42G/3.93G [00:01<00:01, 1.65GB/s] model-00003-of-00004.safetensors: 41%|████ | 1.61G/3.93G [00:01<00:01, 1.72GB/s] model-00003-of-00004.safetensors: 46%|████▌ | 1.79G/3.93G [00:01<00:01, 1.72GB/s] model-00003-of-00004.safetensors: 51%|█████ | 2.00G/3.93G [00:01<00:01, 1.76GB/s] model-00003-of-00004.safetensors: 56%|█████▌ | 2.18G/3.93G [00:01<00:01, 1.68GB/s] model-00003-of-00004.safetensors: 61%|██████ | 2.40G/3.93G [00:01<00:00, 1.79GB/s] model-00003-of-00004.safetensors: 67%|██████▋ | 2.63G/3.93G [00:01<00:00, 1.91GB/s] model-00003-of-00004.safetensors: 72%|███████▏ | 2.83G/3.93G [00:01<00:00, 1.89GB/s] model-00003-of-00004.safetensors: 78%|███████▊ | 3.07G/3.93G [00:02<00:00, 2.03GB/s] model-00003-of-00004.safetensors: 84%|████████▎ | 3.29G/3.93G [00:02<00:00, 1.54GB/s] model-00003-of-00004.safetensors: 88%|████████▊ | 3.46G/3.93G [00:02<00:00, 1.23GB/s] model-00003-of-00004.safetensors: 92%|█████████▏| 3.61G/3.93G [00:02<00:00, 844MB/s] model-00003-of-00004.safetensors: 95%|█████████▍| 3.73G/3.93G [00:02<00:00, 847MB/s] model-00003-of-00004.safetensors: 100%|█████████▉| 3.93G/3.93G [00:03<00:00, 1.26GB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: model-00004-of-00004.safetensors: 0%| | 0.00/2.68G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 0%| | 10.5M/2.68G [00:00<01:01, 43.5MB/s] model-00004-of-00004.safetensors: 3%|▎ | 83.9M/2.68G [00:00<00:08, 294MB/s] model-00004-of-00004.safetensors: 7%|▋ | 178M/2.68G [00:00<00:05, 475MB/s] model-00004-of-00004.safetensors: 11%|█ | 283M/2.68G [00:00<00:03, 650MB/s] model-00004-of-00004.safetensors: 16%|█▋ | 440M/2.68G [00:00<00:02, 930MB/s] model-00004-of-00004.safetensors: 23%|██▎ | 629M/2.68G [00:00<00:01, 1.18GB/s] model-00004-of-00004.safetensors: 33%|███▎ | 881M/2.68G [00:00<00:01, 1.56GB/s] model-00004-of-00004.safetensors: 39%|███▉ | 1.05G/2.68G [00:00<00:01, 1.56GB/s] model-00004-of-00004.safetensors: 45%|████▌ | 1.22G/2.68G [00:01<00:01, 1.43GB/s] model-00004-of-00004.safetensors: 55%|█████▍ | 1.47G/2.68G [00:01<00:00, 1.61GB/s] model-00004-of-00004.safetensors: 61%|██████ | 1.64G/2.68G [00:01<00:00, 1.61GB/s] model-00004-of-00004.safetensors: 68%|██████▊ | 1.82G/2.68G [00:01<00:00, 1.68GB/s] model-00004-of-00004.safetensors: 76%|███████▌ | 2.03G/2.68G [00:01<00:00, 1.70GB/s] model-00004-of-00004.safetensors: 82%|████████▏ | 2.21G/2.68G [00:01<00:00, 1.72GB/s] model-00004-of-00004.safetensors: 100%|█████████▉| 2.67G/2.68G [00:01<00:00, 2.52GB/s] model-00004-of-00004.safetensors: 100%|█████████▉| 2.68G/2.68G [00:01<00:00, 1.41GB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: model.safetensors.index.json: 0%| | 0.00/23.9k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 141MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: special_tokens_map.json: 0%| | 0.00/557 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 557/557 [00:00<00:00, 6.25MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 39.6MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/6.81k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 6.81k/6.81k [00:00<00:00, 45.8MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Downloaded to shared memory in 22.844s
nousresearch-hermes-2-pr-1418-v4-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Saving mkml model at /dev/shm/model_cache
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Reading /tmp/tmpb1ru78ak/model.safetensors.index.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:21, 1.32s/it] Profiling: 4%|▍ | 12/291 [00:01<00:24, 11.37it/s] Profiling: 8%|▊ | 22/291 [00:01<00:12, 21.91it/s] Profiling: 11%|█ | 32/291 [00:01<00:07, 32.87it/s] Profiling: 15%|█▌ | 45/291 [00:01<00:05, 49.09it/s] Profiling: 20%|█▉ | 57/291 [00:01<00:03, 62.58it/s] Profiling: 23%|██▎ | 68/291 [00:01<00:03, 68.33it/s] Profiling: 27%|██▋ | 79/291 [00:02<00:03, 56.20it/s] Profiling: 31%|███ | 90/291 [00:02<00:03, 65.01it/s] Profiling: 35%|███▌ | 103/291 [00:02<00:02, 78.30it/s] Profiling: 40%|███▉ | 116/291 [00:02<00:01, 87.66it/s] Profiling: 44%|████▎ | 127/291 [00:02<00:01, 88.21it/s] Profiling: 49%|████▉ | 142/291 [00:02<00:01, 98.49it/s] Profiling: 53%|█████▎ | 154/291 [00:02<00:01, 99.04it/s] Profiling: 57%|█████▋ | 165/291 [00:03<00:01, 72.27it/s] Profiling: 60%|██████ | 176/291 [00:03<00:01, 78.50it/s] Profiling: 66%|██████▌ | 192/291 [00:03<00:01, 95.59it/s] Profiling: 70%|██████▉ | 203/291 [00:03<00:00, 96.70it/s] Profiling: 75%|███████▌ | 219/291 [00:03<00:00, 110.74it/s] Profiling: 79%|███████▉ | 231/291 [00:03<00:00, 109.44it/s] Profiling: 84%|████████▎ | 243/291 [00:05<00:02, 23.27it/s] Profiling: 88%|████████▊ | 256/291 [00:05<00:01, 30.81it/s] Profiling: 92%|█████████▏| 267/291 [00:05<00:00, 37.64it/s] Profiling: 97%|█████████▋| 283/291 [00:05<00:00, 51.03it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 50.08it/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-hermes-2-pr-1418-v4-mkmlizer: quantized model in 16.597s
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Processed model NousResearch/Hermes-2-Pro-Mistral-7B in 40.395s
nousresearch-hermes-2-pr-1418-v4-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-hermes-2-pr-1418-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/config.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/added_tokens.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/tokenizer_config.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/tokenizer.model
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/special_tokens_map.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/tokenizer.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v4/mkml_model.tensors
nousresearch-hermes-2-pr-1418-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-hermes-2-pr-1418-v4-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.
nousresearch-hermes-2-pr-1418-v4-mkmlizer: warnings.warn(
nousresearch-hermes-2-pr-1418-v4-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.2MB/s]
nousresearch-hermes-2-pr-1418-v4-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.
nousresearch-hermes-2-pr-1418-v4-mkmlizer: warnings.warn(
nousresearch-hermes-2-pr-1418-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.75MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.21MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.15MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 38.1MB/s]
nousresearch-hermes-2-pr-1418-v4-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.
nousresearch-hermes-2-pr-1418-v4-mkmlizer: warnings.warn(
nousresearch-hermes-2-pr-1418-v4-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:06, 216MB/s] pytorch_model.bin: 5%|▌ | 73.4M/1.44G [00:00<00:04, 291MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:02, 483MB/s] pytorch_model.bin: 17%|█▋ | 241M/1.44G [00:00<00:02, 592MB/s] pytorch_model.bin: 23%|██▎ | 336M/1.44G [00:00<00:01, 705MB/s] pytorch_model.bin: 34%|███▍ | 493M/1.44G [00:00<00:00, 969MB/s] pytorch_model.bin: 50%|████▉ | 721M/1.44G [00:00<00:00, 1.36GB/s] pytorch_model.bin: 62%|██████▏ | 899M/1.44G [00:00<00:00, 1.48GB/s] pytorch_model.bin: 73%|███████▎ | 1.06G/1.44G [00:01<00:00, 1.33GB/s] pytorch_model.bin: 85%|████████▍ | 1.22G/1.44G [00:01<00:00, 1.41GB/s] pytorch_model.bin: 96%|█████████▌| 1.38G/1.44G [00:01<00:00, 1.45GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 284MB/s]
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Saving duration: 0.260s
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.796s
nousresearch-hermes-2-pr-1418-v4-mkmlizer: creating bucket guanaco-reward-models
nousresearch-hermes-2-pr-1418-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-hermes-2-pr-1418-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/config.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/special_tokens_map.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/tokenizer_config.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/merges.txt
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/vocab.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/tokenizer.json
nousresearch-hermes-2-pr-1418-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v4_reward/reward.tensors
Job nousresearch-hermes-2-pr-1418-v4-mkmlizer completed after 64.6s with status: succeeded
Stopping job with name nousresearch-hermes-2-pr-1418-v4-mkmlizer
Pipeline stage MKMLizer completed in 67.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-hermes-2-pr-1418-v4
Waiting for inference service nousresearch-hermes-2-pr-1418-v4 to be ready
Inference service nousresearch-hermes-2-pr-1418-v4 ready after 40.39831042289734s
Pipeline stage ISVCDeployer completed in 48.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.474560260772705s
Received healthy response to inference request in 0.530501127243042s
Received healthy response to inference request in 0.5051398277282715s
Received healthy response to inference request in 0.9006249904632568s
Received healthy response to inference request in 0.3576204776763916s
5 requests
0 failed requests
5th percentile: 0.38712434768676757
10th percentile: 0.41662821769714353
20th percentile: 0.4756359577178955
30th percentile: 0.5102120876312256
40th percentile: 0.5203566074371337
50th percentile: 0.530501127243042
60th percentile: 0.6785506725311279
70th percentile: 0.8266002178192138
80th percentile: 1.0154120445251467
90th percentile: 1.2449861526489259
95th percentile: 1.3597732067108153
99th percentile: 1.451602849960327
mean time: 0.7536893367767334
Pipeline stage StressChecker completed in 5.10s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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
nousresearch-hermes-2-pr_1418_v4 status is now deployed due to DeploymentManager action
nousresearch-hermes-2-pr_1418_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-hermes-2-pr_1418_v4
Running pipeline stage ISVCDeleter
Checking if service nousresearch-hermes-2-pr-1418-v4 is running
Tearing down inference service nousresearch-hermes-2-pr-1418-v4
Toredown service nousresearch-hermes-2-pr-1418-v4
Pipeline stage ISVCDeleter completed in 3.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-hermes-2-pr-1418-v4/added_tokens.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v4/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v4/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.31s
nousresearch-hermes-2-pr_1418_v4 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics