submission_id: cgato-thespis-lucywantst_2658_v8
developer_uid: chai_backend_admin
status: inactive
model_repo: cgato/Thespis-LucyWantsToQuantEdition-7b-v0.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, '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}:'}
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}:'}
timestamp: 2024-04-02T16:34:36+00:00
model_name: auto_submit_ricum_metudotinu
model_eval_status: success
safety_score: 0.72
entertaining: 6.74
stay_in_character: 8.42
user_preference: 7.36
double_thumbs_up: 262
thumbs_up: 365
thumbs_down: 186
num_battles: 24352
num_wins: 10639
win_ratio: 0.4368840341655716
celo_rating: 1109.45
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespis-lucywantst-2658-v8-mkmlizer
Waiting for job on cgato-thespis-lucywantst-2658-v8-mkmlizer to finish
cgato-thespis-lucywantst-2658-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ _____ __ __ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ /___/ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ belonging to: ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ Chai Research Corp. ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ║ ║
cgato-thespis-lucywantst-2658-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespis-lucywantst-2658-v8-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.0MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: README.md: 0%| | 0.00/105 [00:00<?, ?B/s] README.md: 100%|██████████| 105/105 [00:00<00:00, 621kB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: config.json: 0%| | 0.00/631 [00:00<?, ?B/s] config.json: 100%|██████████| 631/631 [00:00<00:00, 9.32MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.17MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/4.94G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 10.5M/4.94G [00:00<03:17, 25.0MB/s] pytorch_model-00001-of-00003.bin: 1%| | 31.5M/4.94G [00:00<01:59, 41.2MB/s] pytorch_model-00001-of-00003.bin: 1%| | 52.4M/4.94G [00:00<01:19, 61.6MB/s] pytorch_model-00001-of-00003.bin: 1%|▏ | 62.9M/4.94G [00:01<01:19, 61.7MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 94.4M/4.94G [00:01<00:49, 97.3MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 210M/4.94G [00:01<00:16, 292MB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 336M/4.94G [00:01<00:09, 490MB/s] pytorch_model-00001-of-00003.bin: 10%|▉ | 493M/4.94G [00:01<00:06, 656MB/s] pytorch_model-00001-of-00003.bin: 12%|█▏ | 577M/4.94G [00:01<00:07, 619MB/s] pytorch_model-00001-of-00003.bin: 13%|█▎ | 650M/4.94G [00:01<00:07, 609MB/s] pytorch_model-00001-of-00003.bin: 15%|█▍ | 724M/4.94G [00:02<00:06, 636MB/s] pytorch_model-00001-of-00003.bin: 17%|█▋ | 849M/4.94G [00:02<00:05, 779MB/s] pytorch_model-00001-of-00003.bin: 25%|██▌ | 1.25G/4.94G [00:02<00:02, 1.60GB/s] pytorch_model-00001-of-00003.bin: 29%|██▉ | 1.43G/4.94G [00:02<00:02, 1.40GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 1.63G/4.94G [00:02<00:02, 1.37GB/s] pytorch_model-00001-of-00003.bin: 36%|███▌ | 1.78G/4.94G [00:03<00:04, 772MB/s] pytorch_model-00001-of-00003.bin: 38%|███▊ | 1.90G/4.94G [00:03<00:03, 771MB/s] pytorch_model-00001-of-00003.bin: 41%|████▏ | 2.04G/4.94G [00:03<00:03, 870MB/s] pytorch_model-00001-of-00003.bin: 46%|████▌ | 2.29G/4.94G [00:03<00:02, 1.16GB/s] pytorch_model-00001-of-00003.bin: 50%|████▉ | 2.46G/4.94G [00:03<00:01, 1.27GB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 2.62G/4.94G [00:03<00:01, 1.34GB/s] pytorch_model-00001-of-00003.bin: 56%|█████▌ | 2.78G/4.94G [00:03<00:01, 1.20GB/s] pytorch_model-00001-of-00003.bin: 61%|██████ | 3.01G/4.94G [00:03<00:01, 1.42GB/s] pytorch_model-00001-of-00003.bin: 64%|██████▍ | 3.18G/4.94G [00:04<00:01, 978MB/s] pytorch_model-00001-of-00003.bin: 67%|██████▋ | 3.31G/4.94G [00:04<00:01, 976MB/s] pytorch_model-00001-of-00003.bin: 70%|███████ | 3.46G/4.94G [00:04<00:01, 1.03GB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 3.59G/4.94G [00:04<00:01, 970MB/s] pytorch_model-00001-of-00003.bin: 75%|███████▍ | 3.70G/4.94G [00:04<00:01, 874MB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 3.81G/4.94G [00:04<00:01, 905MB/s] pytorch_model-00001-of-00003.bin: 80%|████████ | 3.96G/4.94G [00:05<00:00, 1.06GB/s] pytorch_model-00001-of-00003.bin: 83%|████████▎ | 4.08G/4.94G [00:05<00:00, 989MB/s] pytorch_model-00001-of-00003.bin: 85%|████████▍ | 4.19G/4.94G [00:05<00:00, 956MB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 4.30G/4.94G [00:05<00:00, 945MB/s] pytorch_model-00001-of-00003.bin: 91%|█████████ | 4.48G/4.94G [00:05<00:00, 1.17GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 4.62G/4.94G [00:05<00:00, 1.20GB/s] pytorch_model-00001-of-00003.bin: 97%|█████████▋| 4.82G/4.94G [00:05<00:00, 1.41GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 4.94G/4.94G [00:05<00:00, 845MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: pytorch_model-00002-of-00003.bin: 0%| | 0.00/5.00G [00:00<?, ?B/s] pytorch_model-00002-of-00003.bin: 0%| | 10.5M/5.00G [00:00<02:56, 28.3MB/s] pytorch_model-00002-of-00003.bin: 0%| | 21.0M/5.00G [00:01<04:47, 17.3MB/s] pytorch_model-00002-of-00003.bin: 1%|▏ | 62.9M/5.00G [00:01<01:16, 65.0MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 105M/5.00G [00:01<00:43, 113MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 210M/5.00G [00:01<00:17, 270MB/s] pytorch_model-00002-of-00003.bin: 8%|▊ | 377M/5.00G [00:01<00:08, 514MB/s] pytorch_model-00002-of-00003.bin: 9%|▉ | 461M/5.00G [00:01<00:10, 435MB/s] pytorch_model-00002-of-00003.bin: 11%|█ | 535M/5.00G [00:02<00:11, 383MB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 629M/5.00G [00:02<00:09, 475MB/s] pytorch_model-00002-of-00003.bin: 17%|█▋ | 849M/5.00G [00:02<00:05, 806MB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 1.11G/5.00G [00:02<00:03, 1.18GB/s] pytorch_model-00002-of-00003.bin: 29%|██▉ | 1.46G/5.00G [00:02<00:02, 1.71GB/s] pytorch_model-00002-of-00003.bin: 34%|███▎ | 1.68G/5.00G [00:03<00:04, 712MB/s] pytorch_model-00002-of-00003.bin: 37%|███▋ | 1.84G/5.00G [00:03<00:05, 593MB/s] pytorch_model-00002-of-00003.bin: 39%|███▉ | 1.96G/5.00G [00:03<00:04, 616MB/s] pytorch_model-00002-of-00003.bin: 42%|████▏ | 2.11G/5.00G [00:03<00:04, 715MB/s] pytorch_model-00002-of-00003.bin: 45%|████▌ | 2.25G/5.00G [00:04<00:03, 828MB/s] pytorch_model-00002-of-00003.bin: 48%|████▊ | 2.38G/5.00G [00:04<00:03, 804MB/s] pytorch_model-00002-of-00003.bin: 51%|█████▏ | 2.57G/5.00G [00:04<00:02, 994MB/s] pytorch_model-00002-of-00003.bin: 55%|█████▍ | 2.74G/5.00G [00:04<00:01, 1.13GB/s] pytorch_model-00002-of-00003.bin: 60%|██████ | 3.02G/5.00G [00:04<00:01, 1.36GB/s] pytorch_model-00002-of-00003.bin: 64%|██████▎ | 3.18G/5.00G [00:04<00:01, 1.09GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▋ | 3.31G/5.00G [00:05<00:02, 809MB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 3.42G/5.00G [00:05<00:02, 717MB/s] pytorch_model-00002-of-00003.bin: 70%|███████ | 3.51G/5.00G [00:05<00:02, 732MB/s] pytorch_model-00002-of-00003.bin: 72%|███████▏ | 3.61G/5.00G [00:05<00:02, 687MB/s] pytorch_model-00002-of-00003.bin: 75%|███████▌ | 3.77G/5.00G [00:05<00:01, 872MB/s] pytorch_model-00002-of-00003.bin: 79%|███████▉ | 3.94G/5.00G [00:05<00:01, 1.04GB/s] pytorch_model-00002-of-00003.bin: 81%|████████▏ | 4.07G/5.00G [00:06<00:01, 900MB/s] pytorch_model-00002-of-00003.bin: 83%|████████▎ | 4.17G/5.00G [00:06<00:00, 928MB/s] pytorch_model-00002-of-00003.bin: 86%|████████▌ | 4.28G/5.00G [00:06<00:00, 951MB/s] pytorch_model-00002-of-00003.bin: 88%|████████▊ | 4.38G/5.00G [00:06<00:00, 967MB/s] pytorch_model-00002-of-00003.bin: 90%|████████▉ | 4.49G/5.00G [00:06<00:00, 856MB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▎| 4.69G/5.00G [00:06<00:00, 1.13GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▋| 4.81G/5.00G [00:06<00:00, 1.16GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:06<00:00, 1.07GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:06<00:00, 717MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: pytorch_model-00003-of-00003.bin: 0%| | 0.00/4.54G [00:00<?, ?B/s] pytorch_model-00003-of-00003.bin: 0%| | 10.5M/4.54G [00:00<07:03, 10.7MB/s] pytorch_model-00003-of-00003.bin: 0%| | 21.0M/4.54G [00:01<03:33, 21.2MB/s] pytorch_model-00003-of-00003.bin: 1%| | 52.4M/4.54G [00:01<01:17, 57.7MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 83.9M/4.54G [00:01<00:46, 96.6MB/s] pytorch_model-00003-of-00003.bin: 3%|▎ | 115M/4.54G [00:01<00:32, 136MB/s] pytorch_model-00003-of-00003.bin: 4%|▍ | 189M/4.54G [00:01<00:17, 251MB/s] pytorch_model-00003-of-00003.bin: 7%|▋ | 304M/4.54G [00:01<00:09, 447MB/s] pytorch_model-00003-of-00003.bin: 13%|█▎ | 587M/4.54G [00:01<00:03, 1.01GB/s] pytorch_model-00003-of-00003.bin: 16%|█▌ | 724M/4.54G [00:01<00:03, 1.04GB/s] pytorch_model-00003-of-00003.bin: 19%|█▉ | 881M/4.54G [00:02<00:03, 1.15GB/s] pytorch_model-00003-of-00003.bin: 25%|██▌ | 1.15G/4.54G [00:02<00:02, 1.49GB/s] pytorch_model-00003-of-00003.bin: 29%|██▉ | 1.32G/4.54G [00:02<00:04, 774MB/s] pytorch_model-00003-of-00003.bin: 32%|███▏ | 1.45G/4.54G [00:02<00:04, 702MB/s] pytorch_model-00003-of-00003.bin: 34%|███▍ | 1.55G/4.54G [00:03<00:04, 627MB/s] pytorch_model-00003-of-00003.bin: 36%|███▋ | 1.65G/4.54G [00:03<00:05, 502MB/s] pytorch_model-00003-of-00003.bin: 38%|███▊ | 1.72G/4.54G [00:03<00:05, 520MB/s] pytorch_model-00003-of-00003.bin: 41%|████ | 1.85G/4.54G [00:03<00:04, 641MB/s] pytorch_model-00003-of-00003.bin: 44%|████▍ | 2.00G/4.54G [00:03<00:03, 799MB/s] pytorch_model-00003-of-00003.bin: 46%|████▋ | 2.11G/4.54G [00:03<00:02, 829MB/s] pytorch_model-00003-of-00003.bin: 50%|████▉ | 2.25G/4.54G [00:04<00:02, 972MB/s] pytorch_model-00003-of-00003.bin: 58%|█████▊ | 2.63G/4.54G [00:04<00:01, 1.26GB/s] pytorch_model-00003-of-00003.bin: 61%|██████ | 2.77G/4.54G [00:04<00:01, 912MB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 2.87G/4.54G [00:04<00:02, 800MB/s] pytorch_model-00003-of-00003.bin: 65%|██████▌ | 2.97G/4.54G [00:04<00:02, 763MB/s] pytorch_model-00003-of-00003.bin: 67%|██████▋ | 3.05G/4.54G [00:05<00:02, 639MB/s] pytorch_model-00003-of-00003.bin: 69%|██████▉ | 3.12G/4.54G [00:05<00:02, 596MB/s] pytorch_model-00003-of-00003.bin: 71%|███████ | 3.21G/4.54G [00:05<00:02, 631MB/s] pytorch_model-00003-of-00003.bin: 75%|███████▍ | 3.39G/4.54G [00:05<00:01, 858MB/s] pytorch_model-00003-of-00003.bin: 81%|████████ | 3.66G/4.54G [00:05<00:00, 1.27GB/s] pytorch_model-00003-of-00003.bin: 84%|████████▍ | 3.81G/4.54G [00:05<00:00, 1.05GB/s] pytorch_model-00003-of-00003.bin: 87%|████████▋ | 3.93G/4.54G [00:05<00:00, 1.02GB/s] pytorch_model-00003-of-00003.bin: 89%|████████▉ | 4.05G/4.54G [00:06<00:00, 951MB/s] pytorch_model-00003-of-00003.bin: 92%|█████████▏| 4.17G/4.54G [00:06<00:00, 962MB/s] pytorch_model-00003-of-00003.bin: 96%|█████████▋| 4.37G/4.54G [00:06<00:00, 1.19GB/s] pytorch_model-00003-of-00003.bin: 99%|█████████▉| 4.51G/4.54G [00:06<00:00, 1.01GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:06<00:00, 649MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/23.9k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 34.1MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: special_tokens_map.json: 0%| | 0.00/551 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 551/551 [00:00<00:00, 9.21MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 14.9MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.02k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.02k/1.02k [00:00<00:00, 12.3MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: Downloaded to shared memory in 45.731s
cgato-thespis-lucywantst-2658-v8-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespis-lucywantst-2658-v8-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespis-lucywantst-2658-v8-mkmlizer: Reading /tmp/tmp84jb9wpu/pytorch_model.bin.index.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:02<11:59, 2.48s/it] Profiling: 34%|███▎ | 98/291 [00:03<00:05, 34.65it/s] Profiling: 70%|███████ | 204/291 [00:04<00:01, 58.33it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 60.12it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 48.78it/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: quantized model in 17.096s
cgato-thespis-lucywantst-2658-v8-mkmlizer: Processed model cgato/Thespis-LucyWantsToQuantEdition-7b-v0.1 in 63.788s
cgato-thespis-lucywantst-2658-v8-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespis-lucywantst-2658-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespis-lucywantst-2658-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8/config.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8/special_tokens_map.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8/tokenizer.model
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8/tokenizer_config.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8/tokenizer.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespis-lucywantst-2658-v8/mkml_model.tensors
cgato-thespis-lucywantst-2658-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespis-lucywantst-2658-v8-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.
cgato-thespis-lucywantst-2658-v8-mkmlizer: warnings.warn(
cgato-thespis-lucywantst-2658-v8-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.92MB/s]
cgato-thespis-lucywantst-2658-v8-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.
cgato-thespis-lucywantst-2658-v8-mkmlizer: warnings.warn(
cgato-thespis-lucywantst-2658-v8-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.76MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 39.1MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 41.5MB/s]
cgato-thespis-lucywantst-2658-v8-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.
cgato-thespis-lucywantst-2658-v8-mkmlizer: warnings.warn(
cgato-thespis-lucywantst-2658-v8-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:20, 70.7MB/s] pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:03, 357MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:02, 487MB/s] pytorch_model.bin: 15%|█▌ | 220M/1.44G [00:00<00:02, 461MB/s] pytorch_model.bin: 27%|██▋ | 388M/1.44G [00:00<00:01, 793MB/s] pytorch_model.bin: 33%|███▎ | 472M/1.44G [00:00<00:01, 721MB/s] pytorch_model.bin: 41%|████ | 587M/1.44G [00:00<00:01, 809MB/s] pytorch_model.bin: 47%|████▋ | 679M/1.44G [00:01<00:00, 807MB/s] pytorch_model.bin: 54%|█████▎ | 773M/1.44G [00:01<00:00, 826MB/s] pytorch_model.bin: 70%|███████ | 1.01G/1.44G [00:01<00:00, 1.25GB/s] pytorch_model.bin: 97%|█████████▋| 1.40G/1.44G [00:01<00:00, 1.68GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 682MB/s]
cgato-thespis-lucywantst-2658-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespis-lucywantst-2658-v8-mkmlizer: Saving duration: 0.254s
cgato-thespis-lucywantst-2658-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.954s
cgato-thespis-lucywantst-2658-v8-mkmlizer: creating bucket guanaco-reward-models
cgato-thespis-lucywantst-2658-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespis-lucywantst-2658-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/tokenizer_config.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/vocab.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/merges.txt
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/config.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/special_tokens_map.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/tokenizer.json
cgato-thespis-lucywantst-2658-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespis-lucywantst-2658-v8_reward/reward.tensors
Job cgato-thespis-lucywantst-2658-v8-mkmlizer completed after 96.3s with status: succeeded
Stopping job with name cgato-thespis-lucywantst-2658-v8-mkmlizer
Pipeline stage MKMLizer completed in 100.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespis-lucywantst-2658-v8
Waiting for inference service cgato-thespis-lucywantst-2658-v8 to be ready
Inference service cgato-thespis-lucywantst-2658-v8 ready after 40.23804807662964s
Pipeline stage ISVCDeployer completed in 48.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3116557598114014s
Received healthy response to inference request in 0.7559733390808105s
Received healthy response to inference request in 0.7391791343688965s
Received healthy response to inference request in 0.6275448799133301s
Received healthy response to inference request in 4.756006240844727s
5 requests
0 failed requests
5th percentile: 0.6498717308044434
10th percentile: 0.6721985816955567
20th percentile: 0.7168522834777832
30th percentile: 0.7425379753112793
40th percentile: 0.7492556571960449
50th percentile: 0.7559733390808105
60th percentile: 0.9782463073730469
70th percentile: 1.2005192756652832
80th percentile: 2.0005258560180668
90th percentile: 3.3782660484313967
95th percentile: 4.067136144638061
99th percentile: 4.618232221603393
mean time: 1.638071870803833
Pipeline stage StressChecker completed in 9.10s
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
cgato-thespis-lucywantst_2658_v8 status is now deployed due to DeploymentManager action
cgato-thespis-lucywantst_2658_v8 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics