submission_id: cgato-thespis-balanced-7b-v2_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/Thespis-Balanced-7b-v2
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-03-16T04:48:10+00:00
model_name: Thespis-Balanced-v2
model_eval_status: success
safety_score: 0.67
entertaining: 7.26
stay_in_character: 8.65
user_preference: 7.4
double_thumbs_up: 1430
thumbs_up: 2213
thumbs_down: 966
num_battles: 112290
num_wins: 59268
win_ratio: 0.5278119155757414
celo_rating: 1177.43
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespis-balanced-7b-v2-v1-mkmlizer
Waiting for job on cgato-thespis-balanced-7b-v2-v1-mkmlizer to finish
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ _____ __ __ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ /___/ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ belonging to: ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ║ ║
cgato-thespis-balanced-7b-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespis-balanced-7b-v2-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 17.2MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 260kB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: config.json: 0%| | 0.00/643 [00:00<?, ?B/s] config.json: 100%|██████████| 643/643 [00:00<00:00, 8.40MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: generation_config.json: 0%| | 0.00/132 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 132/132 [00:00<00:00, 1.67MB/s]
cgato-thespis-balanced-7b-v2-v1-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 [00:01<08:45, 9.39MB/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/4.94G [00:01<06:27, 12.7MB/s] pytorch_model-00001-of-00003.bin: 1%| | 31.5M/4.94G [00:01<03:58, 20.6MB/s] pytorch_model-00001-of-00003.bin: 1%| | 52.4M/4.94G [00:02<02:13, 36.5MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 115M/4.94G [00:02<00:45, 107MB/s] pytorch_model-00001-of-00003.bin: 3%|▎ | 157M/4.94G [00:02<00:33, 144MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 189M/4.94G [00:02<00:28, 168MB/s] pytorch_model-00001-of-00003.bin: 4%|▍ | 220M/4.94G [00:02<00:26, 181MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 273M/4.94G [00:02<00:19, 237MB/s] pytorch_model-00001-of-00003.bin: 6%|▋ | 315M/4.94G [00:02<00:18, 247MB/s] pytorch_model-00001-of-00003.bin: 7%|▋ | 346M/4.94G [00:03<00:18, 244MB/s] pytorch_model-00001-of-00003.bin: 8%|▊ | 388M/4.94G [00:03<00:16, 274MB/s] pytorch_model-00001-of-00003.bin: 11%|█ | 535M/4.94G [00:03<00:08, 539MB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 682M/4.94G [00:03<00:05, 714MB/s] pytorch_model-00001-of-00003.bin: 16%|█▌ | 797M/4.94G [00:03<00:05, 796MB/s] pytorch_model-00001-of-00003.bin: 18%|█▊ | 891M/4.94G [00:03<00:05, 806MB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 1.39G/4.94G [00:03<00:02, 1.55GB/s] pytorch_model-00001-of-00003.bin: 31%|███ | 1.54G/4.94G [00:04<00:05, 610MB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 1.65G/4.94G [00:04<00:06, 502MB/s] pytorch_model-00001-of-00003.bin: 36%|███▋ | 1.79G/4.94G [00:05<00:05, 599MB/s] pytorch_model-00001-of-00003.bin: 39%|███▉ | 1.95G/4.94G [00:05<00:04, 723MB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 2.07G/4.94G [00:05<00:03, 720MB/s] pytorch_model-00001-of-00003.bin: 44%|████▍ | 2.18G/4.94G [00:05<00:03, 771MB/s] pytorch_model-00001-of-00003.bin: 46%|████▌ | 2.29G/4.94G [00:05<00:03, 808MB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 2.39G/4.94G [00:05<00:03, 822MB/s] pytorch_model-00001-of-00003.bin: 50%|█████ | 2.49G/4.94G [00:05<00:03, 737MB/s] pytorch_model-00001-of-00003.bin: 57%|█████▋ | 2.83G/4.94G [00:05<00:01, 1.32GB/s] pytorch_model-00001-of-00003.bin: 62%|██████▏ | 3.06G/4.94G [00:06<00:01, 1.55GB/s] pytorch_model-00001-of-00003.bin: 66%|██████▌ | 3.25G/4.94G [00:06<00:01, 995MB/s] pytorch_model-00001-of-00003.bin: 69%|██████▊ | 3.40G/4.94G [00:06<00:02, 635MB/s] pytorch_model-00001-of-00003.bin: 71%|███████ | 3.51G/4.94G [00:07<00:02, 622MB/s] pytorch_model-00001-of-00003.bin: 73%|███████▎ | 3.61G/4.94G [00:07<00:02, 595MB/s] pytorch_model-00001-of-00003.bin: 77%|███████▋ | 3.79G/4.94G [00:07<00:01, 766MB/s] pytorch_model-00001-of-00003.bin: 80%|███████▉ | 3.94G/4.94G [00:07<00:01, 904MB/s] pytorch_model-00001-of-00003.bin: 85%|████████▌ | 4.20G/4.94G [00:07<00:00, 1.23GB/s] pytorch_model-00001-of-00003.bin: 88%|████████▊ | 4.36G/4.94G [00:07<00:00, 1.23GB/s] pytorch_model-00001-of-00003.bin: 91%|█████████▏| 4.51G/4.94G [00:07<00:00, 984MB/s] pytorch_model-00001-of-00003.bin: 94%|█████████▍| 4.65G/4.94G [00:08<00:00, 1.04GB/s] pytorch_model-00001-of-00003.bin: 97%|█████████▋| 4.82G/4.94G [00:08<00:00, 1.18GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 4.94G/4.94G [00:08<00:00, 601MB/s]
cgato-thespis-balanced-7b-v2-v1-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<07:24, 11.2MB/s] pytorch_model-00002-of-00003.bin: 0%| | 21.0M/5.00G [00:01<04:12, 19.8MB/s] pytorch_model-00002-of-00003.bin: 1%| | 31.5M/5.00G [00:01<02:53, 28.7MB/s] pytorch_model-00002-of-00003.bin: 1%| | 52.4M/5.00G [00:01<01:31, 54.4MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 105M/5.00G [00:01<00:37, 132MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 147M/5.00G [00:01<00:26, 182MB/s] pytorch_model-00002-of-00003.bin: 4%|▎ | 178M/5.00G [00:01<00:24, 194MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 231M/5.00G [00:01<00:18, 253MB/s] pytorch_model-00002-of-00003.bin: 5%|▌ | 262M/5.00G [00:02<00:17, 267MB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 325M/5.00G [00:02<00:14, 327MB/s] pytorch_model-00002-of-00003.bin: 7%|▋ | 367M/5.00G [00:02<00:13, 339MB/s] pytorch_model-00002-of-00003.bin: 8%|▊ | 409M/5.00G [00:02<00:12, 357MB/s] pytorch_model-00002-of-00003.bin: 9%|▉ | 472M/5.00G [00:02<00:11, 404MB/s] pytorch_model-00002-of-00003.bin: 11%|█ | 535M/5.00G [00:02<00:09, 459MB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 629M/5.00G [00:02<00:07, 588MB/s] pytorch_model-00002-of-00003.bin: 14%|█▍ | 724M/5.00G [00:02<00:06, 669MB/s] pytorch_model-00002-of-00003.bin: 16%|█▌ | 807M/5.00G [00:03<00:06, 608MB/s] pytorch_model-00002-of-00003.bin: 18%|█▊ | 912M/5.00G [00:03<00:05, 716MB/s] pytorch_model-00002-of-00003.bin: 31%|███ | 1.55G/5.00G [00:03<00:01, 2.21GB/s] pytorch_model-00002-of-00003.bin: 36%|███▌ | 1.80G/5.00G [00:04<00:04, 787MB/s] pytorch_model-00002-of-00003.bin: 40%|███▉ | 1.99G/5.00G [00:04<00:04, 744MB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 2.16G/5.00G [00:04<00:03, 851MB/s] pytorch_model-00002-of-00003.bin: 46%|████▋ | 2.32G/5.00G [00:04<00:02, 946MB/s] pytorch_model-00002-of-00003.bin: 49%|████▉ | 2.47G/5.00G [00:04<00:02, 982MB/s] pytorch_model-00002-of-00003.bin: 55%|█████▌ | 2.76G/5.00G [00:04<00:01, 1.15GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 2.90G/5.00G [00:05<00:02, 835MB/s] pytorch_model-00002-of-00003.bin: 60%|██████ | 3.02G/5.00G [00:05<00:02, 715MB/s] pytorch_model-00002-of-00003.bin: 62%|██████▏ | 3.11G/5.00G [00:05<00:02, 686MB/s] pytorch_model-00002-of-00003.bin: 65%|██████▌ | 3.25G/5.00G [00:05<00:02, 778MB/s] pytorch_model-00002-of-00003.bin: 67%|██████▋ | 3.37G/5.00G [00:05<00:01, 848MB/s] pytorch_model-00002-of-00003.bin: 70%|██████▉ | 3.49G/5.00G [00:05<00:01, 897MB/s] pytorch_model-00002-of-00003.bin: 73%|███████▎ | 3.64G/5.00G [00:06<00:01, 1.00GB/s] pytorch_model-00002-of-00003.bin: 76%|███████▌ | 3.79G/5.00G [00:06<00:01, 1.06GB/s] pytorch_model-00002-of-00003.bin: 78%|███████▊ | 3.90G/5.00G [00:06<00:01, 957MB/s] pytorch_model-00002-of-00003.bin: 80%|████████ | 4.01G/5.00G [00:06<00:01, 753MB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 4.10G/5.00G [00:06<00:01, 646MB/s] pytorch_model-00002-of-00003.bin: 83%|████████▎ | 4.17G/5.00G [00:06<00:01, 659MB/s] pytorch_model-00002-of-00003.bin: 86%|████████▌ | 4.29G/5.00G [00:06<00:00, 756MB/s] pytorch_model-00002-of-00003.bin: 89%|████████▊ | 4.44G/5.00G [00:07<00:00, 922MB/s] pytorch_model-00002-of-00003.bin: 91%|█████████ | 4.55G/5.00G [00:07<00:00, 977MB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▎| 4.69G/5.00G [00:07<00:00, 1.07GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:07<00:00, 679MB/s]
cgato-thespis-balanced-7b-v2-v1-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 [00:01<09:08, 8.25MB/s] pytorch_model-00003-of-00003.bin: 0%| | 21.0M/4.54G [00:01<04:12, 17.9MB/s] pytorch_model-00003-of-00003.bin: 2%|▏ | 73.4M/4.54G [00:01<00:55, 81.1MB/s] pytorch_model-00003-of-00003.bin: 4%|▍ | 189M/4.54G [00:01<00:19, 222MB/s] pytorch_model-00003-of-00003.bin: 5%|▌ | 241M/4.54G [00:01<00:16, 257MB/s] pytorch_model-00003-of-00003.bin: 7%|▋ | 304M/4.54G [00:01<00:13, 321MB/s] pytorch_model-00003-of-00003.bin: 8%|▊ | 357M/4.54G [00:01<00:11, 354MB/s] pytorch_model-00003-of-00003.bin: 9%|▉ | 409M/4.54G [00:02<00:11, 372MB/s] pytorch_model-00003-of-00003.bin: 10%|█ | 461M/4.54G [00:02<00:12, 339MB/s] pytorch_model-00003-of-00003.bin: 12%|█▏ | 524M/4.54G [00:02<00:10, 386MB/s] pytorch_model-00003-of-00003.bin: 14%|█▍ | 650M/4.54G [00:02<00:06, 574MB/s] pytorch_model-00003-of-00003.bin: 18%|█▊ | 807M/4.54G [00:02<00:04, 812MB/s] pytorch_model-00003-of-00003.bin: 21%|██ | 944M/4.54G [00:02<00:03, 910MB/s] pytorch_model-00003-of-00003.bin: 23%|██▎ | 1.05G/4.54G [00:02<00:03, 876MB/s] pytorch_model-00003-of-00003.bin: 35%|███▍ | 1.57G/4.54G [00:03<00:01, 1.85GB/s] pytorch_model-00003-of-00003.bin: 39%|███▉ | 1.76G/4.54G [00:03<00:03, 752MB/s] pytorch_model-00003-of-00003.bin: 42%|████▏ | 1.91G/4.54G [00:03<00:03, 806MB/s] pytorch_model-00003-of-00003.bin: 47%|████▋ | 2.15G/4.54G [00:03<00:02, 994MB/s] pytorch_model-00003-of-00003.bin: 51%|█████ | 2.30G/4.54G [00:04<00:02, 843MB/s] pytorch_model-00003-of-00003.bin: 53%|█████▎ | 2.42G/4.54G [00:04<00:02, 883MB/s] pytorch_model-00003-of-00003.bin: 57%|█████▋ | 2.59G/4.54G [00:04<00:01, 1.01GB/s] pytorch_model-00003-of-00003.bin: 60%|██████ | 2.73G/4.54G [00:04<00:01, 1.01GB/s] pytorch_model-00003-of-00003.bin: 63%|██████▎ | 2.86G/4.54G [00:04<00:01, 1.00GB/s] pytorch_model-00003-of-00003.bin: 66%|██████▌ | 2.98G/4.54G [00:04<00:01, 945MB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 3.29G/4.54G [00:04<00:00, 1.43GB/s] pytorch_model-00003-of-00003.bin: 79%|███████▉ | 3.61G/4.54G [00:05<00:00, 1.83GB/s] pytorch_model-00003-of-00003.bin: 84%|████████▍ | 3.82G/4.54G [00:05<00:00, 1.25GB/s] pytorch_model-00003-of-00003.bin: 88%|████████▊ | 3.98G/4.54G [00:05<00:00, 1.05GB/s] pytorch_model-00003-of-00003.bin: 91%|█████████ | 4.13G/4.54G [00:05<00:00, 1.10GB/s] pytorch_model-00003-of-00003.bin: 94%|█████████▍| 4.27G/4.54G [00:05<00:00, 1.11GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.53G/4.54G [00:05<00:00, 1.35GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:06<00:00, 728MB/s]
cgato-thespis-balanced-7b-v2-v1-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, 160MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 7.02MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 54.8MB/s]
cgato-thespis-balanced-7b-v2-v1-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, 13.6MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Downloaded to shared memory in 23.890s
cgato-thespis-balanced-7b-v2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Reading /tmp/tmpkgdqcgvo/pytorch_model.bin.index.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:02<10:03, 2.08s/it] Profiling: 34%|███▎ | 98/291 [00:02<00:04, 43.18it/s] Profiling: 70%|███████ | 204/291 [00:03<00:01, 77.06it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 72.88it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 59.99it/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: quantized model in 15.262s
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Processed model cgato/Thespis-Balanced-7b-v2 in 40.068s
cgato-thespis-balanced-7b-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespis-balanced-7b-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1/tokenizer.model
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1/tokenizer_config.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1/special_tokens_map.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1/config.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1/tokenizer.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespis-balanced-7b-v2-v1/mkml_model.tensors
cgato-thespis-balanced-7b-v2-v1-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cgato-thespis-balanced-7b-v2-v1-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-balanced-7b-v2-v1-mkmlizer: warnings.warn(
cgato-thespis-balanced-7b-v2-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.9MB/s]
cgato-thespis-balanced-7b-v2-v1-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-balanced-7b-v2-v1-mkmlizer: warnings.warn(
cgato-thespis-balanced-7b-v2-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.29MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 28.5MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 42.4MB/s]
cgato-thespis-balanced-7b-v2-v1-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-balanced-7b-v2-v1-mkmlizer: warnings.warn(
cgato-thespis-balanced-7b-v2-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:23, 61.4MB/s] pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:13, 106MB/s] pytorch_model.bin: 9%|▉ | 136M/1.44G [00:00<00:06, 193MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:07, 176MB/s] pytorch_model.bin: 14%|█▍ | 199M/1.44G [00:01<00:05, 220MB/s] pytorch_model.bin: 20%|█▉ | 283M/1.44G [00:01<00:03, 338MB/s] pytorch_model.bin: 50%|█████ | 724M/1.44G [00:01<00:00, 1.25GB/s] pytorch_model.bin: 84%|████████▍ | 1.21G/1.44G [00:01<00:00, 2.13GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 977MB/s]
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Saving duration: 0.230s
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.937s
cgato-thespis-balanced-7b-v2-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thespis-balanced-7b-v2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespis-balanced-7b-v2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/config.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/tokenizer_config.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/merges.txt
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/special_tokens_map.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/vocab.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/tokenizer.json
cgato-thespis-balanced-7b-v2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespis-balanced-7b-v2-v1_reward/reward.tensors
Job cgato-thespis-balanced-7b-v2-v1-mkmlizer completed after 64.41s with status: succeeded
Stopping job with name cgato-thespis-balanced-7b-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 68.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespis-balanced-7b-v2-v1
Waiting for inference service cgato-thespis-balanced-7b-v2-v1 to be ready
Inference service cgato-thespis-balanced-7b-v2-v1 ready after 40.233816385269165s
Pipeline stage ISVCDeployer completed in 47.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5931360721588135s
Received healthy response to inference request in 1.1762008666992188s
Received healthy response to inference request in 1.185537338256836s
Received healthy response to inference request in 1.1987066268920898s
Received healthy response to inference request in 1.1715247631072998s
5 requests
0 failed requests
5th percentile: 1.1724599838256835
10th percentile: 1.1733952045440674
20th percentile: 1.175265645980835
30th percentile: 1.1780681610107422
40th percentile: 1.181802749633789
50th percentile: 1.185537338256836
60th percentile: 1.1908050537109376
70th percentile: 1.196072769165039
80th percentile: 1.2775925159454347
90th percentile: 1.435364294052124
95th percentile: 1.5142501831054687
99th percentile: 1.5773588943481445
mean time: 1.2650211334228516
Pipeline stage StressChecker completed in 7.09s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespis-balanced-7b-v2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics