submission_id: cgato-thespice-7b-quick-_5889_v1
developer_uid: c.gato
status: torndown
model_repo: cgato/TheSpice-7b-Quick-v0.1.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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}:', '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: 2024-04-15T11:47:26+00:00
model_name: cgato-thespice-7b-quick-_5889_v1
model_eval_status: success
model_group: cgato/TheSpice-7b-Quick-
num_battles: 14552
num_wins: 7836
celo_rating: 1173.06
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thespice-7b-quick-_5889_v1
ineligible_reason: propriety_total_count < 800
language_model: cgato/TheSpice-7b-Quick-v0.1.1
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-15
win_ratio: 0.5384826827927433
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-quick-5889-v1-mkmlizer
Waiting for job on cgato-thespice-7b-quick-5889-v1-mkmlizer to finish
Stopping job with name cgato-thespice-7b-quick-5889-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-thespice-7b-quick-5889-v1-mkmlizer
Waiting for job on cgato-thespice-7b-quick-5889-v1-mkmlizer to finish
cgato-thespice-7b-quick-5889-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ /___/ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ║ ║
cgato-thespice-7b-quick-5889-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-quick-5889-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.0MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 309kB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 5.31MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.13MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: model-00001-of-00003.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s] model-00001-of-00003.safetensors: 0%| | 10.5M/4.94G [00:00<04:02, 20.3MB/s] model-00001-of-00003.safetensors: 0%| | 21.0M/4.94G [00:02<10:14, 8.01MB/s] model-00001-of-00003.safetensors: 1%|▏ | 62.9M/4.94G [00:02<02:30, 32.5MB/s] model-00001-of-00003.safetensors: 2%|▏ | 105M/4.94G [00:02<01:20, 60.3MB/s] model-00001-of-00003.safetensors: 6%|▌ | 273M/4.94G [00:02<00:21, 217MB/s] model-00001-of-00003.safetensors: 8%|▊ | 388M/4.94G [00:02<00:14, 320MB/s] model-00001-of-00003.safetensors: 10%|▉ | 472M/4.94G [00:03<00:12, 354MB/s] model-00001-of-00003.safetensors: 22%|██▏ | 1.08G/4.94G [00:03<00:05, 723MB/s] model-00001-of-00003.safetensors: 24%|██▎ | 1.16G/4.94G [00:03<00:05, 678MB/s] model-00001-of-00003.safetensors: 26%|██▌ | 1.27G/4.94G [00:03<00:05, 709MB/s] model-00001-of-00003.safetensors: 28%|██▊ | 1.39G/4.94G [00:04<00:04, 787MB/s] model-00001-of-00003.safetensors: 33%|███▎ | 1.64G/4.94G [00:04<00:03, 1.03GB/s] model-00001-of-00003.safetensors: 37%|███▋ | 1.81G/4.94G [00:04<00:02, 1.16GB/s] model-00001-of-00003.safetensors: 39%|███▉ | 1.95G/4.94G [00:04<00:03, 996MB/s] model-00001-of-00003.safetensors: 42%|████▏ | 2.07G/4.94G [00:04<00:03, 957MB/s] model-00001-of-00003.safetensors: 47%|████▋ | 2.32G/4.94G [00:04<00:02, 1.28GB/s] model-00001-of-00003.safetensors: 50%|█████ | 2.47G/4.94G [00:05<00:03, 820MB/s] model-00001-of-00003.safetensors: 53%|█████▎ | 2.64G/4.94G [00:05<00:02, 955MB/s] model-00001-of-00003.safetensors: 57%|█████▋ | 2.82G/4.94G [00:05<00:01, 1.11GB/s] model-00001-of-00003.safetensors: 60%|██████ | 2.97G/4.94G [00:05<00:02, 787MB/s] model-00001-of-00003.safetensors: 62%|██████▏ | 3.08G/4.94G [00:05<00:02, 708MB/s] model-00001-of-00003.safetensors: 66%|██████▌ | 3.26G/4.94G [00:05<00:01, 880MB/s] model-00001-of-00003.safetensors: 69%|██████▉ | 3.42G/4.94G [00:06<00:01, 967MB/s] model-00001-of-00003.safetensors: 72%|███████▏ | 3.54G/4.94G [00:06<00:02, 684MB/s] model-00001-of-00003.safetensors: 75%|███████▌ | 3.71G/4.94G [00:06<00:01, 819MB/s] model-00001-of-00003.safetensors: 79%|███████▉ | 3.91G/4.94G [00:06<00:01, 1.03GB/s] model-00001-of-00003.safetensors: 82%|████████▏ | 4.05G/4.94G [00:06<00:01, 779MB/s] model-00001-of-00003.safetensors: 84%|████████▍ | 4.16G/4.94G [00:07<00:01, 737MB/s] model-00001-of-00003.safetensors: 89%|████████▊ | 4.38G/4.94G [00:07<00:00, 982MB/s] model-00001-of-00003.safetensors: 93%|█████████▎| 4.58G/4.94G [00:07<00:00, 1.16GB/s] model-00001-of-00003.safetensors: 96%|█████████▌| 4.72G/4.94G [00:07<00:00, 1.13GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:07<00:00, 654MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: model-00002-of-00003.safetensors: 0%| | 0.00/5.00G [00:00<?, ?B/s] model-00002-of-00003.safetensors: 0%| | 10.5M/5.00G [00:02<17:56, 4.63MB/s] model-00002-of-00003.safetensors: 0%| | 21.0M/5.00G [00:02<08:58, 9.25MB/s] model-00002-of-00003.safetensors: 1%|▏ | 62.9M/5.00G [00:02<02:11, 37.4MB/s] model-00002-of-00003.safetensors: 2%|▏ | 115M/5.00G [00:02<01:01, 79.4MB/s] model-00002-of-00003.safetensors: 4%|▍ | 220M/5.00G [00:02<00:25, 187MB/s] model-00002-of-00003.safetensors: 6%|▌ | 283M/5.00G [00:03<00:20, 232MB/s] model-00002-of-00003.safetensors: 8%|▊ | 388M/5.00G [00:03<00:13, 350MB/s] model-00002-of-00003.safetensors: 22%|██▏ | 1.10G/5.00G [00:03<00:02, 1.53GB/s] model-00002-of-00003.safetensors: 27%|██▋ | 1.36G/5.00G [00:04<00:05, 688MB/s] model-00002-of-00003.safetensors: 31%|███ | 1.55G/5.00G [00:04<00:04, 733MB/s] model-00002-of-00003.safetensors: 38%|███▊ | 1.88G/5.00G [00:04<00:03, 1.01GB/s] model-00002-of-00003.safetensors: 42%|████▏ | 2.08G/5.00G [00:04<00:02, 1.02GB/s] model-00002-of-00003.safetensors: 48%|████▊ | 2.40G/5.00G [00:04<00:02, 1.20GB/s] model-00002-of-00003.safetensors: 52%|█████▏ | 2.58G/5.00G [00:05<00:03, 806MB/s] model-00002-of-00003.safetensors: 54%|█████▍ | 2.72G/5.00G [00:05<00:02, 869MB/s] model-00002-of-00003.safetensors: 57%|█████▋ | 2.85G/5.00G [00:05<00:02, 894MB/s] model-00002-of-00003.safetensors: 60%|██████ | 3.01G/5.00G [00:05<00:02, 973MB/s] model-00002-of-00003.safetensors: 64%|██████▍ | 3.22G/5.00G [00:05<00:01, 1.18GB/s] model-00002-of-00003.safetensors: 70%|██████▉ | 3.49G/5.00G [00:05<00:01, 1.47GB/s] model-00002-of-00003.safetensors: 73%|███████▎ | 3.67G/5.00G [00:06<00:01, 1.03GB/s] model-00002-of-00003.safetensors: 76%|███████▋ | 3.82G/5.00G [00:06<00:01, 1.01GB/s] model-00002-of-00003.safetensors: 79%|███████▉ | 3.95G/5.00G [00:06<00:01, 824MB/s] model-00002-of-00003.safetensors: 81%|████████ | 4.06G/5.00G [00:06<00:01, 797MB/s] model-00002-of-00003.safetensors: 84%|████████▎ | 4.18G/5.00G [00:06<00:00, 874MB/s] model-00002-of-00003.safetensors: 86%|████████▌ | 4.30G/5.00G [00:07<00:00, 921MB/s] model-00002-of-00003.safetensors: 91%|█████████ | 4.55G/5.00G [00:07<00:00, 1.27GB/s] model-00002-of-00003.safetensors: 95%|█████████▌| 4.75G/5.00G [00:07<00:00, 1.43GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:07<00:00, 685MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: model-00003-of-00003.safetensors: 0%| | 0.00/4.54G [00:00<?, ?B/s] model-00003-of-00003.safetensors: 0%| | 10.5M/4.54G [00:00<03:46, 20.0MB/s] model-00003-of-00003.safetensors: 0%| | 21.0M/4.54G [00:02<08:22, 9.00MB/s] model-00003-of-00003.safetensors: 1%| | 31.5M/4.54G [00:02<04:57, 15.1MB/s] model-00003-of-00003.safetensors: 1%| | 41.9M/4.54G [00:02<03:35, 20.9MB/s] model-00003-of-00003.safetensors: 2%|▏ | 105M/4.54G [00:02<01:03, 69.7MB/s] model-00003-of-00003.safetensors: 4%|▎ | 168M/4.54G [00:02<00:33, 130MB/s] model-00003-of-00003.safetensors: 6%|▌ | 283M/4.54G [00:02<00:16, 265MB/s] model-00003-of-00003.safetensors: 10%|▉ | 451M/4.54G [00:03<00:09, 449MB/s] model-00003-of-00003.safetensors: 14%|█▍ | 629M/4.54G [00:03<00:05, 677MB/s] model-00003-of-00003.safetensors: 24%|██▎ | 1.07G/4.54G [00:03<00:04, 827MB/s] model-00003-of-00003.safetensors: 26%|██▌ | 1.17G/4.54G [00:04<00:05, 590MB/s] model-00003-of-00003.safetensors: 29%|██▉ | 1.31G/4.54G [00:04<00:05, 601MB/s] model-00003-of-00003.safetensors: 31%|███ | 1.39G/4.54G [00:04<00:05, 615MB/s] model-00003-of-00003.safetensors: 32%|███▏ | 1.47G/4.54G [00:04<00:05, 610MB/s] model-00003-of-00003.safetensors: 36%|███▌ | 1.63G/4.54G [00:04<00:03, 774MB/s] model-00003-of-00003.safetensors: 38%|███▊ | 1.73G/4.54G [00:04<00:03, 829MB/s] model-00003-of-00003.safetensors: 40%|████ | 1.84G/4.54G [00:04<00:03, 867MB/s] model-00003-of-00003.safetensors: 43%|████▎ | 1.96G/4.54G [00:04<00:02, 938MB/s] model-00003-of-00003.safetensors: 46%|████▌ | 2.09G/4.54G [00:05<00:02, 998MB/s] model-00003-of-00003.safetensors: 48%|████▊ | 2.20G/4.54G [00:05<00:02, 1.01GB/s] model-00003-of-00003.safetensors: 51%|█████ | 2.32G/4.54G [00:05<00:02, 1.03GB/s] model-00003-of-00003.safetensors: 60%|██████ | 2.74G/4.54G [00:05<00:00, 1.86GB/s] model-00003-of-00003.safetensors: 65%|██████▍ | 2.94G/4.54G [00:05<00:01, 1.16GB/s] model-00003-of-00003.safetensors: 68%|██████▊ | 3.09G/4.54G [00:06<00:01, 799MB/s] model-00003-of-00003.safetensors: 71%|███████ | 3.22G/4.54G [00:06<00:02, 622MB/s] model-00003-of-00003.safetensors: 73%|███████▎ | 3.32G/4.54G [00:06<00:01, 612MB/s] model-00003-of-00003.safetensors: 75%|███████▌ | 3.41G/4.54G [00:06<00:01, 610MB/s] model-00003-of-00003.safetensors: 80%|███████▉ | 3.62G/4.54G [00:06<00:01, 854MB/s] model-00003-of-00003.safetensors: 88%|████████▊ | 4.02G/4.54G [00:07<00:00, 1.42GB/s] model-00003-of-00003.safetensors: 93%|█████████▎| 4.20G/4.54G [00:07<00:00, 1.39GB/s] model-00003-of-00003.safetensors: 97%|█████████▋| 4.38G/4.54G [00:07<00:00, 1.45GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:10<00:00, 439MB/s]
cgato-thespice-7b-quick-5889-v1-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, 22.1MB/s]
cgato-thespice-7b-quick-5889-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, 3.80MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 6.59MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 8.49MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: Downloaded to shared memory in 28.596s
cgato-thespice-7b-quick-5889-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-quick-5889-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-quick-5889-v1-mkmlizer: Reading /tmp/tmpgeqkly9c/model.safetensors.index.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<05:57, 1.23s/it] Profiling: 6%|▌ | 18/291 [00:01<00:14, 18.33it/s] Profiling: 13%|█▎ | 37/291 [00:01<00:06, 39.81it/s] Profiling: 19%|█▉ | 56/291 [00:01<00:03, 61.80it/s] Profiling: 25%|██▌ | 74/291 [00:01<00:02, 82.58it/s] Profiling: 32%|███▏ | 94/291 [00:01<00:01, 106.20it/s] Profiling: 38%|███▊ | 112/291 [00:02<00:02, 82.57it/s] Profiling: 45%|████▌ | 131/291 [00:02<00:01, 99.79it/s] Profiling: 52%|█████▏ | 151/291 [00:02<00:01, 119.70it/s] Profiling: 58%|█████▊ | 170/291 [00:02<00:00, 135.16it/s] Profiling: 65%|██████▍ | 189/291 [00:02<00:00, 147.63it/s] Profiling: 71%|███████ | 207/291 [00:04<00:02, 32.81it/s] Profiling: 76%|███████▋ | 222/291 [00:04<00:01, 41.05it/s] Profiling: 83%|████████▎ | 241/291 [00:04<00:00, 54.71it/s] Profiling: 89%|████████▉ | 259/291 [00:04<00:00, 69.21it/s] Profiling: 95%|█████████▍| 276/291 [00:04<00:00, 83.27it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 61.29it/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: quantized model in 14.927s
cgato-thespice-7b-quick-5889-v1-mkmlizer: Processed model cgato/TheSpice-7b-Quick-v0.1.1 in 44.400s
cgato-thespice-7b-quick-5889-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-quick-5889-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-quick-5889-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1/config.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1/special_tokens_map.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1/tokenizer_config.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1/tokenizer.model
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1/tokenizer.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-quick-5889-v1/mkml_model.tensors
cgato-thespice-7b-quick-5889-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-quick-5889-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-thespice-7b-quick-5889-v1-mkmlizer: warnings.warn(
cgato-thespice-7b-quick-5889-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 13.1MB/s]
cgato-thespice-7b-quick-5889-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-thespice-7b-quick-5889-v1-mkmlizer: warnings.warn(
cgato-thespice-7b-quick-5889-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.41MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 11.6MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 13.3MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 13.2MB/s]
cgato-thespice-7b-quick-5889-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-thespice-7b-quick-5889-v1-mkmlizer: warnings.warn(
cgato-thespice-7b-quick-5889-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:49, 29.2MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:17, 78.8MB/s] pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:18, 74.7MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:08, 153MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:01<00:05, 254MB/s] pytorch_model.bin: 15%|█▍ | 210M/1.44G [00:01<00:05, 246MB/s] pytorch_model.bin: 41%|████ | 587M/1.44G [00:01<00:00, 1.01GB/s] pytorch_model.bin: 83%|████████▎ | 1.20G/1.44G [00:01<00:00, 2.18GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 950MB/s]
cgato-thespice-7b-quick-5889-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-quick-5889-v1-mkmlizer: Saving duration: 0.240s
cgato-thespice-7b-quick-5889-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.511s
cgato-thespice-7b-quick-5889-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-quick-5889-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-quick-5889-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward/config.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward/special_tokens_map.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward/tokenizer_config.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward/merges.txt
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward/vocab.json
cgato-thespice-7b-quick-5889-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-quick-5889-v1_reward/tokenizer.json
Job cgato-thespice-7b-quick-5889-v1-mkmlizer completed after 75.44s with status: succeeded
Stopping job with name cgato-thespice-7b-quick-5889-v1-mkmlizer
Pipeline stage MKMLizer completed in 80.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-quick-5889-v1
Waiting for inference service cgato-thespice-7b-quick-5889-v1 to be ready
Inference service cgato-thespice-7b-quick-5889-v1 ready after 40.58347177505493s
Pipeline stage ISVCDeployer completed in 48.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7783758640289307s
Received healthy response to inference request in 1.1776721477508545s
Received healthy response to inference request in 1.180584192276001s
Received healthy response to inference request in 1.2000105381011963s
Received healthy response to inference request in 1.3023228645324707s
5 requests
0 failed requests
5th percentile: 1.1782545566558837
10th percentile: 1.178836965560913
20th percentile: 1.1800017833709717
30th percentile: 1.18446946144104
40th percentile: 1.1922399997711182
50th percentile: 1.2000105381011963
60th percentile: 1.240935468673706
70th percentile: 1.2818603992462159
80th percentile: 1.3975334644317627
90th percentile: 1.5879546642303468
95th percentile: 1.6831652641296386
99th percentile: 1.7593337440490722
mean time: 1.3277931213378906
Pipeline stage StressChecker completed in 7.90s
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-thespice-7b-quick-_5889_v1 status is now deployed due to DeploymentManager action
cgato-thespice-7b-quick-_5889_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-quick-_5889_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-quick-5889-v1 is running
Tearing down inference service cgato-thespice-7b-quick-5889-v1
Toredown service cgato-thespice-7b-quick-5889-v1
Pipeline stage ISVCDeleter completed in 3.90s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-quick-5889-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-quick-5889-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-quick-5889-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-quick-5889-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-quick-5889-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-quick-5889-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-quick-5889-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-quick-5889-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-quick-5889-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-quick-5889-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-quick-5889-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-quick-5889-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-quick-5889-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.18s
cgato-thespice-7b-quick-_5889_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics