submission_id: cgato-thespice-7b-ft-v0-4-1_v3
developer_uid: c.gato
status: torndown
model_repo: cgato/TheSpice-7b-FT-v0.4.1
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 {bot_name} gives single line responses.\n{bot_name} gives short responses.\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: 2024-04-09T19:02:44+00:00
model_name: cgato-thespice-7b-ft-v0-4-1_v3
model_eval_status: success
model_group: cgato/TheSpice-7b-FT-v0.
num_battles: 64582
num_wins: 32924
celo_rating: 1170.44
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-ft-v0-4-1_v3
ineligible_reason: propriety_total_count < 800
language_model: cgato/TheSpice-7b-FT-v0.4.1
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-09
win_ratio: 0.5098014926759779
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer
Waiting for job on cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer to finish
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ /___/ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ║ ║
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.2MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s] README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 245kB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 10.7MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.12MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-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<00:50, 97.1MB/s] model-00001-of-00003.safetensors: 1%| | 31.5M/4.94G [00:00<01:29, 54.7MB/s] model-00001-of-00003.safetensors: 1%| | 52.4M/4.94G [00:00<00:56, 86.7MB/s] model-00001-of-00003.safetensors: 2%|▏ | 115M/4.94G [00:00<00:23, 208MB/s] model-00001-of-00003.safetensors: 4%|▍ | 210M/4.94G [00:00<00:12, 378MB/s] model-00001-of-00003.safetensors: 5%|▌ | 262M/4.94G [00:00<00:11, 415MB/s] model-00001-of-00003.safetensors: 10%|▉ | 493M/4.94G [00:01<00:04, 893MB/s] model-00001-of-00003.safetensors: 13%|█▎ | 619M/4.94G [00:01<00:04, 976MB/s] model-00001-of-00003.safetensors: 15%|█▌ | 765M/4.94G [00:01<00:03, 1.09GB/s] model-00001-of-00003.safetensors: 18%|█▊ | 891M/4.94G [00:01<00:03, 1.01GB/s] model-00001-of-00003.safetensors: 24%|██▍ | 1.17G/4.94G [00:01<00:02, 1.48GB/s] model-00001-of-00003.safetensors: 27%|██▋ | 1.34G/4.94G [00:01<00:02, 1.52GB/s] model-00001-of-00003.safetensors: 32%|███▏ | 1.59G/4.94G [00:01<00:01, 1.77GB/s] model-00001-of-00003.safetensors: 36%|███▌ | 1.78G/4.94G [00:01<00:01, 1.75GB/s] model-00001-of-00003.safetensors: 40%|███▉ | 1.97G/4.94G [00:02<00:01, 1.51GB/s] model-00001-of-00003.safetensors: 43%|████▎ | 2.14G/4.94G [00:02<00:01, 1.50GB/s] model-00001-of-00003.safetensors: 46%|████▋ | 2.30G/4.94G [00:02<00:02, 1.25GB/s] model-00001-of-00003.safetensors: 50%|█████ | 2.50G/4.94G [00:02<00:01, 1.40GB/s] model-00001-of-00003.safetensors: 54%|█████▎ | 2.65G/4.94G [00:02<00:01, 1.35GB/s] model-00001-of-00003.safetensors: 57%|█████▋ | 2.80G/4.94G [00:02<00:01, 1.27GB/s] model-00001-of-00003.safetensors: 59%|█████▉ | 2.94G/4.94G [00:02<00:01, 1.14GB/s] model-00001-of-00003.safetensors: 62%|██████▏ | 3.06G/4.94G [00:02<00:01, 1.12GB/s] model-00001-of-00003.safetensors: 64%|██████▍ | 3.19G/4.94G [00:03<00:01, 1.11GB/s] model-00001-of-00003.safetensors: 69%|██████▊ | 3.40G/4.94G [00:03<00:01, 1.33GB/s] model-00001-of-00003.safetensors: 72%|███████▏ | 3.54G/4.94G [00:03<00:01, 1.21GB/s] model-00001-of-00003.safetensors: 74%|███████▍ | 3.67G/4.94G [00:03<00:01, 1.19GB/s] model-00001-of-00003.safetensors: 78%|███████▊ | 3.85G/4.94G [00:03<00:00, 1.33GB/s] model-00001-of-00003.safetensors: 81%|████████ | 4.00G/4.94G [00:03<00:00, 1.08GB/s] model-00001-of-00003.safetensors: 83%|████████▎ | 4.12G/4.94G [00:03<00:00, 1.06GB/s] model-00001-of-00003.safetensors: 86%|████████▌ | 4.24G/4.94G [00:04<00:00, 1.04GB/s] model-00001-of-00003.safetensors: 96%|█████████▌| 4.75G/4.94G [00:04<00:00, 2.03GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:04<00:00, 1.17GB/s]
cgato-thespice-7b-ft-v0-4-1-v3-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 [00:00<04:52, 17.1MB/s] model-00002-of-00003.safetensors: 4%|▍ | 220M/5.00G [00:00<00:11, 407MB/s] model-00002-of-00003.safetensors: 10%|█ | 514M/5.00G [00:00<00:04, 930MB/s] model-00002-of-00003.safetensors: 14%|█▍ | 713M/5.00G [00:01<00:05, 790MB/s] model-00002-of-00003.safetensors: 17%|█▋ | 860M/5.00G [00:01<00:04, 899MB/s] model-00002-of-00003.safetensors: 21%|██ | 1.03G/5.00G [00:01<00:03, 1.05GB/s] model-00002-of-00003.safetensors: 24%|██▍ | 1.20G/5.00G [00:01<00:03, 1.17GB/s] model-00002-of-00003.safetensors: 32%|███▏ | 1.58G/5.00G [00:01<00:01, 1.79GB/s] model-00002-of-00003.safetensors: 36%|███▌ | 1.80G/5.00G [00:01<00:02, 1.40GB/s] model-00002-of-00003.safetensors: 40%|███▉ | 1.99G/5.00G [00:01<00:02, 1.41GB/s] model-00002-of-00003.safetensors: 43%|████▎ | 2.17G/5.00G [00:02<00:02, 1.24GB/s] model-00002-of-00003.safetensors: 46%|████▋ | 2.32G/5.00G [00:02<00:02, 1.25GB/s] model-00002-of-00003.safetensors: 49%|████▉ | 2.46G/5.00G [00:02<00:02, 1.20GB/s] model-00002-of-00003.safetensors: 52%|█████▏ | 2.60G/5.00G [00:02<00:01, 1.22GB/s] model-00002-of-00003.safetensors: 55%|█████▍ | 2.74G/5.00G [00:02<00:01, 1.25GB/s] model-00002-of-00003.safetensors: 57%|█████▋ | 2.87G/5.00G [00:02<00:02, 959MB/s] model-00002-of-00003.safetensors: 60%|█████▉ | 2.99G/5.00G [00:02<00:02, 981MB/s] model-00002-of-00003.safetensors: 64%|██████▍ | 3.19G/5.00G [00:03<00:01, 1.22GB/s] model-00002-of-00003.safetensors: 66%|██████▋ | 3.32G/5.00G [00:03<00:01, 1.19GB/s] model-00002-of-00003.safetensors: 70%|███████ | 3.52G/5.00G [00:03<00:01, 1.35GB/s] model-00002-of-00003.safetensors: 74%|███████▍ | 3.69G/5.00G [00:03<00:00, 1.43GB/s] model-00002-of-00003.safetensors: 77%|███████▋ | 3.86G/5.00G [00:03<00:00, 1.47GB/s] model-00002-of-00003.safetensors: 80%|████████ | 4.02G/5.00G [00:03<00:00, 1.35GB/s] model-00002-of-00003.safetensors: 83%|████████▎ | 4.16G/5.00G [00:03<00:00, 1.30GB/s] model-00002-of-00003.safetensors: 86%|████████▋ | 4.32G/5.00G [00:03<00:00, 1.34GB/s] model-00002-of-00003.safetensors: 93%|█████████▎| 4.66G/5.00G [00:03<00:00, 1.87GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:04<00:00, 1.22GB/s]
cgato-thespice-7b-ft-v0-4-1-v3-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<01:38, 46.1MB/s] model-00003-of-00003.safetensors: 3%|▎ | 126M/4.54G [00:00<00:10, 421MB/s] model-00003-of-00003.safetensors: 4%|▍ | 189M/4.54G [00:00<00:10, 405MB/s] model-00003-of-00003.safetensors: 6%|▋ | 294M/4.54G [00:00<00:07, 534MB/s] model-00003-of-00003.safetensors: 10%|▉ | 451M/4.54G [00:00<00:05, 809MB/s] model-00003-of-00003.safetensors: 12%|█▏ | 556M/4.54G [00:00<00:04, 872MB/s] model-00003-of-00003.safetensors: 15%|█▍ | 671M/4.54G [00:00<00:04, 855MB/s] model-00003-of-00003.safetensors: 17%|█▋ | 765M/4.54G [00:01<00:04, 786MB/s] model-00003-of-00003.safetensors: 20%|██ | 912M/4.54G [00:01<00:03, 952MB/s] model-00003-of-00003.safetensors: 22%|██▏ | 1.02G/4.54G [00:01<00:03, 948MB/s] model-00003-of-00003.safetensors: 29%|██▉ | 1.32G/4.54G [00:01<00:02, 1.51GB/s] model-00003-of-00003.safetensors: 33%|███▎ | 1.49G/4.54G [00:01<00:02, 1.47GB/s] model-00003-of-00003.safetensors: 36%|███▋ | 1.65G/4.54G [00:01<00:02, 1.11GB/s] model-00003-of-00003.safetensors: 39%|███▉ | 1.78G/4.54G [00:01<00:02, 1.05GB/s] model-00003-of-00003.safetensors: 42%|████▏ | 1.91G/4.54G [00:02<00:03, 867MB/s] model-00003-of-00003.safetensors: 45%|████▌ | 2.06G/4.54G [00:02<00:02, 984MB/s] model-00003-of-00003.safetensors: 48%|████▊ | 2.17G/4.54G [00:02<00:02, 1.00GB/s] model-00003-of-00003.safetensors: 52%|█████▏ | 2.38G/4.54G [00:02<00:01, 1.25GB/s] model-00003-of-00003.safetensors: 56%|█████▌ | 2.55G/4.54G [00:02<00:01, 1.34GB/s] model-00003-of-00003.safetensors: 59%|█████▉ | 2.69G/4.54G [00:02<00:01, 1.27GB/s] model-00003-of-00003.safetensors: 62%|██████▏ | 2.83G/4.54G [00:02<00:01, 1.05GB/s] model-00003-of-00003.safetensors: 65%|██████▌ | 2.96G/4.54G [00:03<00:01, 932MB/s] model-00003-of-00003.safetensors: 68%|██████▊ | 3.08G/4.54G [00:03<00:01, 981MB/s] model-00003-of-00003.safetensors: 72%|███████▏ | 3.28G/4.54G [00:03<00:01, 1.21GB/s] model-00003-of-00003.safetensors: 75%|███████▌ | 3.42G/4.54G [00:03<00:00, 1.22GB/s] model-00003-of-00003.safetensors: 80%|███████▉ | 3.62G/4.54G [00:03<00:00, 1.42GB/s] model-00003-of-00003.safetensors: 84%|████████▎ | 3.80G/4.54G [00:03<00:00, 1.37GB/s] model-00003-of-00003.safetensors: 91%|█████████▏| 4.15G/4.54G [00:03<00:00, 1.90GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:03<00:00, 1.17GB/s]
cgato-thespice-7b-ft-v0-4-1-v3-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, 173MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 3.41MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 60.8MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 7.70MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Downloaded to shared memory in 13.466s
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Reading /tmp/tmpmfe9r3n7/model.safetensors.index.json
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<07:46, 1.61s/it] Profiling: 4%|▍ | 12/291 [00:01<00:29, 9.44it/s] Profiling: 7%|▋ | 21/291 [00:01<00:15, 17.70it/s] Profiling: 11%|█▏ | 33/291 [00:01<00:08, 30.77it/s] Profiling: 15%|█▌ | 45/291 [00:02<00:05, 44.28it/s] Profiling: 19%|█▉ | 55/291 [00:02<00:04, 53.91it/s] Profiling: 22%|██▏ | 65/291 [00:02<00:03, 63.11it/s] Profiling: 28%|██▊ | 81/291 [00:02<00:02, 82.35it/s] Profiling: 32%|███▏ | 93/291 [00:02<00:02, 85.46it/s] Profiling: 36%|███▌ | 104/291 [00:03<00:04, 43.90it/s] Profiling: 41%|████ | 120/291 [00:03<00:02, 59.76it/s] Profiling: 45%|████▌ | 131/291 [00:03<00:02, 65.89it/s] Profiling: 51%|█████ | 147/291 [00:03<00:01, 82.68it/s] Profiling: 55%|█████▍ | 159/291 [00:03<00:01, 86.17it/s] Profiling: 60%|█████▉ | 174/291 [00:03<00:01, 99.27it/s] Profiling: 64%|██████▍ | 186/291 [00:03<00:01, 99.07it/s] Profiling: 70%|██████▉ | 203/291 [00:03<00:00, 116.32it/s] Profiling: 74%|███████▍ | 216/291 [00:05<00:03, 20.46it/s] Profiling: 79%|███████▊ | 229/291 [00:05<00:02, 26.89it/s] Profiling: 82%|████████▏ | 240/291 [00:06<00:01, 33.03it/s] Profiling: 88%|████████▊ | 256/291 [00:06<00:00, 45.09it/s] Profiling: 92%|█████████▏| 268/291 [00:06<00:00, 53.21it/s] Profiling: 97%|█████████▋| 283/291 [00:06<00:00, 66.69it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 43.67it/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: quantized model in 19.172s
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Processed model cgato/TheSpice-7b-FT-v0.4.1 in 33.650s
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3/config.json
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3/special_tokens_map.json
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3/tokenizer_config.json
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3/tokenizer.model
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3/tokenizer.json
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-ft-v0-4-1-v3/mkml_model.tensors
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-ft-v0-4-1-v3-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-ft-v0-4-1-v3-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.09MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-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-ft-v0-4-1-v3-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.01MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 10.8MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 32.7MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-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-ft-v0-4-1-v3-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:27, 51.6MB/s] pytorch_model.bin: 27%|██▋ | 388M/1.44G [00:00<00:01, 967MB/s] pytorch_model.bin: 41%|████ | 587M/1.44G [00:00<00:00, 860MB/s] pytorch_model.bin: 51%|█████ | 732M/1.44G [00:00<00:00, 922MB/s] pytorch_model.bin: 61%|██████ | 878M/1.44G [00:01<00:00, 1.02GB/s] pytorch_model.bin: 71%|███████ | 1.03G/1.44G [00:01<00:00, 1.10GB/s] pytorch_model.bin: 80%|████████ | 1.16G/1.44G [00:01<00:00, 1.08GB/s] pytorch_model.bin: 99%|█████████▊| 1.42G/1.44G [00:01<00:00, 1.35GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 549MB/s]
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Saving duration: 0.319s
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.760s
cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-ft-v0-4-1-v3_reward/reward.tensors
Job cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer completed after 63.83s with status: succeeded
Stopping job with name cgato-thespice-7b-ft-v0-4-1-v3-mkmlizer
Pipeline stage MKMLizer completed in 68.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-ft-v0-4-1-v3
Waiting for inference service cgato-thespice-7b-ft-v0-4-1-v3 to be ready
Inference service cgato-thespice-7b-ft-v0-4-1-v3 ready after 50.379586935043335s
Pipeline stage ISVCDeployer completed in 58.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7692348957061768s
Received healthy response to inference request in 1.2628538608551025s
Received healthy response to inference request in 1.550905466079712s
Received healthy response to inference request in 1.2510507106781006s
Received healthy response to inference request in 1.2404565811157227s
5 requests
0 failed requests
5th percentile: 1.2425754070281982
10th percentile: 1.2446942329406738
20th percentile: 1.248931884765625
30th percentile: 1.253411340713501
40th percentile: 1.2581326007843017
50th percentile: 1.2628538608551025
60th percentile: 1.3780745029449464
70th percentile: 1.49329514503479
80th percentile: 1.5945713520050049
90th percentile: 1.6819031238555908
95th percentile: 1.7255690097808838
99th percentile: 1.7605017185211183
mean time: 1.414900302886963
Pipeline stage StressChecker completed in 7.88s
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-ft-v0-4-1_v3 status is now deployed due to DeploymentManager action
cgato-thespice-7b-ft-v0-4-1_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-ft-v0-4-1_v3
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-ft-v0-4-1-v3 is running
Tearing down inference service cgato-thespice-7b-ft-v0-4-1-v3
Toredown service cgato-thespice-7b-ft-v0-4-1-v3
Pipeline stage ISVCDeleter completed in 4.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-v0-4-1-v3/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-v0-4-1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.22s
cgato-thespice-7b-ft-v0-4-1_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics