submission_id: nitral-ai-nsm-delta-7b_v1
developer_uid: Nitral-AI
status: torndown
model_repo: Nitral-AI/NSM-delta-7B
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: 2024-04-18T01:42:44+00:00
model_name: nitral-ai-nsm-delta-7b_v1
model_eval_status: success
model_group: Nitral-AI/NSM-delta-7B
num_battles: 6050
num_wins: 3222
celo_rating: 1168.14
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: nitral-ai-nsm-delta-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: Nitral-AI/NSM-delta-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-17
win_ratio: 0.5325619834710744
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-nsm-delta-7b-v1-mkmlizer
Waiting for job on nitral-ai-nsm-delta-7b-v1-mkmlizer to finish
nitral-ai-nsm-delta-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ _____ __ __ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ /___/ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ Version: 0.6.11 ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ belonging to: ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ║ ║
nitral-ai-nsm-delta-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-nsm-delta-7b-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 11.0MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: README.md: 0%| | 0.00/1.02k [00:00<?, ?B/s] README.md: 100%|██████████| 1.02k/1.02k [00:00<00:00, 8.90MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: config.json: 0%| | 0.00/691 [00:00<?, ?B/s] config.json: 100%|██████████| 691/691 [00:00<00:00, 9.03MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: mergekit_config.yml: 0%| | 0.00/373 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 373/373 [00:00<00:00, 5.86MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: model-00001-of-00002.safetensors: 0%| | 0.00/9.94G [00:00<?, ?B/s] model-00001-of-00002.safetensors: 0%| | 10.5M/9.94G [00:00<06:48, 24.3MB/s] model-00001-of-00002.safetensors: 0%| | 21.0M/9.94G [00:00<04:24, 37.5MB/s] model-00001-of-00002.safetensors: 1%| | 73.4M/9.94G [00:00<01:40, 97.8MB/s] model-00001-of-00002.safetensors: 1%|▏ | 126M/9.94G [00:01<00:57, 172MB/s] model-00001-of-00002.safetensors: 2%|▏ | 157M/9.94G [00:01<00:52, 187MB/s] model-00001-of-00002.safetensors: 2%|▏ | 220M/9.94G [00:01<00:41, 232MB/s] model-00001-of-00002.safetensors: 3%|▎ | 273M/9.94G [00:01<00:35, 269MB/s] model-00001-of-00002.safetensors: 4%|▍ | 440M/9.94G [00:01<00:18, 514MB/s] model-00001-of-00002.safetensors: 5%|▌ | 503M/9.94G [00:01<00:22, 414MB/s] model-00001-of-00002.safetensors: 6%|▌ | 577M/9.94G [00:02<00:20, 447MB/s] model-00001-of-00002.safetensors: 6%|▋ | 629M/9.94G [00:02<00:21, 438MB/s] model-00001-of-00002.safetensors: 8%|▊ | 797M/9.94G [00:02<00:13, 698MB/s] model-00001-of-00002.safetensors: 9%|▉ | 881M/9.94G [00:02<00:13, 662MB/s] model-00001-of-00002.safetensors: 10%|▉ | 965M/9.94G [00:02<00:14, 621MB/s] model-00001-of-00002.safetensors: 10%|█ | 1.04G/9.94G [00:02<00:16, 528MB/s] model-00001-of-00002.safetensors: 12%|█▏ | 1.23G/9.94G [00:02<00:10, 811MB/s] model-00001-of-00002.safetensors: 14%|█▎ | 1.36G/9.94G [00:02<00:09, 934MB/s] model-00001-of-00002.safetensors: 15%|█▍ | 1.48G/9.94G [00:03<00:17, 495MB/s] model-00001-of-00002.safetensors: 16%|█▌ | 1.56G/9.94G [00:03<00:16, 515MB/s] model-00001-of-00002.safetensors: 18%|█▊ | 1.82G/9.94G [00:03<00:09, 858MB/s] model-00001-of-00002.safetensors: 23%|██▎ | 2.30G/9.94G [00:03<00:04, 1.59GB/s] model-00001-of-00002.safetensors: 26%|██▋ | 2.61G/9.94G [00:03<00:04, 1.74GB/s] model-00001-of-00002.safetensors: 29%|██▊ | 2.84G/9.94G [00:04<00:05, 1.28GB/s] model-00001-of-00002.safetensors: 30%|███ | 3.02G/9.94G [00:04<00:05, 1.26GB/s] model-00001-of-00002.safetensors: 32%|███▏ | 3.19G/9.94G [00:04<00:06, 1.05GB/s] model-00001-of-00002.safetensors: 33%|███▎ | 3.32G/9.94G [00:04<00:06, 1.01GB/s] model-00001-of-00002.safetensors: 35%|███▌ | 3.52G/9.94G [00:04<00:05, 1.19GB/s] model-00001-of-00002.safetensors: 38%|███▊ | 3.79G/9.94G [00:05<00:04, 1.46GB/s] model-00001-of-00002.safetensors: 40%|███▉ | 3.96G/9.94G [00:05<00:04, 1.36GB/s] model-00001-of-00002.safetensors: 41%|████▏ | 4.12G/9.94G [00:05<00:04, 1.30GB/s] model-00001-of-00002.safetensors: 43%|████▎ | 4.27G/9.94G [00:05<00:05, 1.10GB/s] model-00001-of-00002.safetensors: 44%|████▍ | 4.39G/9.94G [00:05<00:05, 1.11GB/s] model-00001-of-00002.safetensors: 46%|████▌ | 4.56G/9.94G [00:05<00:04, 1.22GB/s] model-00001-of-00002.safetensors: 48%|████▊ | 4.81G/9.94G [00:05<00:03, 1.50GB/s] model-00001-of-00002.safetensors: 50%|█████ | 5.01G/9.94G [00:05<00:03, 1.61GB/s] model-00001-of-00002.safetensors: 53%|█████▎ | 5.28G/9.94G [00:06<00:02, 1.86GB/s] model-00001-of-00002.safetensors: 55%|█████▌ | 5.49G/9.94G [00:06<00:02, 1.88GB/s] model-00001-of-00002.safetensors: 58%|█████▊ | 5.78G/9.94G [00:06<00:01, 2.13GB/s] model-00001-of-00002.safetensors: 60%|██████ | 6.00G/9.94G [00:06<00:02, 1.54GB/s] model-00001-of-00002.safetensors: 62%|██████▏ | 6.21G/9.94G [00:06<00:02, 1.64GB/s] model-00001-of-00002.safetensors: 64%|██████▍ | 6.40G/9.94G [00:06<00:02, 1.57GB/s] model-00001-of-00002.safetensors: 66%|██████▌ | 6.57G/9.94G [00:06<00:02, 1.44GB/s] model-00001-of-00002.safetensors: 68%|██████▊ | 6.78G/9.94G [00:07<00:01, 1.58GB/s] model-00001-of-00002.safetensors: 70%|███████ | 6.96G/9.94G [00:07<00:02, 1.38GB/s] model-00001-of-00002.safetensors: 72%|███████▏ | 7.12G/9.94G [00:07<00:02, 1.34GB/s] model-00001-of-00002.safetensors: 75%|███████▍ | 7.44G/9.94G [00:07<00:01, 1.77GB/s] model-00001-of-00002.safetensors: 77%|███████▋ | 7.64G/9.94G [00:07<00:01, 1.60GB/s] model-00001-of-00002.safetensors: 79%|███████▉ | 7.86G/9.94G [00:07<00:01, 1.72GB/s] model-00001-of-00002.safetensors: 81%|████████ | 8.05G/9.94G [00:07<00:01, 1.68GB/s] model-00001-of-00002.safetensors: 83%|████████▎ | 8.23G/9.94G [00:07<00:01, 1.44GB/s] model-00001-of-00002.safetensors: 84%|████████▍ | 8.40G/9.94G [00:08<00:01, 1.48GB/s] model-00001-of-00002.safetensors: 87%|████████▋ | 8.62G/9.94G [00:08<00:00, 1.51GB/s] model-00001-of-00002.safetensors: 88%|████████▊ | 8.78G/9.94G [00:08<00:00, 1.46GB/s] model-00001-of-00002.safetensors: 90%|████████▉ | 8.93G/9.94G [00:08<00:00, 1.47GB/s] model-00001-of-00002.safetensors: 92%|█████████▏| 9.11G/9.94G [00:08<00:00, 1.53GB/s] model-00001-of-00002.safetensors: 94%|█████████▎| 9.31G/9.94G [00:08<00:00, 1.65GB/s] model-00001-of-00002.safetensors: 95%|█████████▌| 9.49G/9.94G [00:08<00:00, 1.64GB/s] model-00001-of-00002.safetensors: 97%|█████████▋| 9.66G/9.94G [00:08<00:00, 1.62GB/s] model-00001-of-00002.safetensors: 99%|█████████▉| 9.83G/9.94G [00:09<00:00, 1.23GB/s] model-00001-of-00002.safetensors: 100%|█████████▉| 9.94G/9.94G [00:09<00:00, 1.07GB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: model-00002-of-00002.safetensors: 0%| | 0.00/4.54G [00:00<?, ?B/s] model-00002-of-00002.safetensors: 0%| | 10.5M/4.54G [00:00<03:00, 25.1MB/s] model-00002-of-00002.safetensors: 1%|▏ | 62.9M/4.54G [00:00<00:31, 141MB/s] model-00002-of-00002.safetensors: 2%|▏ | 94.4M/4.54G [00:00<00:34, 130MB/s] model-00002-of-00002.safetensors: 3%|▎ | 136M/4.54G [00:00<00:26, 164MB/s] model-00002-of-00002.safetensors: 4%|▍ | 199M/4.54G [00:01<00:20, 211MB/s] model-00002-of-00002.safetensors: 6%|▌ | 252M/4.54G [00:01<00:17, 244MB/s] model-00002-of-00002.safetensors: 7%|▋ | 304M/4.54G [00:01<00:15, 268MB/s] model-00002-of-00002.safetensors: 7%|▋ | 336M/4.54G [00:01<00:17, 243MB/s] model-00002-of-00002.safetensors: 8%|▊ | 377M/4.54G [00:01<00:14, 278MB/s] model-00002-of-00002.safetensors: 9%|▉ | 409M/4.54G [00:01<00:15, 265MB/s] model-00002-of-00002.safetensors: 10%|█ | 472M/4.54G [00:02<00:12, 332MB/s] model-00002-of-00002.safetensors: 11%|█▏ | 514M/4.54G [00:02<00:11, 345MB/s] model-00002-of-00002.safetensors: 13%|█▎ | 577M/4.54G [00:02<00:09, 403MB/s] model-00002-of-00002.safetensors: 14%|█▍ | 629M/4.54G [00:02<00:09, 408MB/s] model-00002-of-00002.safetensors: 15%|█▌ | 682M/4.54G [00:02<00:08, 435MB/s] model-00002-of-00002.safetensors: 16%|█▌ | 734M/4.54G [00:02<00:09, 385MB/s] model-00002-of-00002.safetensors: 17%|█▋ | 776M/4.54G [00:02<00:09, 389MB/s] model-00002-of-00002.safetensors: 18%|█▊ | 818M/4.54G [00:03<00:12, 290MB/s] model-00002-of-00002.safetensors: 19%|█▉ | 860M/4.54G [00:03<00:11, 311MB/s] model-00002-of-00002.safetensors: 25%|██▌ | 1.15G/4.54G [00:03<00:03, 863MB/s] model-00002-of-00002.safetensors: 28%|██▊ | 1.26G/4.54G [00:03<00:04, 692MB/s] model-00002-of-00002.safetensors: 30%|██▉ | 1.34G/4.54G [00:03<00:04, 710MB/s] model-00002-of-00002.safetensors: 42%|████▏ | 1.90G/4.54G [00:03<00:01, 1.72GB/s] model-00002-of-00002.safetensors: 46%|████▌ | 2.10G/4.54G [00:04<00:02, 1.04GB/s] model-00002-of-00002.safetensors: 50%|████▉ | 2.25G/4.54G [00:04<00:02, 889MB/s] model-00002-of-00002.safetensors: 52%|█████▏ | 2.38G/4.54G [00:04<00:02, 832MB/s] model-00002-of-00002.safetensors: 55%|█████▍ | 2.50G/4.54G [00:04<00:03, 670MB/s] model-00002-of-00002.safetensors: 57%|█████▋ | 2.59G/4.54G [00:05<00:02, 659MB/s] model-00002-of-00002.safetensors: 59%|█████▉ | 2.67G/4.54G [00:05<00:03, 584MB/s] model-00002-of-00002.safetensors: 61%|██████ | 2.75G/4.54G [00:05<00:03, 507MB/s] model-00002-of-00002.safetensors: 62%|██████▏ | 2.81G/4.54G [00:05<00:03, 450MB/s] model-00002-of-00002.safetensors: 64%|██████▍ | 2.93G/4.54G [00:05<00:02, 564MB/s] model-00002-of-00002.safetensors: 70%|███████ | 3.20G/4.54G [00:05<00:01, 981MB/s] model-00002-of-00002.safetensors: 73%|███████▎ | 3.33G/4.54G [00:05<00:01, 981MB/s] model-00002-of-00002.safetensors: 76%|███████▌ | 3.46G/4.54G [00:06<00:01, 957MB/s] model-00002-of-00002.safetensors: 79%|███████▉ | 3.58G/4.54G [00:06<00:01, 889MB/s] model-00002-of-00002.safetensors: 82%|████████▏ | 3.70G/4.54G [00:06<00:00, 944MB/s] model-00002-of-00002.safetensors: 84%|████████▍ | 3.81G/4.54G [00:06<00:00, 946MB/s] model-00002-of-00002.safetensors: 92%|█████████▏| 4.16G/4.54G [00:06<00:00, 1.59GB/s] model-00002-of-00002.safetensors: 96%|█████████▌| 4.34G/4.54G [00:06<00:00, 1.10GB/s] model-00002-of-00002.safetensors: 99%|█████████▉| 4.49G/4.54G [00:07<00:00, 1.10GB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 4.54G/4.54G [00:07<00:00, 609MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: model.safetensors.index.json: 0%| | 0.00/22.8k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 22.8k/22.8k [00:00<00:00, 92.8MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/625 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 625/625 [00:00<00:00, 8.86MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 19.1MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 63.5MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.01k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.01k/1.01k [00:00<00:00, 16.0MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: Downloaded to shared memory in 18.860s
nitral-ai-nsm-delta-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-nsm-delta-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
nitral-ai-nsm-delta-7b-v1-mkmlizer: Reading /tmp/tmp3df1vfef/model.safetensors.index.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<07:22, 1.53s/it] Profiling: 4%|▍ | 13/291 [00:01<00:25, 10.74it/s] Profiling: 9%|▉ | 26/291 [00:01<00:11, 23.44it/s] Profiling: 13%|█▎ | 39/291 [00:01<00:06, 37.44it/s] Profiling: 18%|█▊ | 53/291 [00:01<00:04, 52.38it/s] Profiling: 23%|██▎ | 67/291 [00:02<00:03, 67.98it/s] Profiling: 27%|██▋ | 80/291 [00:02<00:02, 79.33it/s] Profiling: 33%|███▎ | 95/291 [00:02<00:02, 94.82it/s] Profiling: 37%|███▋ | 108/291 [00:02<00:01, 98.68it/s] Profiling: 43%|████▎ | 125/291 [00:02<00:01, 115.06it/s] Profiling: 48%|████▊ | 139/291 [00:02<00:01, 119.05it/s] Profiling: 53%|█████▎ | 153/291 [00:02<00:01, 121.63it/s] Profiling: 57%|█████▋ | 167/291 [00:02<00:00, 124.68it/s] Profiling: 63%|██████▎ | 183/291 [00:02<00:00, 134.41it/s] Profiling: 68%|██████▊ | 198/291 [00:03<00:00, 128.62it/s] Profiling: 73%|███████▎ | 212/291 [00:05<00:03, 20.14it/s] Profiling: 77%|███████▋ | 223/291 [00:05<00:02, 25.04it/s] Profiling: 82%|████████▏ | 238/291 [00:05<00:01, 34.23it/s] Profiling: 86%|████████▌ | 250/291 [00:05<00:00, 42.19it/s] Profiling: 91%|█████████ | 264/291 [00:05<00:00, 53.82it/s] Profiling: 95%|█████████▌| 277/291 [00:05<00:00, 64.51it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 48.12it/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: quantized model in 17.484s
nitral-ai-nsm-delta-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-nsm-delta-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-nsm-delta-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1/special_tokens_map.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1/tokenizer.model
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1/config.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1/tokenizer_config.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1/tokenizer.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/nitral-ai-nsm-delta-7b-v1/mkml_model.tensors
nitral-ai-nsm-delta-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-nsm-delta-7b-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.
nitral-ai-nsm-delta-7b-v1-mkmlizer: warnings.warn(
nitral-ai-nsm-delta-7b-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.4MB/s]
nitral-ai-nsm-delta-7b-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.
nitral-ai-nsm-delta-7b-v1-mkmlizer: warnings.warn(
nitral-ai-nsm-delta-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.31MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 11.0MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 32.5MB/s]
nitral-ai-nsm-delta-7b-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.
nitral-ai-nsm-delta-7b-v1-mkmlizer: warnings.warn(
nitral-ai-nsm-delta-7b-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:59, 24.1MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:22, 64.1MB/s] pytorch_model.bin: 4%|▍ | 62.9M/1.44G [00:00<00:11, 123MB/s] pytorch_model.bin: 8%|▊ | 115M/1.44G [00:00<00:06, 191MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:00<00:04, 267MB/s] pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:01<00:03, 381MB/s] pytorch_model.bin: 22%|██▏ | 315M/1.44G [00:01<00:02, 417MB/s] pytorch_model.bin: 25%|██▌ | 367M/1.44G [00:01<00:03, 280MB/s] pytorch_model.bin: 30%|███ | 440M/1.44G [00:01<00:02, 363MB/s] pytorch_model.bin: 39%|███▉ | 566M/1.44G [00:01<00:01, 545MB/s] pytorch_model.bin: 47%|████▋ | 679M/1.44G [00:01<00:01, 645MB/s] pytorch_model.bin: 56%|█████▋ | 815M/1.44G [00:01<00:00, 796MB/s] pytorch_model.bin: 68%|██████▊ | 983M/1.44G [00:02<00:00, 1.00GB/s] pytorch_model.bin: 76%|███████▌ | 1.10G/1.44G [00:02<00:00, 1.04GB/s] pytorch_model.bin: 86%|████████▌ | 1.25G/1.44G [00:02<00:00, 1.15GB/s] pytorch_model.bin: 97%|█████████▋| 1.40G/1.44G [00:02<00:00, 611MB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:03<00:00, 454MB/s]
nitral-ai-nsm-delta-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-nsm-delta-7b-v1-mkmlizer: Saving duration: 0.283s
nitral-ai-nsm-delta-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.534s
nitral-ai-nsm-delta-7b-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-nsm-delta-7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-nsm-delta-7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/config.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/tokenizer_config.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/special_tokens_map.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/merges.txt
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/vocab.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/tokenizer.json
nitral-ai-nsm-delta-7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-nsm-delta-7b-v1_reward/reward.tensors
Job nitral-ai-nsm-delta-7b-v1-mkmlizer completed after 64.32s with status: succeeded
Stopping job with name nitral-ai-nsm-delta-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 66.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-nsm-delta-7b-v1
Waiting for inference service nitral-ai-nsm-delta-7b-v1 to be ready
Inference service nitral-ai-nsm-delta-7b-v1 ready after 40.252564668655396s
Pipeline stage ISVCDeployer completed in 47.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.759657621383667s
Received healthy response to inference request in 1.3829925060272217s
Received healthy response to inference request in 1.193044900894165s
Received healthy response to inference request in 1.1924128532409668s
Received healthy response to inference request in 1.206268548965454s
5 requests
0 failed requests
5th percentile: 1.1925392627716065
10th percentile: 1.1926656723022462
20th percentile: 1.1929184913635253
30th percentile: 1.1956896305084228
40th percentile: 1.2009790897369386
50th percentile: 1.206268548965454
60th percentile: 1.276958131790161
70th percentile: 1.3476477146148682
80th percentile: 1.4583255290985109
90th percentile: 1.6089915752410888
95th percentile: 1.6843245983123778
99th percentile: 1.7445910167694092
mean time: 1.346875286102295
Pipeline stage StressChecker completed in 7.68s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-nsm-delta-7b_v1 status is now deployed due to DeploymentManager action
nitral-ai-nsm-delta-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-nsm-delta-7b_v1
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-nsm-delta-7b-v1 is running
Tearing down inference service nitral-ai-nsm-delta-7b-v1
Toredown service nitral-ai-nsm-delta-7b-v1
Pipeline stage ISVCDeleter completed in 3.94s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-nsm-delta-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-nsm-delta-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key nitral-ai-nsm-delta-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-nsm-delta-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-nsm-delta-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key nitral-ai-nsm-delta-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-nsm-delta-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-nsm-delta-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-nsm-delta-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-nsm-delta-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-nsm-delta-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-nsm-delta-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-nsm-delta-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.14s
nitral-ai-nsm-delta-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics