submission_id: inv-gamma-alpha-7b_v1
developer_uid: Inv
status: torndown
model_repo: Inv/Gamma-Alpha-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': 'This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}.\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: 2024-03-28T19:52:40+00:00
model_name: inv-gamma-alpha-7b_v1
model_eval_status: success
model_group: Inv/Gamma-Alpha-7B
num_battles: 96397
num_wins: 51392
celo_rating: 1181.12
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: inv-gamma-alpha-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: Inv/Gamma-Alpha-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-28
win_ratio: 0.5331286243347823
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-gamma-alpha-7b-v1-mkmlizer
Waiting for job on inv-gamma-alpha-7b-v1-mkmlizer to finish
Stopping job with name inv-gamma-alpha-7b-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name inv-gamma-alpha-7b-v1-mkmlizer
Waiting for job on inv-gamma-alpha-7b-v1-mkmlizer to finish
inv-gamma-alpha-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-gamma-alpha-7b-v1-mkmlizer: ║ _____ __ __ ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ /___/ ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ Version: 0.6.11 ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ belonging to: ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ Chai Research Corp. ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
inv-gamma-alpha-7b-v1-mkmlizer: ║ ║
inv-gamma-alpha-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-gamma-alpha-7b-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.8MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: README.md: 0%| | 0.00/1.07k [00:00<?, ?B/s] README.md: 100%|██████████| 1.07k/1.07k [00:00<00:00, 16.7MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: config.json: 0%| | 0.00/641 [00:00<?, ?B/s] config.json: 100%|██████████| 641/641 [00:00<00:00, 6.81MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: mergekit_config.yml: 0%| | 0.00/468 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 468/468 [00:00<00:00, 5.48MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 10.5M/1.98G [00:01<03:29, 9.38MB/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<03:02, 10.7MB/s] model-00001-of-00008.safetensors: 3%|▎ | 52.4M/1.98G [00:02<00:58, 32.9MB/s] model-00001-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:02<00:39, 48.5MB/s] model-00001-of-00008.safetensors: 5%|▍ | 94.4M/1.98G [00:02<00:32, 58.8MB/s] model-00001-of-00008.safetensors: 6%|▋ | 126M/1.98G [00:02<00:20, 89.4MB/s] model-00001-of-00008.safetensors: 11%|█ | 220M/1.98G [00:02<00:08, 215MB/s] model-00001-of-00008.safetensors: 14%|█▍ | 273M/1.98G [00:02<00:06, 257MB/s] model-00001-of-00008.safetensors: 16%|█▋ | 325M/1.98G [00:03<00:05, 295MB/s] model-00001-of-00008.safetensors: 25%|██▌ | 503M/1.98G [00:03<00:02, 603MB/s] model-00001-of-00008.safetensors: 58%|█████▊ | 1.15G/1.98G [00:03<00:00, 1.94GB/s] model-00001-of-00008.safetensors: 71%|███████▏ | 1.41G/1.98G [00:03<00:00, 882MB/s] model-00001-of-00008.safetensors: 81%|████████ | 1.60G/1.98G [00:03<00:00, 1.01GB/s] model-00001-of-00008.safetensors: 90%|█████████ | 1.79G/1.98G [00:04<00:00, 951MB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 465MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00002-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00002-of-00008.safetensors: 1%| | 10.5M/1.95G [00:01<04:54, 6.58MB/s] model-00002-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:01<01:26, 22.2MB/s] model-00002-of-00008.safetensors: 2%|▏ | 41.9M/1.95G [00:02<01:45, 18.0MB/s] model-00002-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:02<01:18, 24.2MB/s] model-00002-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:02<01:02, 30.3MB/s] model-00002-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:02<00:24, 75.6MB/s] model-00002-of-00008.safetensors: 11%|█▏ | 220M/1.95G [00:03<00:07, 229MB/s] model-00002-of-00008.safetensors: 15%|█▍ | 283M/1.95G [00:03<00:05, 284MB/s] model-00002-of-00008.safetensors: 19%|█▉ | 367M/1.95G [00:03<00:04, 362MB/s] model-00002-of-00008.safetensors: 30%|██▉ | 577M/1.95G [00:03<00:01, 699MB/s] model-00002-of-00008.safetensors: 57%|█████▋ | 1.10G/1.95G [00:03<00:00, 1.44GB/s] model-00002-of-00008.safetensors: 65%|██████▍ | 1.26G/1.95G [00:04<00:00, 744MB/s] model-00002-of-00008.safetensors: 73%|███████▎ | 1.42G/1.95G [00:04<00:00, 831MB/s] model-00002-of-00008.safetensors: 80%|███████▉ | 1.55G/1.95G [00:04<00:00, 656MB/s] model-00002-of-00008.safetensors: 85%|████████▍ | 1.65G/1.95G [00:04<00:00, 657MB/s] model-00002-of-00008.safetensors: 90%|█████████ | 1.76G/1.95G [00:04<00:00, 715MB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 394MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<02:07, 15.2MB/s] model-00003-of-00008.safetensors: 1%| | 21.0M/1.95G [00:02<03:19, 9.67MB/s] model-00003-of-00008.safetensors: 2%|▏ | 41.9M/1.95G [00:02<01:20, 23.8MB/s] model-00003-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:02<00:47, 39.7MB/s] model-00003-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:02<00:35, 52.6MB/s] model-00003-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:02<00:21, 83.7MB/s] model-00003-of-00008.safetensors: 13%|█▎ | 262M/1.95G [00:02<00:05, 291MB/s] model-00003-of-00008.safetensors: 17%|█▋ | 325M/1.95G [00:02<00:04, 333MB/s] model-00003-of-00008.safetensors: 22%|██▏ | 419M/1.95G [00:02<00:03, 450MB/s] model-00003-of-00008.safetensors: 55%|█████▍ | 1.07G/1.95G [00:03<00:00, 1.74GB/s] model-00003-of-00008.safetensors: 68%|██████▊ | 1.32G/1.95G [00:03<00:00, 825MB/s] model-00003-of-00008.safetensors: 77%|███████▋ | 1.50G/1.95G [00:03<00:00, 802MB/s] model-00003-of-00008.safetensors: 84%|████████▍ | 1.64G/1.95G [00:04<00:00, 726MB/s] model-00003-of-00008.safetensors: 91%|█████████ | 1.77G/1.95G [00:04<00:00, 756MB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 439MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00004-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00004-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<02:12, 14.8MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<02:08, 15.2MB/s] model-00004-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:51, 17.5MB/s] model-00004-of-00008.safetensors: 3%|▎ | 52.4M/1.98G [00:02<01:13, 26.4MB/s] model-00004-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:02<00:46, 41.2MB/s] model-00004-of-00008.safetensors: 7%|▋ | 136M/1.98G [00:02<00:17, 106MB/s] model-00004-of-00008.safetensors: 9%|▉ | 178M/1.98G [00:02<00:12, 147MB/s] model-00004-of-00008.safetensors: 13%|█▎ | 252M/1.98G [00:02<00:07, 242MB/s] model-00004-of-00008.safetensors: 21%|██ | 409M/1.98G [00:02<00:03, 480MB/s] model-00004-of-00008.safetensors: 25%|██▍ | 493M/1.98G [00:03<00:03, 478MB/s] model-00004-of-00008.safetensors: 56%|█████▌ | 1.10G/1.98G [00:03<00:00, 1.36GB/s] model-00004-of-00008.safetensors: 63%|██████▎ | 1.25G/1.98G [00:03<00:00, 810MB/s] model-00004-of-00008.safetensors: 69%|██████▉ | 1.36G/1.98G [00:04<00:01, 600MB/s] model-00004-of-00008.safetensors: 74%|███████▎ | 1.46G/1.98G [00:04<00:00, 525MB/s] model-00004-of-00008.safetensors: 77%|███████▋ | 1.53G/1.98G [00:04<00:00, 540MB/s] model-00004-of-00008.safetensors: 83%|████████▎ | 1.64G/1.98G [00:04<00:00, 599MB/s] model-00004-of-00008.safetensors: 87%|████████▋ | 1.72G/1.98G [00:04<00:00, 592MB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 400MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.89G [00:01<04:05, 7.66MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.89G [00:02<02:53, 10.8MB/s] model-00005-of-00008.safetensors: 2%|▏ | 31.5M/1.89G [00:02<02:07, 14.6MB/s] model-00005-of-00008.safetensors: 3%|▎ | 52.4M/1.89G [00:02<01:03, 28.9MB/s] model-00005-of-00008.safetensors: 5%|▍ | 94.4M/1.89G [00:02<00:26, 67.8MB/s] model-00005-of-00008.safetensors: 10%|▉ | 189M/1.89G [00:02<00:09, 176MB/s] model-00005-of-00008.safetensors: 17%|█▋ | 315M/1.89G [00:03<00:05, 294MB/s] model-00005-of-00008.safetensors: 23%|██▎ | 440M/1.89G [00:03<00:03, 438MB/s] model-00005-of-00008.safetensors: 58%|█████▊ | 1.09G/1.89G [00:03<00:00, 1.45GB/s] model-00005-of-00008.safetensors: 68%|██████▊ | 1.29G/1.89G [00:04<00:00, 645MB/s] model-00005-of-00008.safetensors: 79%|███████▉ | 1.49G/1.89G [00:04<00:00, 780MB/s] model-00005-of-00008.safetensors: 88%|████████▊ | 1.66G/1.89G [00:04<00:00, 703MB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:04<00:00, 405MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00006-of-00008.safetensors: 0%| | 0.00/1.92G [00:00<?, ?B/s] model-00006-of-00008.safetensors: 1%| | 10.5M/1.92G [00:01<03:39, 8.71MB/s] model-00006-of-00008.safetensors: 1%| | 21.0M/1.92G [00:02<03:26, 9.20MB/s] model-00006-of-00008.safetensors: 3%|▎ | 62.9M/1.92G [00:02<00:51, 35.9MB/s] model-00006-of-00008.safetensors: 6%|▌ | 115M/1.92G [00:02<00:23, 77.2MB/s] model-00006-of-00008.safetensors: 15%|█▍ | 283M/1.92G [00:02<00:06, 250MB/s] model-00006-of-00008.safetensors: 19%|█▉ | 367M/1.92G [00:02<00:05, 295MB/s] model-00006-of-00008.safetensors: 31%|███ | 587M/1.92G [00:02<00:02, 572MB/s] model-00006-of-00008.safetensors: 56%|█████▌ | 1.08G/1.92G [00:03<00:00, 1.11GB/s] model-00006-of-00008.safetensors: 65%|██████▍ | 1.24G/1.92G [00:03<00:01, 588MB/s] model-00006-of-00008.safetensors: 71%|███████ | 1.36G/1.92G [00:04<00:01, 503MB/s] model-00006-of-00008.safetensors: 78%|███████▊ | 1.50G/1.92G [00:04<00:00, 604MB/s] model-00006-of-00008.safetensors: 84%|████████▎ | 1.61G/1.92G [00:04<00:00, 617MB/s] model-00006-of-00008.safetensors: 89%|████████▊ | 1.70G/1.92G [00:04<00:00, 647MB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:04<00:00, 411MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 0%| | 2.13M/872M [00:00<06:42, 2.16MB/s] model-00008-of-00008.safetensors: 1%|▏ | 12.6M/872M [00:01<01:30, 9.48MB/s] model-00008-of-00008.safetensors: 4%|▍ | 33.6M/872M [00:01<00:31, 26.9MB/s] model-00008-of-00008.safetensors: 5%|▌ | 44.1M/872M [00:01<00:25, 32.7MB/s] model-00008-of-00008.safetensors: 7%|▋ | 65.0M/872M [00:02<00:15, 51.9MB/s] model-00008-of-00008.safetensors: 16%|█▌ | 138M/872M [00:02<00:04, 147MB/s] model-00008-of-00008.safetensors: 27%|██▋ | 233M/872M [00:02<00:02, 265MB/s] model-00008-of-00008.safetensors: 42%|████▏ | 369M/872M [00:02<00:01, 467MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 343MB/s]
inv-gamma-alpha-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, 131MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 4.61MB/s]
inv-gamma-alpha-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, 23.2MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 42.5MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 11.6MB/s]
inv-gamma-alpha-7b-v1-mkmlizer: Downloaded to shared memory in 38.381s
inv-gamma-alpha-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
inv-gamma-alpha-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-gamma-alpha-7b-v1-mkmlizer: Reading /tmp/tmpy_xgfz0a/model.safetensors.index.json
inv-gamma-alpha-7b-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<01:20, 3.59it/s] Profiling: 6%|▌ | 18/291 [00:00<00:04, 59.53it/s] Profiling: 13%|█▎ | 38/291 [00:00<00:02, 104.77it/s] Profiling: 18%|█▊ | 53/291 [00:00<00:02, 95.34it/s] Profiling: 25%|██▌ | 73/291 [00:00<00:01, 122.81it/s] Profiling: 30%|███ | 88/291 [00:00<00:01, 112.94it/s] Profiling: 37%|███▋ | 107/291 [00:01<00:01, 131.60it/s] Profiling: 42%|████▏ | 122/291 [00:01<00:01, 119.18it/s] Profiling: 48%|████▊ | 140/291 [00:01<00:01, 133.84it/s] Profiling: 55%|█████▍ | 160/291 [00:02<00:03, 34.55it/s] Profiling: 62%|██████▏ | 181/291 [00:02<00:02, 48.00it/s] Profiling: 68%|██████▊ | 197/291 [00:03<00:03, 28.22it/s] Profiling: 74%|███████▍ | 215/291 [00:04<00:02, 37.78it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 45.77it/s] Profiling: 86%|████████▌ | 250/291 [00:04<00:00, 60.27it/s] Profiling: 94%|█████████▍| 273/291 [00:04<00:00, 81.72it/s] Profiling: 100%|█████████▉| 290/291 [00:04<00:00, 86.31it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 62.65it/s]
inv-gamma-alpha-7b-v1-mkmlizer: quantized model in 14.528s
inv-gamma-alpha-7b-v1-mkmlizer: Processed model Inv/Gamma-Alpha-7B in 53.812s
inv-gamma-alpha-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
inv-gamma-alpha-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-gamma-alpha-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-gamma-alpha-7b-v1
inv-gamma-alpha-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-gamma-alpha-7b-v1/config.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-gamma-alpha-7b-v1/tokenizer_config.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-gamma-alpha-7b-v1/tokenizer.model
inv-gamma-alpha-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-gamma-alpha-7b-v1/special_tokens_map.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-gamma-alpha-7b-v1/tokenizer.json
inv-gamma-alpha-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-gamma-alpha-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.
inv-gamma-alpha-7b-v1-mkmlizer: warnings.warn(
inv-gamma-alpha-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, 10.4MB/s]
inv-gamma-alpha-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.
inv-gamma-alpha-7b-v1-mkmlizer: warnings.warn(
inv-gamma-alpha-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.00MB/s]
inv-gamma-alpha-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, 9.96MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 9.90MB/s]
inv-gamma-alpha-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, 15.2MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 15.2MB/s]
inv-gamma-alpha-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.
inv-gamma-alpha-7b-v1-mkmlizer: warnings.warn(
inv-gamma-alpha-7b-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:06, 223MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:03, 400MB/s] pytorch_model.bin: 12%|█▏ | 178M/1.44G [00:00<00:02, 567MB/s] pytorch_model.bin: 17%|█▋ | 241M/1.44G [00:00<00:02, 574MB/s] pytorch_model.bin: 22%|██▏ | 315M/1.44G [00:00<00:02, 560MB/s] pytorch_model.bin: 30%|███ | 440M/1.44G [00:00<00:01, 768MB/s] pytorch_model.bin: 36%|███▋ | 524M/1.44G [00:00<00:01, 679MB/s] pytorch_model.bin: 43%|████▎ | 619M/1.44G [00:00<00:01, 726MB/s] pytorch_model.bin: 64%|██████▍ | 923M/1.44G [00:01<00:00, 1.33GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.21GB/s]
inv-gamma-alpha-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-gamma-alpha-7b-v1-mkmlizer: Saving duration: 0.242s
inv-gamma-alpha-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.379s
inv-gamma-alpha-7b-v1-mkmlizer: creating bucket guanaco-reward-models
inv-gamma-alpha-7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-gamma-alpha-7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/config.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/tokenizer_config.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/special_tokens_map.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/merges.txt
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/vocab.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/tokenizer.json
inv-gamma-alpha-7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-gamma-alpha-7b-v1_reward/reward.tensors
Job inv-gamma-alpha-7b-v1-mkmlizer completed after 87.69s with status: succeeded
Stopping job with name inv-gamma-alpha-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 92.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service inv-gamma-alpha-7b-v1
Waiting for inference service inv-gamma-alpha-7b-v1 to be ready
Inference service inv-gamma-alpha-7b-v1 ready after 40.26696562767029s
Pipeline stage ISVCDeployer completed in 47.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8429899215698242s
Received healthy response to inference request in 1.1901674270629883s
Received healthy response to inference request in 1.1726279258728027s
Received healthy response to inference request in 1.2156381607055664s
Received healthy response to inference request in 1.2064099311828613s
5 requests
0 failed requests
5th percentile: 1.1761358261108399
10th percentile: 1.179643726348877
20th percentile: 1.1866595268249511
30th percentile: 1.193415927886963
40th percentile: 1.199912929534912
50th percentile: 1.2064099311828613
60th percentile: 1.2101012229919434
70th percentile: 1.2137925148010253
80th percentile: 1.3411085128784181
90th percentile: 1.5920492172241212
95th percentile: 1.7175195693969725
99th percentile: 1.8178958511352539
mean time: 1.3255666732788085
Pipeline stage StressChecker completed in 9.20s
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
inv-gamma-alpha-7b_v1 status is now deployed due to DeploymentManager action
inv-gamma-alpha-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of inv-gamma-alpha-7b_v1
Running pipeline stage ISVCDeleter
Checking if service inv-gamma-alpha-7b-v1 is running
Tearing down inference service inv-gamma-alpha-7b-v1
Toredown service inv-gamma-alpha-7b-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 inv-gamma-alpha-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key inv-gamma-alpha-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key inv-gamma-alpha-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key inv-gamma-alpha-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key inv-gamma-alpha-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key inv-gamma-alpha-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key inv-gamma-alpha-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key inv-gamma-alpha-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key inv-gamma-alpha-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key inv-gamma-alpha-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key inv-gamma-alpha-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key inv-gamma-alpha-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key inv-gamma-alpha-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.96s
inv-gamma-alpha-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics