submission_id: inv-konstanta-v4-alpha-7b_v4
developer_uid: Inv
best_of: 16
celo_rating: 1177.73
display_name: inv-konstanta-v4-alpha-7b_v4
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\nThis 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}. Put actions in asterisks.<|im_end|>\n', 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
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', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Inv/Konstanta-V4-Alpha-7B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_eval_status: success
model_group: Inv/Konstanta-V4-Alpha-7
model_name: inv-konstanta-v4-alpha-7b_v4
model_num_parameters: 7241732096.0
model_repo: Inv/Konstanta-V4-Alpha-7B
model_size: 7B
num_battles: 112534
num_wins: 59480
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-03-25T17:47:42+00:00
us_pacific_date: 2024-03-25
win_ratio: 0.5285513711411662
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-konstanta-v4-alpha-7b-v4-mkmlizer
Waiting for job on inv-konstanta-v4-alpha-7b-v4-mkmlizer to finish
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ _____ __ __ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ /___/ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ Version: 0.6.11 ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ The license key for the current software has been verified as ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ belonging to: ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ Chai Research Corp. ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-konstanta-v4-alpha-7b-v4-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 [00:00<00:40, 49.1MB/s] model-00001-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:00<00:22, 87.3MB/s] model-00001-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:00<00:13, 143MB/s] model-00001-of-00008.safetensors: 7%|▋ | 147M/1.98G [00:00<00:05, 338MB/s] model-00001-of-00008.safetensors: 10%|█ | 199M/1.98G [00:00<00:04, 385MB/s] model-00001-of-00008.safetensors: 16%|█▋ | 325M/1.98G [00:00<00:02, 615MB/s] model-00001-of-00008.safetensors: 20%|██ | 398M/1.98G [00:00<00:02, 640MB/s] model-00001-of-00008.safetensors: 25%|██▌ | 503M/1.98G [00:01<00:01, 750MB/s] model-00001-of-00008.safetensors: 31%|███ | 608M/1.98G [00:01<00:01, 776MB/s] model-00001-of-00008.safetensors: 35%|███▍ | 692M/1.98G [00:01<00:01, 711MB/s] model-00001-of-00008.safetensors: 40%|███▉ | 786M/1.98G [00:01<00:01, 753MB/s] model-00001-of-00008.safetensors: 45%|████▌ | 891M/1.98G [00:01<00:01, 682MB/s] model-00001-of-00008.safetensors: 49%|████▊ | 965M/1.98G [00:01<00:01, 682MB/s] model-00001-of-00008.safetensors: 52%|█████▏ | 1.04G/1.98G [00:01<00:01, 686MB/s] model-00001-of-00008.safetensors: 60%|██████ | 1.19G/1.98G [00:01<00:00, 868MB/s] model-00001-of-00008.safetensors: 65%|██████▌ | 1.29G/1.98G [00:02<00:00, 874MB/s] model-00001-of-00008.safetensors: 70%|██████▉ | 1.38G/1.98G [00:02<00:00, 842MB/s] model-00001-of-00008.safetensors: 79%|███████▉ | 1.57G/1.98G [00:02<00:00, 1.11GB/s] model-00001-of-00008.safetensors: 97%|█████████▋| 1.93G/1.98G [00:02<00:00, 1.78GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 367MB/s]
inv-konstanta-v4-alpha-7b-v4-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 [00:00<00:49, 39.1MB/s] model-00002-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:36, 53.0MB/s] model-00002-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:08, 216MB/s] model-00002-of-00008.safetensors: 10%|█ | 199M/1.95G [00:00<00:04, 433MB/s] model-00002-of-00008.safetensors: 16%|█▌ | 315M/1.95G [00:00<00:03, 523MB/s] model-00002-of-00008.safetensors: 19%|█▉ | 377M/1.95G [00:00<00:03, 500MB/s] model-00002-of-00008.safetensors: 23%|██▎ | 451M/1.95G [00:01<00:02, 518MB/s] model-00002-of-00008.safetensors: 26%|██▋ | 514M/1.95G [00:01<00:02, 534MB/s] model-00002-of-00008.safetensors: 30%|███ | 587M/1.95G [00:01<00:02, 489MB/s] model-00002-of-00008.safetensors: 37%|███▋ | 713M/1.95G [00:01<00:01, 645MB/s] model-00002-of-00008.safetensors: 44%|████▍ | 860M/1.95G [00:01<00:01, 821MB/s] model-00002-of-00008.safetensors: 54%|█████▍ | 1.06G/1.95G [00:01<00:00, 1.12GB/s] model-00002-of-00008.safetensors: 66%|██████▋ | 1.29G/1.95G [00:01<00:00, 1.42GB/s] model-00002-of-00008.safetensors: 81%|████████▏ | 1.58G/1.95G [00:01<00:00, 1.81GB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:02<00:00, 955MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<00:54, 36.0MB/s] model-00003-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:00<00:15, 124MB/s] model-00003-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:00<00:14, 131MB/s] model-00003-of-00008.safetensors: 7%|▋ | 136M/1.98G [00:00<00:06, 277MB/s] model-00003-of-00008.safetensors: 10%|▉ | 189M/1.98G [00:00<00:05, 328MB/s] model-00003-of-00008.safetensors: 14%|█▍ | 283M/1.98G [00:00<00:03, 482MB/s] model-00003-of-00008.safetensors: 21%|██ | 419M/1.98G [00:01<00:02, 718MB/s] model-00003-of-00008.safetensors: 26%|██▋ | 524M/1.98G [00:01<00:01, 809MB/s] model-00003-of-00008.safetensors: 31%|███ | 619M/1.98G [00:01<00:01, 847MB/s] model-00003-of-00008.safetensors: 38%|███▊ | 755M/1.98G [00:01<00:01, 982MB/s] model-00003-of-00008.safetensors: 47%|████▋ | 933M/1.98G [00:01<00:00, 1.17GB/s] model-00003-of-00008.safetensors: 58%|█████▊ | 1.15G/1.98G [00:01<00:00, 1.44GB/s] model-00003-of-00008.safetensors: 75%|███████▍ | 1.48G/1.98G [00:01<00:00, 1.94GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.11GB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: model-00004-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00004-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<00:52, 36.7MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:37, 51.4MB/s] model-00004-of-00008.safetensors: 6%|▋ | 126M/1.95G [00:00<00:05, 328MB/s] model-00004-of-00008.safetensors: 13%|█▎ | 252M/1.95G [00:00<00:02, 587MB/s] model-00004-of-00008.safetensors: 17%|█▋ | 336M/1.95G [00:00<00:02, 587MB/s] model-00004-of-00008.safetensors: 21%|██ | 409M/1.95G [00:00<00:02, 577MB/s] model-00004-of-00008.safetensors: 25%|██▍ | 482M/1.95G [00:01<00:03, 482MB/s] model-00004-of-00008.safetensors: 30%|███ | 587M/1.95G [00:01<00:02, 600MB/s] model-00004-of-00008.safetensors: 38%|███▊ | 734M/1.95G [00:01<00:01, 807MB/s] model-00004-of-00008.safetensors: 45%|████▍ | 870M/1.95G [00:01<00:01, 942MB/s] model-00004-of-00008.safetensors: 58%|█████▊ | 1.12G/1.95G [00:01<00:00, 1.34GB/s] model-00004-of-00008.safetensors: 72%|███████▏ | 1.41G/1.95G [00:01<00:00, 1.74GB/s] model-00004-of-00008.safetensors: 96%|█████████▌| 1.86G/1.95G [00:01<00:00, 2.52GB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.08GB/s]
inv-konstanta-v4-alpha-7b-v4-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 [00:00<00:49, 38.1MB/s] model-00005-of-00008.safetensors: 2%|▏ | 31.5M/1.89G [00:00<00:22, 81.3MB/s] model-00005-of-00008.safetensors: 3%|▎ | 52.4M/1.89G [00:00<00:16, 114MB/s] model-00005-of-00008.safetensors: 12%|█▏ | 220M/1.89G [00:00<00:02, 559MB/s] model-00005-of-00008.safetensors: 21%|██ | 398M/1.89G [00:00<00:01, 885MB/s] model-00005-of-00008.safetensors: 32%|███▏ | 598M/1.89G [00:00<00:01, 1.17GB/s] model-00005-of-00008.safetensors: 39%|███▉ | 734M/1.89G [00:00<00:00, 1.18GB/s] model-00005-of-00008.safetensors: 46%|████▌ | 870M/1.89G [00:01<00:00, 1.11GB/s] model-00005-of-00008.safetensors: 55%|█████▍ | 1.04G/1.89G [00:01<00:00, 1.24GB/s] model-00005-of-00008.safetensors: 64%|██████▍ | 1.22G/1.89G [00:01<00:00, 1.35GB/s] model-00005-of-00008.safetensors: 74%|███████▍ | 1.40G/1.89G [00:01<00:00, 1.47GB/s] model-00005-of-00008.safetensors: 88%|████████▊ | 1.67G/1.89G [00:01<00:00, 1.81GB/s] model-00005-of-00008.safetensors: 99%|█████████▉| 1.88G/1.89G [00:01<00:00, 1.79GB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:01<00:00, 988MB/s]
inv-konstanta-v4-alpha-7b-v4-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 [00:00<00:50, 37.7MB/s] model-00006-of-00008.safetensors: 2%|▏ | 31.5M/1.92G [00:00<00:23, 81.4MB/s] model-00006-of-00008.safetensors: 8%|▊ | 157M/1.92G [00:00<00:04, 397MB/s] model-00006-of-00008.safetensors: 13%|█▎ | 252M/1.92G [00:00<00:03, 522MB/s] model-00006-of-00008.safetensors: 17%|█▋ | 325M/1.92G [00:00<00:02, 579MB/s] model-00006-of-00008.safetensors: 21%|██ | 398M/1.92G [00:00<00:02, 597MB/s] model-00006-of-00008.safetensors: 28%|██▊ | 535M/1.92G [00:00<00:01, 800MB/s] model-00006-of-00008.safetensors: 33%|███▎ | 629M/1.92G [00:01<00:01, 737MB/s] model-00006-of-00008.safetensors: 42%|████▏ | 807M/1.92G [00:01<00:01, 943MB/s] model-00006-of-00008.safetensors: 50%|████▉ | 954M/1.92G [00:01<00:00, 1.05GB/s] model-00006-of-00008.safetensors: 56%|█████▌ | 1.07G/1.92G [00:01<00:00, 989MB/s] model-00006-of-00008.safetensors: 64%|██████▍ | 1.23G/1.92G [00:01<00:00, 1.08GB/s] model-00006-of-00008.safetensors: 83%|████████▎ | 1.59G/1.92G [00:01<00:00, 1.71GB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:01<00:00, 1.06GB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:10, 27.3MB/s] model-00007-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:09, 198MB/s] model-00007-of-00008.safetensors: 9%|▉ | 178M/1.95G [00:00<00:04, 390MB/s] model-00007-of-00008.safetensors: 14%|█▍ | 273M/1.95G [00:00<00:03, 535MB/s] model-00007-of-00008.safetensors: 22%|██▏ | 430M/1.95G [00:00<00:01, 821MB/s] model-00007-of-00008.safetensors: 27%|██▋ | 535M/1.95G [00:00<00:01, 758MB/s] model-00007-of-00008.safetensors: 34%|███▍ | 661M/1.95G [00:01<00:01, 862MB/s] model-00007-of-00008.safetensors: 39%|███▉ | 765M/1.95G [00:01<00:01, 749MB/s] model-00007-of-00008.safetensors: 44%|████▍ | 860M/1.95G [00:01<00:01, 713MB/s] model-00007-of-00008.safetensors: 55%|█████▍ | 1.07G/1.95G [00:01<00:00, 1.03GB/s] model-00007-of-00008.safetensors: 65%|██████▌ | 1.27G/1.95G [00:01<00:00, 1.24GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.10GB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/872M [00:00<00:43, 20.0MB/s] model-00008-of-00008.safetensors: 10%|▉ | 86.0M/872M [00:00<00:06, 126MB/s] model-00008-of-00008.safetensors: 12%|█▏ | 107M/872M [00:01<00:15, 49.7MB/s] model-00008-of-00008.safetensors: 13%|█▎ | 117M/872M [00:02<00:18, 41.9MB/s] model-00008-of-00008.safetensors: 23%|██▎ | 201M/872M [00:02<00:06, 108MB/s] model-00008-of-00008.safetensors: 47%|████▋ | 411M/872M [00:02<00:01, 317MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 325MB/s]
inv-konstanta-v4-alpha-7b-v4-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, 138MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.50MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 60.3MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 63.6MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 11.9MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Downloaded to shared memory in 23.230s
inv-konstanta-v4-alpha-7b-v4-mkmlizer: quantizing model to /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Reading /tmp/tmpv119w30b/model.safetensors.index.json
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:39, 7.26it/s] Profiling: 3%|▎ | 10/291 [00:00<00:05, 49.32it/s] Profiling: 7%|▋ | 20/291 [00:00<00:03, 70.52it/s] Profiling: 10%|█ | 30/291 [00:00<00:03, 78.66it/s] Profiling: 13%|█▎ | 39/291 [00:00<00:03, 64.92it/s] Profiling: 17%|█▋ | 49/291 [00:00<00:03, 69.95it/s] Profiling: 22%|██▏ | 65/291 [00:00<00:02, 90.51it/s] Profiling: 27%|██▋ | 78/291 [00:00<00:02, 99.32it/s] Profiling: 31%|███ | 89/291 [00:01<00:02, 79.38it/s] Profiling: 34%|███▎ | 98/291 [00:01<00:02, 76.85it/s] Profiling: 38%|███▊ | 112/291 [00:01<00:02, 88.86it/s] Profiling: 42%|████▏ | 122/291 [00:01<00:02, 71.88it/s] Profiling: 46%|████▌ | 134/291 [00:01<00:01, 82.12it/s] Profiling: 50%|████▉ | 145/291 [00:01<00:01, 88.54it/s] Profiling: 54%|█████▎ | 156/291 [00:01<00:01, 93.66it/s] Profiling: 57%|█████▋ | 167/291 [00:03<00:06, 20.11it/s] Profiling: 62%|██████▏ | 180/291 [00:03<00:03, 27.76it/s] Profiling: 67%|██████▋ | 195/291 [00:03<00:02, 38.61it/s] Profiling: 70%|███████ | 205/291 [00:05<00:04, 18.21it/s] Profiling: 74%|███████▍ | 215/291 [00:05<00:03, 23.18it/s] Profiling: 78%|███████▊ | 226/291 [00:05<00:02, 30.16it/s] Profiling: 81%|████████ | 235/291 [00:05<00:01, 33.31it/s] Profiling: 85%|████████▍ | 247/291 [00:05<00:01, 43.47it/s] Profiling: 89%|████████▉ | 259/291 [00:05<00:00, 53.31it/s] Profiling: 94%|█████████▍| 274/291 [00:05<00:00, 60.66it/s] Profiling: 98%|█████████▊| 284/291 [00:06<00:00, 66.31it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 47.21it/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: quantized model in 17.930s
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Processed model Inv/Konstanta-V4-Alpha-7B in 42.366s
inv-konstanta-v4-alpha-7b-v4-mkmlizer: creating bucket guanaco-mkml-models
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-konstanta-v4-alpha-7b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v4
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v4/mkml_model.tensors
inv-konstanta-v4-alpha-7b-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-konstanta-v4-alpha-7b-v4-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-konstanta-v4-alpha-7b-v4-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v4-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.50MB/s]
inv-konstanta-v4-alpha-7b-v4-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-konstanta-v4-alpha-7b-v4-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.50MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 18.4MB/s]
inv-konstanta-v4-alpha-7b-v4-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 18.9MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 18.8MB/s]
inv-konstanta-v4-alpha-7b-v4-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-konstanta-v4-alpha-7b-v4-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Saving duration: 0.273s
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.013s
inv-konstanta-v4-alpha-7b-v4-mkmlizer: creating bucket guanaco-reward-models
inv-konstanta-v4-alpha-7b-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-konstanta-v4-alpha-7b-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/config.json
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/merges.txt
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/vocab.json
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/tokenizer.json
inv-konstanta-v4-alpha-7b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v4_reward/reward.tensors
Job inv-konstanta-v4-alpha-7b-v4-mkmlizer completed after 189.76s with status: succeeded
Stopping job with name inv-konstanta-v4-alpha-7b-v4-mkmlizer
Pipeline stage MKMLizer completed in 195.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service inv-konstanta-v4-alpha-7b-v4
Waiting for inference service inv-konstanta-v4-alpha-7b-v4 to be ready
Inference service inv-konstanta-v4-alpha-7b-v4 ready after 30.21855330467224s
Pipeline stage ISVCDeployer completed in 38.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8367516994476318s
Received healthy response to inference request in 1.1952431201934814s
Received healthy response to inference request in 1.1948902606964111s
Received healthy response to inference request in 1.1891229152679443s
Received healthy response to inference request in 1.192098617553711s
5 requests
0 failed requests
5th percentile: 1.1897180557250977
10th percentile: 1.190313196182251
20th percentile: 1.1915034770965576
30th percentile: 1.192656946182251
40th percentile: 1.1937736034393311
50th percentile: 1.1948902606964111
60th percentile: 1.1950314044952393
70th percentile: 1.1951725482940674
80th percentile: 1.3235448360443116
90th percentile: 1.5801482677459717
95th percentile: 1.7084499835968017
99th percentile: 1.8110913562774658
mean time: 1.3216213226318358
Pipeline stage StressChecker completed in 7.49s
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
inv-konstanta-v4-alpha-7b_v4 status is now deployed due to DeploymentManager action
inv-konstanta-v4-alpha-7b_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of inv-konstanta-v4-alpha-7b_v4
Running pipeline stage ISVCDeleter
Checking if service inv-konstanta-v4-alpha-7b-v4 is running
Tearing down inference service inv-konstanta-v4-alpha-7b-v4
Toredown service inv-konstanta-v4-alpha-7b-v4
Pipeline stage ISVCDeleter completed in 2.89s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key inv-konstanta-v4-alpha-7b-v4/config.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v4/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/config.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.21s
inv-konstanta-v4-alpha-7b_v4 status is now torndown due to DeploymentManager action