submission_id: undi95-lewdmistral-7b-0-2_v1
developer_uid: Undi95
status: inactive
model_repo: Undi95/LewdMistral-7B-0.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n###', '###', '</s>'], 'max_input_tokens': 512, 'best_of': 8, '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}:'}
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}:'}
timestamp: 2024-04-02T22:01:18+00:00
model_name: undi95-lewdmistral-7b-0-2_v1
model_eval_status: success
safety_score: 0.77
entertaining: 6.68
stay_in_character: 7.98
user_preference: 6.78
double_thumbs_up: 226
thumbs_up: 333
thumbs_down: 178
num_battles: 20968
num_wins: 10251
win_ratio: 0.4888878290728729
celo_rating: 1146.26
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-lewdmistral-7b-0-2-v1-mkmlizer
Waiting for job on undi95-lewdmistral-7b-0-2-v1-mkmlizer to finish
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ _____ __ __ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ /___/ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ Version: 0.6.11 ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ belonging to: ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ Chai Research Corp. ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ║ ║
undi95-lewdmistral-7b-0-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-lewdmistral-7b-0-2-v1-mkmlizer: README.md: 0%| | 0.00/1.01k [00:00<?, ?B/s] README.md: 100%|██████████| 1.01k/1.01k [00:00<00:00, 9.61MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: config.json: 0%| | 0.00/653 [00:00<?, ?B/s] config.json: 100%|██████████| 653/653 [00:00<00:00, 8.06MB/s]
undi95-lewdmistral-7b-0-2-v1-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]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/4.94G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 10.5M/4.94G [00:03<24:27, 3.36MB/s] pytorch_model-00001-of-00003.bin: 0%| | 21.0M/4.94G [00:03<12:06, 6.78MB/s] pytorch_model-00001-of-00003.bin: 1%| | 52.4M/4.94G [00:03<03:36, 22.6MB/s] pytorch_model-00001-of-00003.bin: 5%|▍ | 231M/4.94G [00:03<00:33, 141MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 304M/4.94G [00:04<00:28, 163MB/s] pytorch_model-00001-of-00003.bin: 23%|██▎ | 1.12G/4.94G [00:04<00:05, 731MB/s] pytorch_model-00001-of-00003.bin: 25%|██▌ | 1.24G/4.94G [00:04<00:05, 663MB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 1.37G/4.94G [00:04<00:04, 738MB/s] pytorch_model-00001-of-00003.bin: 30%|██▉ | 1.48G/4.94G [00:04<00:04, 766MB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 1.65G/4.94G [00:05<00:03, 893MB/s] pytorch_model-00001-of-00003.bin: 36%|███▋ | 1.80G/4.94G [00:05<00:03, 1.01GB/s] pytorch_model-00001-of-00003.bin: 40%|███▉ | 1.97G/4.94G [00:05<00:02, 1.14GB/s] pytorch_model-00001-of-00003.bin: 43%|████▎ | 2.12G/4.94G [00:05<00:02, 1.03GB/s] pytorch_model-00001-of-00003.bin: 45%|████▌ | 2.24G/4.94G [00:05<00:02, 1.04GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 2.37G/4.94G [00:05<00:02, 1.04GB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 2.62G/4.94G [00:05<00:01, 1.38GB/s] pytorch_model-00001-of-00003.bin: 56%|█████▌ | 2.78G/4.94G [00:06<00:01, 1.11GB/s] pytorch_model-00001-of-00003.bin: 59%|█████▉ | 2.92G/4.94G [00:06<00:01, 1.04GB/s] pytorch_model-00001-of-00003.bin: 62%|██████▏ | 3.04G/4.94G [00:06<00:02, 861MB/s] pytorch_model-00001-of-00003.bin: 66%|██████▌ | 3.27G/4.94G [00:06<00:01, 1.14GB/s] pytorch_model-00001-of-00003.bin: 71%|███████ | 3.49G/4.94G [00:06<00:01, 1.37GB/s] pytorch_model-00001-of-00003.bin: 79%|███████▉ | 3.92G/4.94G [00:06<00:00, 2.03GB/s] pytorch_model-00001-of-00003.bin: 87%|████████▋ | 4.29G/4.94G [00:06<00:00, 2.43GB/s] pytorch_model-00001-of-00003.bin: 92%|█████████▏| 4.56G/4.94G [00:06<00:00, 2.45GB/s] pytorch_model-00001-of-00003.bin: 98%|█████████▊| 4.84G/4.94G [00:07<00:00, 2.53GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 4.94G/4.94G [00:07<00:00, 697MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: pytorch_model-00002-of-00003.bin: 0%| | 0.00/5.00G [00:00<?, ?B/s] pytorch_model-00002-of-00003.bin: 0%| | 10.5M/5.00G [00:03<26:20, 3.16MB/s] pytorch_model-00002-of-00003.bin: 1%| | 31.5M/5.00G [00:03<07:54, 10.5MB/s] pytorch_model-00002-of-00003.bin: 5%|▍ | 231M/5.00G [00:03<00:43, 110MB/s] pytorch_model-00002-of-00003.bin: 22%|██▏ | 1.10G/5.00G [00:03<00:05, 669MB/s] pytorch_model-00002-of-00003.bin: 28%|██▊ | 1.42G/5.00G [00:04<00:06, 545MB/s] pytorch_model-00002-of-00003.bin: 33%|███▎ | 1.64G/5.00G [00:05<00:07, 438MB/s] pytorch_model-00002-of-00003.bin: 36%|███▌ | 1.79G/5.00G [00:06<00:08, 398MB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 1.91G/5.00G [00:06<00:07, 415MB/s] pytorch_model-00002-of-00003.bin: 40%|████ | 2.02G/5.00G [00:06<00:06, 472MB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 2.13G/5.00G [00:06<00:05, 523MB/s] pytorch_model-00002-of-00003.bin: 45%|████▍ | 2.23G/5.00G [00:06<00:04, 566MB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 2.33G/5.00G [00:06<00:04, 576MB/s] pytorch_model-00002-of-00003.bin: 59%|█████▉ | 2.97G/5.00G [00:06<00:01, 1.50GB/s] pytorch_model-00002-of-00003.bin: 65%|██████▍ | 3.24G/5.00G [00:07<00:01, 1.71GB/s] pytorch_model-00002-of-00003.bin: 70%|██████▉ | 3.49G/5.00G [00:07<00:01, 1.38GB/s] pytorch_model-00002-of-00003.bin: 74%|███████▍ | 3.69G/5.00G [00:07<00:00, 1.43GB/s] pytorch_model-00002-of-00003.bin: 78%|███████▊ | 3.88G/5.00G [00:07<00:00, 1.43GB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 4.10G/5.00G [00:07<00:00, 1.59GB/s] pytorch_model-00002-of-00003.bin: 86%|████████▋ | 4.32G/5.00G [00:07<00:00, 1.70GB/s] pytorch_model-00002-of-00003.bin: 90%|█████████ | 4.52G/5.00G [00:07<00:00, 1.71GB/s] pytorch_model-00002-of-00003.bin: 94%|█████████▍| 4.71G/5.00G [00:08<00:00, 1.00GB/s] pytorch_model-00002-of-00003.bin: 97%|█████████▋| 4.85G/5.00G [00:08<00:00, 1.07GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 5.00G/5.00G [00:08<00:00, 589MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: pytorch_model-00003-of-00003.bin: 0%| | 0.00/4.54G [00:00<?, ?B/s] pytorch_model-00003-of-00003.bin: 0%| | 10.5M/4.54G [00:03<23:38, 3.19MB/s] pytorch_model-00003-of-00003.bin: 1%|▏ | 62.9M/4.54G [00:03<03:18, 22.6MB/s] pytorch_model-00003-of-00003.bin: 9%|▉ | 419M/4.54G [00:03<00:20, 204MB/s] pytorch_model-00003-of-00003.bin: 24%|██▍ | 1.10G/4.54G [00:03<00:05, 655MB/s] pytorch_model-00003-of-00003.bin: 33%|███▎ | 1.48G/4.54G [00:04<00:06, 509MB/s] pytorch_model-00003-of-00003.bin: 38%|███▊ | 1.73G/4.54G [00:05<00:04, 590MB/s] pytorch_model-00003-of-00003.bin: 43%|████▎ | 1.94G/4.54G [00:05<00:04, 594MB/s] pytorch_model-00003-of-00003.bin: 46%|████▌ | 2.10G/4.54G [00:05<00:04, 609MB/s] pytorch_model-00003-of-00003.bin: 49%|████▉ | 2.23G/4.54G [00:05<00:03, 583MB/s] pytorch_model-00003-of-00003.bin: 51%|█████▏ | 2.34G/4.54G [00:06<00:03, 581MB/s] pytorch_model-00003-of-00003.bin: 54%|█████▎ | 2.43G/4.54G [00:06<00:03, 598MB/s] pytorch_model-00003-of-00003.bin: 58%|█████▊ | 2.65G/4.54G [00:06<00:02, 817MB/s] pytorch_model-00003-of-00003.bin: 61%|██████ | 2.78G/4.54G [00:06<00:02, 713MB/s] pytorch_model-00003-of-00003.bin: 73%|███████▎ | 3.29G/4.54G [00:06<00:00, 1.43GB/s] pytorch_model-00003-of-00003.bin: 80%|████████ | 3.65G/4.54G [00:06<00:00, 1.75GB/s] pytorch_model-00003-of-00003.bin: 86%|████████▌ | 3.90G/4.54G [00:06<00:00, 1.77GB/s] pytorch_model-00003-of-00003.bin: 91%|█████████ | 4.13G/4.54G [00:07<00:00, 1.81GB/s] pytorch_model-00003-of-00003.bin: 96%|█████████▌| 4.35G/4.54G [00:07<00:00, 1.73GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 4.54G/4.54G [00:07<00:00, 621MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/23.9k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 109MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 5.12MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 54.2MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 8.39MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Downloaded to shared memory in 31.647s
undi95-lewdmistral-7b-0-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Reading /tmp/tmp5ixx3cwv/pytorch_model.bin.index.json
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:02<09:56, 2.06s/it] Profiling: 34%|███▎ | 98/291 [00:02<00:04, 45.10it/s] Profiling: 70%|███████ | 204/291 [00:03<00:01, 80.57it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 76.99it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 62.82it/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: quantized model in 14.549s
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Processed model Undi95/LewdMistral-7B-0.2 in 47.029s
undi95-lewdmistral-7b-0-2-v1-mkmlizer: creating bucket guanaco-mkml-models
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-lewdmistral-7b-0-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-lewdmistral-7b-0-2-v1
undi95-lewdmistral-7b-0-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-lewdmistral-7b-0-2-v1/config.json
undi95-lewdmistral-7b-0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-lewdmistral-7b-0-2-v1/tokenizer.json
undi95-lewdmistral-7b-0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-lewdmistral-7b-0-2-v1/tokenizer_config.json
undi95-lewdmistral-7b-0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/undi95-lewdmistral-7b-0-2-v1/tokenizer.model
undi95-lewdmistral-7b-0-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-lewdmistral-7b-0-2-v1/special_tokens_map.json
undi95-lewdmistral-7b-0-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-lewdmistral-7b-0-2-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.
undi95-lewdmistral-7b-0-2-v1-mkmlizer: warnings.warn(
undi95-lewdmistral-7b-0-2-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.9MB/s]
undi95-lewdmistral-7b-0-2-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.
undi95-lewdmistral-7b-0-2-v1-mkmlizer: warnings.warn(
undi95-lewdmistral-7b-0-2-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.80MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 42.6MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 41.4MB/s]
undi95-lewdmistral-7b-0-2-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.
undi95-lewdmistral-7b-0-2-v1-mkmlizer: warnings.warn(
undi95-lewdmistral-7b-0-2-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:12, 111MB/s] pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:00<00:17, 79.5MB/s] pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:09, 137MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:01<00:13, 101MB/s] pytorch_model.bin: 10%|█ | 147M/1.44G [00:01<00:08, 157MB/s] pytorch_model.bin: 22%|██▏ | 315M/1.44G [00:01<00:02, 459MB/s] pytorch_model.bin: 41%|████ | 587M/1.44G [00:01<00:00, 944MB/s] pytorch_model.bin: 70%|██████▉ | 1.01G/1.44G [00:01<00:00, 1.71GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 283MB/s]
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Saving duration: 0.212s
undi95-lewdmistral-7b-0-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.193s
undi95-lewdmistral-7b-0-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-lewdmistral-7b-0-2-v1_reward/reward.tensors
Job undi95-lewdmistral-7b-0-2-v1-mkmlizer completed after 84.68s with status: succeeded
Stopping job with name undi95-lewdmistral-7b-0-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service undi95-lewdmistral-7b-0-2-v1
Waiting for inference service undi95-lewdmistral-7b-0-2-v1 to be ready
Inference service undi95-lewdmistral-7b-0-2-v1 ready after 50.302085876464844s
Pipeline stage ISVCDeployer completed in 58.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3815836906433105s
Received healthy response to inference request in 1.1138598918914795s
Received healthy response to inference request in 0.7644987106323242s
Received healthy response to inference request in 0.8513965606689453s
Received healthy response to inference request in 1.1225299835205078s
5 requests
0 failed requests
5th percentile: 0.7818782806396485
10th percentile: 0.7992578506469726
20th percentile: 0.834016990661621
30th percentile: 0.9038892269134522
40th percentile: 1.0088745594024657
50th percentile: 1.1138598918914795
60th percentile: 1.1173279285430908
70th percentile: 1.1207959651947021
80th percentile: 1.1743407249450684
90th percentile: 1.2779622077941895
95th percentile: 1.32977294921875
99th percentile: 1.3712215423583984
mean time: 1.0467737674713136
Pipeline stage StressChecker completed in 6.34s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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
undi95-lewdmistral-7b-0-2_v1 status is now deployed due to DeploymentManager action
undi95-lewdmistral-7b-0-2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics