submission_id: sao10k-typhon-mixtral-v1_v2
developer_uid: sao10k
status: inactive
model_repo: Sao10K/Typhon-Mixtral-v1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.22, 'top_p': 0.86, 'top_k': 40, 'presence_penalty': 1.0, 'frequency_penalty': 1.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, '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: 2024-03-27T16:13:36+00:00
model_name: sao10k-typhon-mixtral-v1_v2
model_eval_status: success
safety_score: 0.98
entertaining: 7.04
stay_in_character: 8.69
user_preference: 7.5
double_thumbs_up: 751
thumbs_up: 1098
thumbs_down: 495
num_battles: 111949
num_wins: 59038
win_ratio: 0.5273651394831576
celo_rating: 1176.99
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-typhon-mixtral-v1-v2-mkmlizer
Waiting for job on sao10k-typhon-mixtral-v1-v2-mkmlizer to finish
sao10k-typhon-mixtral-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ _____ __ __ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ /___/ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ Version: 0.8.6 ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ belonging to: ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ Chai Research Corp. ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-typhon-mixtral-v1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
sao10k-typhon-mixtral-v1-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-typhon-mixtral-v1-v2-mkmlizer: Downloaded to shared memory in 80.055s
sao10k-typhon-mixtral-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-typhon-mixtral-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-typhon-mixtral-v1-v2-mkmlizer: quantized model in 62.237s
sao10k-typhon-mixtral-v1-v2-mkmlizer: Processed model Sao10K/Typhon-Mixtral-v1 in 148.130s
sao10k-typhon-mixtral-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-typhon-mixtral-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-typhon-mixtral-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/config.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/tokenizer.model
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/special_tokens_map.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/tokenizer.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/tokenizer_config.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/flywheel_model.3.safetensors
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/flywheel_model.2.safetensors
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/flywheel_model.1.safetensors
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v2/flywheel_model.0.safetensors
sao10k-typhon-mixtral-v1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-typhon-mixtral-v1-v2-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 7/995 [00:00<00:15, 62.80it/s] Loading 0: 1%|▏ | 14/995 [00:00<00:16, 58.07it/s] Loading 0: 2%|▏ | 20/995 [00:00<00:17, 56.39it/s] Loading 0: 3%|▎ | 31/995 [00:00<00:12, 74.55it/s] Loading 0: 4%|▍ | 39/995 [00:00<00:13, 69.36it/s] Loading 0: 5%|▍ | 47/995 [00:00<00:14, 63.72it/s] Loading 0: 5%|▌ | 54/995 [00:00<00:15, 60.92it/s] Loading 0: 7%|▋ | 66/995 [00:00<00:12, 75.65it/s] Loading 0: 7%|▋ | 74/995 [00:01<00:13, 68.47it/s] Loading 0: 8%|▊ | 82/995 [00:01<00:14, 63.89it/s] Loading 0: 9%|▉ | 93/995 [00:01<00:12, 74.45it/s] Loading 0: 10%|█ | 101/995 [00:01<00:12, 70.78it/s] Loading 0: 11%|█▏ | 113/995 [00:02<00:26, 33.16it/s] Loading 0: 12%|█▏ | 119/995 [00:02<00:24, 36.19it/s] Loading 0: 13%|█▎ | 125/995 [00:02<00:22, 39.38it/s] Loading 0: 13%|█▎ | 133/995 [00:02<00:18, 46.01it/s] Loading 0: 14%|█▍ | 140/995 [00:02<00:17, 48.22it/s] Loading 0: 15%|█▍ | 146/995 [00:02<00:17, 49.86it/s] Loading 0: 15%|█▌ | 152/995 [00:02<00:16, 51.11it/s] Loading 0: 16%|█▋ | 163/995 [00:02<00:12, 64.87it/s] Loading 0: 17%|█▋ | 171/995 [00:03<00:13, 61.68it/s] Loading 0: 18%|█▊ | 178/995 [00:03<00:13, 60.09it/s] Loading 0: 19%|█▊ | 185/995 [00:03<00:13, 58.97it/s] Loading 0: 19%|█▉ | 193/995 [00:03<00:12, 62.54it/s] Loading 0: 20%|██ | 200/995 [00:03<00:13, 60.65it/s] Loading 0: 21%|██ | 210/995 [00:03<00:11, 70.50it/s] Loading 0: 22%|██▏ | 218/995 [00:04<00:27, 28.53it/s] Loading 0: 23%|██▎ | 226/995 [00:04<00:22, 34.94it/s] Loading 0: 24%|██▎ | 234/995 [00:04<00:18, 41.64it/s] Loading 0: 24%|██▍ | 241/995 [00:04<00:16, 44.92it/s] Loading 0: 25%|██▍ | 248/995 [00:04<00:15, 47.70it/s] Loading 0: 26%|██▌ | 255/995 [00:04<00:14, 51.83it/s] Loading 0: 27%|██▋ | 267/995 [00:05<00:11, 65.33it/s] Loading 0: 28%|██▊ | 275/995 [00:05<00:11, 62.72it/s] Loading 0: 28%|██▊ | 282/995 [00:16<04:58, 2.39it/s] Loading 0: 29%|██▉ | 293/995 [00:16<03:08, 3.73it/s] Loading 0: 30%|███ | 302/995 [00:16<02:13, 5.19it/s] Loading 0: 31%|███ | 310/995 [00:16<01:38, 6.93it/s] Loading 0: 32%|███▏ | 322/995 [00:17<01:19, 8.47it/s] Loading 0: 33%|███▎ | 328/995 [00:17<01:04, 10.31it/s] Loading 0: 34%|███▎ | 334/995 [00:17<00:51, 12.73it/s] Loading 0: 34%|███▍ | 340/995 [00:17<00:41, 15.78it/s] Loading 0: 35%|███▍ | 348/995 [00:17<00:30, 21.16it/s] Loading 0: 36%|███▌ | 355/995 [00:17<00:24, 25.90it/s] Loading 0: 36%|███▋ | 362/995 [00:18<00:20, 30.94it/s] Loading 0: 38%|███▊ | 374/995 [00:18<00:14, 43.65it/s] Loading 0: 38%|███▊ | 382/995 [00:18<00:13, 46.60it/s] Loading 0: 39%|███▉ | 389/995 [00:18<00:12, 48.49it/s] Loading 0: 40%|███▉ | 396/995 [00:18<00:12, 48.48it/s] Loading 0: 41%|████ | 408/995 [00:18<00:09, 63.19it/s] Loading 0: 42%|████▏ | 416/995 [00:18<00:09, 61.23it/s] Loading 0: 43%|████▎ | 426/995 [00:19<00:18, 30.76it/s] Loading 0: 43%|████▎ | 432/995 [00:19<00:16, 34.31it/s] Loading 0: 44%|████▍ | 440/995 [00:19<00:13, 41.16it/s] Loading 0: 45%|████▍ | 447/995 [00:19<00:12, 43.65it/s] Loading 0: 46%|████▌ | 453/995 [00:19<00:11, 46.18it/s] Loading 0: 46%|████▌ | 459/995 [00:20<00:11, 47.98it/s] Loading 0: 47%|████▋ | 471/995 [00:20<00:08, 64.43it/s] Loading 0: 48%|████▊ | 479/995 [00:20<00:08, 61.55it/s] Loading 0: 49%|████▉ | 486/995 [00:20<00:08, 59.09it/s] Loading 0: 50%|████▉ | 495/995 [00:20<00:07, 66.49it/s] Loading 0: 51%|█████ | 503/995 [00:20<00:07, 67.55it/s] Loading 0: 51%|█████▏ | 511/995 [00:20<00:07, 63.58it/s] Loading 0: 52%|█████▏ | 518/995 [00:20<00:07, 60.76it/s] Loading 0: 53%|█████▎ | 528/995 [00:21<00:06, 69.65it/s] Loading 0: 54%|█████▍ | 536/995 [00:21<00:14, 31.70it/s] Loading 0: 54%|█████▍ | 542/995 [00:21<00:12, 35.10it/s] Loading 0: 55%|█████▌ | 548/995 [00:21<00:11, 38.45it/s] Loading 0: 56%|█████▌ | 554/995 [00:21<00:10, 41.60it/s] Loading 0: 56%|█████▌ | 555/995 [00:33<00:10, 41.60it/s] Loading 0: 56%|█████▌ | 556/995 [00:33<04:51, 1.50it/s] Loading 0: 57%|█████▋ | 568/995 [00:33<02:26, 2.91it/s] Loading 0: 58%|█████▊ | 576/995 [00:33<01:40, 4.16it/s] Loading 0: 59%|█████▊ | 583/995 [00:33<01:13, 5.63it/s] Loading 0: 60%|█████▉ | 594/995 [00:33<00:45, 8.91it/s] Loading 0: 61%|██████ | 602/995 [00:34<00:33, 11.70it/s] Loading 0: 61%|██████ | 609/995 [00:34<00:26, 14.76it/s] Loading 0: 62%|██████▏ | 618/995 [00:34<00:18, 20.32it/s] Loading 0: 63%|██████▎ | 626/995 [00:34<00:14, 25.78it/s] Loading 0: 64%|██████▍ | 637/995 [00:34<00:10, 35.32it/s] Loading 0: 65%|██████▍ | 645/995 [00:35<00:18, 18.56it/s] Loading 0: 65%|██████▌ | 651/995 [00:35<00:15, 21.84it/s] Loading 0: 66%|██████▌ | 657/995 [00:35<00:13, 25.60it/s] Loading 0: 67%|██████▋ | 665/995 [00:35<00:10, 32.24it/s] Loading 0: 68%|██████▊ | 672/995 [00:35<00:08, 36.46it/s] Loading 0: 68%|██████▊ | 678/995 [00:36<00:08, 39.56it/s] Loading 0: 69%|██████▊ | 684/995 [00:36<00:07, 42.27it/s] Loading 0: 70%|██████▉ | 695/995 [00:36<00:05, 55.76it/s] Loading 0: 71%|███████ | 702/995 [00:36<00:05, 55.83it/s] Loading 0: 71%|███████▏ | 709/995 [00:36<00:05, 55.11it/s] Loading 0: 72%|███████▏ | 717/995 [00:36<00:04, 59.02it/s] Loading 0: 73%|███████▎ | 724/995 [00:36<00:04, 57.17it/s] Loading 0: 73%|███████▎ | 731/995 [00:36<00:04, 55.92it/s] Loading 0: 74%|███████▍ | 741/995 [00:37<00:03, 65.49it/s] Loading 0: 75%|███████▌ | 748/995 [00:37<00:09, 27.42it/s] Loading 0: 76%|███████▌ | 755/995 [00:37<00:07, 32.59it/s] Loading 0: 76%|███████▋ | 761/995 [00:37<00:06, 36.32it/s] Loading 0: 77%|███████▋ | 767/995 [00:38<00:05, 39.97it/s] Loading 0: 78%|███████▊ | 773/995 [00:38<00:05, 43.22it/s] Loading 0: 79%|███████▉ | 785/995 [00:38<00:03, 59.62it/s] Loading 0: 80%|███████▉ | 793/995 [00:38<00:03, 57.95it/s] Loading 0: 80%|████████ | 800/995 [00:38<00:03, 56.79it/s] Loading 0: 81%|████████ | 808/995 [00:38<00:03, 61.64it/s] Loading 0: 82%|████████▏ | 815/995 [00:38<00:03, 58.83it/s] Loading 0: 83%|████████▎ | 822/995 [00:38<00:03, 54.19it/s] Loading 0: 83%|████████▎ | 828/995 [00:39<00:03, 53.87it/s] Loading 0: 84%|████████▍ | 840/995 [00:39<00:02, 68.51it/s] Loading 0: 85%|████████▌ | 848/995 [00:50<00:59, 2.46it/s] Loading 0: 86%|████████▌ | 853/995 [00:52<00:57, 2.45it/s] Loading 0: 86%|████████▋ | 859/995 [00:52<00:41, 3.26it/s] Loading 0: 87%|████████▋ | 865/995 [00:52<00:29, 4.37it/s] Loading 0: 88%|████████▊ | 871/995 [00:52<00:21, 5.87it/s] Loading 0: 88%|████████▊ | 879/995 [00:52<00:13, 8.59it/s] Loading 0: 89%|████████▉ | 885/995 [00:52<00:09, 11.13it/s] Loading 0: 90%|████████▉ | 891/995 [00:52<00:07, 14.35it/s] Loading 0: 91%|█████████ | 902/995 [00:53<00:04, 22.60it/s] Loading 0: 91%|█████████▏| 910/995 [00:53<00:03, 27.56it/s] Loading 0: 92%|█████████▏| 917/995 [00:53<00:02, 32.11it/s] Loading 0: 93%|█████████▎| 924/995 [00:53<00:01, 36.55it/s] Loading 0: 94%|█████████▍| 936/995 [00:53<00:01, 50.94it/s] Loading 0: 95%|█████████▍| 944/995 [00:53<00:00, 52.18it/s] Loading 0: 96%|█████████▌| 956/995 [00:54<00:01, 31.65it/s] Loading 0: 97%|█████████▋| 962/995 [00:54<00:00, 35.10it/s] Loading 0: 98%|█████████▊| 971/995 [00:54<00:00, 42.35it/s] Loading 0: 98%|█████████▊| 978/995 [00:54<00:00, 46.40it/s] Loading 0: 99%|█████████▉| 985/995 [00:54<00:00, 49.79it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1096: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-typhon-mixtral-v1-v2-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:720: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-typhon-mixtral-v1-v2-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:466: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-typhon-mixtral-v1-v2-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
sao10k-typhon-mixtral-v1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-typhon-mixtral-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-typhon-mixtral-v1-v2-mkmlizer: Saving duration: 0.254s
sao10k-typhon-mixtral-v1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.195s
sao10k-typhon-mixtral-v1-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-typhon-mixtral-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-typhon-mixtral-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/config.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/special_tokens_map.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/merges.txt
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/tokenizer_config.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/vocab.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/tokenizer.json
sao10k-typhon-mixtral-v1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v2_reward/reward.tensors
Job sao10k-typhon-mixtral-v1-v2-mkmlizer completed after 189.21s with status: succeeded
Stopping job with name sao10k-typhon-mixtral-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 195.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-typhon-mixtral-v1-v2
Waiting for inference service sao10k-typhon-mixtral-v1-v2 to be ready
Inference service sao10k-typhon-mixtral-v1-v2 ready after 50.33062124252319s
Pipeline stage ISVCDeployer completed in 58.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0786502361297607s
Received healthy response to inference request in 2.0455665588378906s
Received healthy response to inference request in 1.9428246021270752s
Received healthy response to inference request in 2.5356104373931885s
Received healthy response to inference request in 2.5025808811187744s
5 requests
0 failed requests
5th percentile: 1.9633729934692383
10th percentile: 1.9839213848114015
20th percentile: 2.0250181674957277
30th percentile: 2.1369694232940675
40th percentile: 2.3197751522064207
50th percentile: 2.5025808811187744
60th percentile: 2.51579270362854
70th percentile: 2.529004526138306
80th percentile: 2.644218397140503
90th percentile: 2.861434316635132
95th percentile: 2.970042276382446
99th percentile: 3.0569286441802976
mean time: 2.4210465431213377
Pipeline stage StressChecker completed in 13.00s
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
sao10k-typhon-mixtral-v1_v2 status is now deployed due to DeploymentManager action
sao10k-typhon-mixtral-v1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics