submission_id: sao10k-typhon-mixtral-v1_v1
developer_uid: sao10k
status: inactive
model_repo: Sao10K/Typhon-Mixtral-v1
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'], 'max_input_tokens': 512, '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: 2024-03-27T16:11:18+00:00
model_name: sao10k-typhon-mixtral-v1_v1
model_eval_status: success
safety_score: 0.98
entertaining: 6.88
stay_in_character: 8.62
user_preference: 7.66
double_thumbs_up: 706
thumbs_up: 1049
thumbs_down: 421
num_battles: 106719
num_wins: 55648
win_ratio: 0.5214441664558326
celo_rating: 1172.4
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-typhon-mixtral-v1-v1-mkmlizer
Waiting for job on sao10k-typhon-mixtral-v1-v1-mkmlizer to finish
sao10k-typhon-mixtral-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ /___/ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ Version: 0.8.6 ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ belonging to: ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-typhon-mixtral-v1-v1-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-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-typhon-mixtral-v1-v1-mkmlizer: Downloaded to shared memory in 142.816s
sao10k-typhon-mixtral-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-typhon-mixtral-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-typhon-mixtral-v1-v1-mkmlizer: quantized model in 67.088s
sao10k-typhon-mixtral-v1-v1-mkmlizer: Processed model Sao10K/Typhon-Mixtral-v1 in 215.742s
sao10k-typhon-mixtral-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-typhon-mixtral-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-typhon-mixtral-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/config.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/tokenizer_config.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/tokenizer.model
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/special_tokens_map.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/tokenizer.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/flywheel_model.3.safetensors
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/flywheel_model.1.safetensors
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/flywheel_model.0.safetensors
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v1/flywheel_model.2.safetensors
sao10k-typhon-mixtral-v1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-typhon-mixtral-v1-v1-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 10/995 [00:00<00:10, 96.79it/s] Loading 0: 2%|▏ | 20/995 [00:00<00:10, 95.42it/s] Loading 0: 4%|▎ | 35/995 [00:00<00:08, 119.54it/s] Loading 0: 5%|▍ | 48/995 [00:00<00:09, 104.75it/s] Loading 0: 6%|▋ | 64/995 [00:00<00:07, 120.54it/s] Loading 0: 8%|▊ | 77/995 [00:00<00:08, 106.13it/s] Loading 0: 9%|▉ | 89/995 [00:00<00:08, 106.66it/s] Loading 0: 11%|█ | 111/995 [00:00<00:06, 137.38it/s] Loading 0: 13%|█▎ | 126/995 [00:01<00:14, 58.47it/s] Loading 0: 14%|█▍ | 137/995 [00:01<00:13, 65.68it/s] Loading 0: 15%|█▍ | 148/995 [00:01<00:11, 71.09it/s] Loading 0: 16%|█▋ | 163/995 [00:01<00:09, 85.57it/s] Loading 0: 18%|█▊ | 175/995 [00:01<00:09, 86.68it/s] Loading 0: 19%|█▊ | 186/995 [00:02<00:08, 90.59it/s] Loading 0: 20%|█▉ | 197/995 [00:02<00:08, 93.30it/s] Loading 0: 21%|██▏ | 212/995 [00:02<00:15, 51.43it/s] Loading 0: 23%|██▎ | 226/995 [00:02<00:11, 64.26it/s] Loading 0: 24%|██▍ | 238/995 [00:02<00:10, 72.65it/s] Loading 0: 25%|██▌ | 249/995 [00:03<00:09, 77.75it/s] Loading 0: 27%|██▋ | 265/995 [00:03<00:07, 92.85it/s] Loading 0: 28%|██▊ | 277/995 [00:03<00:07, 92.59it/s] Loading 0: 29%|██▉ | 288/995 [00:16<03:55, 3.00it/s] Loading 0: 30%|███ | 300/995 [00:16<02:45, 4.20it/s] Loading 0: 31%|███▏ | 311/995 [00:16<01:59, 5.71it/s] Loading 0: 32%|███▏ | 322/995 [00:17<01:33, 7.20it/s] Loading 0: 33%|███▎ | 332/995 [00:17<01:09, 9.59it/s] Loading 0: 34%|███▍ | 342/995 [00:17<00:51, 12.77it/s] Loading 0: 35%|███▌ | 353/995 [00:17<00:36, 17.45it/s] Loading 0: 36%|███▋ | 363/995 [00:17<00:28, 22.53it/s] Loading 0: 38%|███▊ | 378/995 [00:18<00:18, 33.08it/s] Loading 0: 39%|███▉ | 389/995 [00:18<00:14, 40.57it/s] Loading 0: 41%|████ | 405/995 [00:18<00:10, 55.66it/s] Loading 0: 42%|████▏ | 417/995 [00:18<00:09, 62.62it/s] Loading 0: 43%|████▎ | 428/995 [00:18<00:13, 41.99it/s] Loading 0: 44%|████▍ | 440/995 [00:18<00:10, 51.32it/s] Loading 0: 45%|████▌ | 450/995 [00:19<00:09, 57.64it/s] Loading 0: 46%|████▌ | 460/995 [00:19<00:08, 63.39it/s] Loading 0: 48%|████▊ | 476/995 [00:19<00:06, 81.47it/s] Loading 0: 49%|████▉ | 487/995 [00:19<00:06, 84.56it/s] Loading 0: 50%|█████ | 502/995 [00:19<00:05, 97.59it/s] Loading 0: 52%|█████▏ | 514/995 [00:19<00:05, 95.85it/s] Loading 0: 53%|█████▎ | 528/995 [00:19<00:04, 105.18it/s] Loading 0: 54%|█████▍ | 540/995 [00:20<00:08, 51.08it/s] Loading 0: 55%|█████▌ | 550/995 [00:20<00:07, 57.40it/s] Loading 0: 56%|█████▌ | 559/995 [00:34<02:52, 2.52it/s] Loading 0: 57%|█████▋ | 572/995 [00:34<01:52, 3.76it/s] Loading 0: 58%|█████▊ | 582/995 [00:34<01:21, 5.07it/s] Loading 0: 60%|██████ | 597/995 [00:34<00:50, 7.84it/s] Loading 0: 61%|██████ | 609/995 [00:34<00:35, 10.74it/s] Loading 0: 63%|██████▎ | 625/995 [00:35<00:22, 16.15it/s] Loading 0: 65%|██████▍ | 644/995 [00:35<00:17, 20.12it/s] Loading 0: 66%|██████▌ | 654/995 [00:35<00:14, 24.30it/s] Loading 0: 67%|██████▋ | 665/995 [00:35<00:10, 30.34it/s] Loading 0: 68%|██████▊ | 675/995 [00:35<00:08, 36.50it/s] Loading 0: 69%|██████▉ | 689/995 [00:36<00:06, 48.40it/s] Loading 0: 70%|███████ | 700/995 [00:36<00:05, 55.89it/s] Loading 0: 71%|███████▏ | 711/995 [00:36<00:04, 59.36it/s] Loading 0: 72%|███████▏ | 721/995 [00:36<00:04, 65.33it/s] Loading 0: 73%|███████▎ | 731/995 [00:36<00:04, 65.86it/s] Loading 0: 75%|███████▍ | 743/995 [00:37<00:06, 38.81it/s] Loading 0: 76%|███████▌ | 753/995 [00:37<00:05, 45.90it/s] Loading 0: 76%|███████▋ | 761/995 [00:37<00:04, 49.99it/s] Loading 0: 77%|███████▋ | 769/995 [00:37<00:04, 53.92it/s] Loading 0: 79%|███████▊ | 783/995 [00:37<00:03, 69.88it/s] Loading 0: 80%|███████▉ | 792/995 [00:37<00:02, 70.28it/s] Loading 0: 81%|████████ | 801/995 [00:37<00:02, 69.17it/s] Loading 0: 82%|████████▏ | 813/995 [00:37<00:02, 80.46it/s] Loading 0: 83%|████████▎ | 823/995 [00:38<00:02, 77.58it/s] Loading 0: 84%|████████▎ | 832/995 [00:38<00:02, 78.44it/s] Loading 0: 85%|████████▍ | 841/995 [00:52<00:01, 78.44it/s] Loading 0: 85%|████████▍ | 842/995 [00:52<01:06, 2.30it/s] Loading 0: 86%|████████▌ | 853/995 [00:55<00:53, 2.65it/s] Loading 0: 86%|████████▋ | 860/995 [00:55<00:39, 3.39it/s] Loading 0: 87%|████████▋ | 868/995 [00:55<00:27, 4.55it/s] Loading 0: 88%|████████▊ | 877/995 [00:55<00:18, 6.37it/s] Loading 0: 89%|████████▉ | 885/995 [00:55<00:12, 8.52it/s] Loading 0: 90%|████████▉ | 893/995 [00:55<00:08, 11.36it/s] Loading 0: 91%|█████████ | 906/995 [00:55<00:05, 17.72it/s] Loading 0: 92%|█████████▏| 915/995 [00:56<00:03, 22.12it/s] Loading 0: 93%|█████████▎| 923/995 [00:56<00:02, 26.67it/s] Loading 0: 94%|█████████▍| 936/995 [00:56<00:01, 37.94it/s] Loading 0: 95%|█████████▍| 945/995 [00:56<00:01, 43.08it/s] Loading 0: 96%|█████████▌| 956/995 [00:57<00:01, 28.51it/s] Loading 0: 97%|█████████▋| 963/995 [00:57<00:00, 32.70it/s] Loading 0: 98%|█████████▊| 972/995 [00:57<00:00, 39.54it/s] Loading 0: 98%|█████████▊| 980/995 [00:57<00:00, 44.91it/s] Loading 0: 99%|█████████▉| 987/995 [00:57<00:00, 48.46it/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-v1-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v1-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-v1-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v1-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-v1-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v1-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-v1-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-typhon-mixtral-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-typhon-mixtral-v1-v1-mkmlizer: Saving duration: 0.235s
sao10k-typhon-mixtral-v1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.730s
sao10k-typhon-mixtral-v1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-typhon-mixtral-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-typhon-mixtral-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/config.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/merges.txt
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/tokenizer_config.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/vocab.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/special_tokens_map.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/tokenizer.json
sao10k-typhon-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v1_reward/reward.tensors
Job sao10k-typhon-mixtral-v1-v1-mkmlizer completed after 250.13s with status: succeeded
Stopping job with name sao10k-typhon-mixtral-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 255.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-typhon-mixtral-v1-v1
Waiting for inference service sao10k-typhon-mixtral-v1-v1 to be ready
Inference service sao10k-typhon-mixtral-v1-v1 ready after 50.34260177612305s
Pipeline stage ISVCDeployer completed in 58.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3171327114105225s
Received healthy response to inference request in 1.7825627326965332s
Received healthy response to inference request in 1.560314655303955s
Received healthy response to inference request in 1.5975778102874756s
Received healthy response to inference request in 1.8486406803131104s
5 requests
0 failed requests
5th percentile: 1.567767286300659
10th percentile: 1.5752199172973633
20th percentile: 1.5901251792907716
30th percentile: 1.634574794769287
40th percentile: 1.7085687637329101
50th percentile: 1.7825627326965332
60th percentile: 1.8089939117431642
70th percentile: 1.8354250907897949
80th percentile: 1.942339086532593
90th percentile: 2.129735898971558
95th percentile: 2.22343430519104
99th percentile: 2.298393030166626
mean time: 1.8212457180023194
Pipeline stage StressChecker completed in 9.82s
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_v1 status is now deployed due to DeploymentManager action
sao10k-typhon-mixtral-v1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics