submission_id: sao10k-solstice-mixtral-v1_v1
developer_uid: sao10k
status: inactive
model_repo: Sao10K/Solstice-Mixtral-v1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.32, 'top_p': 0.84, '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: 2024-03-28T04:18:21+00:00
model_name: sao10k-solstice-mixtral-v1_v1
model_eval_status: success
safety_score: 0.98
entertaining: 7.02
stay_in_character: 8.71
user_preference: 7.6
double_thumbs_up: 254
thumbs_up: 350
thumbs_down: 162
num_battles: 60820
num_wins: 30610
win_ratio: 0.5032883919763236
celo_rating: 1159.57
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-solstice-mixtral-v1-v1-mkmlizer
Waiting for job on sao10k-solstice-mixtral-v1-v1-mkmlizer to finish
sao10k-solstice-mixtral-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ /___/ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ Version: 0.8.6 ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ belonging to: ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-solstice-mixtral-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-solstice-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-solstice-mixtral-v1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-solstice-mixtral-v1-v1-mkmlizer: Downloaded to shared memory in 235.462s
sao10k-solstice-mixtral-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-solstice-mixtral-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-solstice-mixtral-v1-v1-mkmlizer: quantized model in 68.203s
sao10k-solstice-mixtral-v1-v1-mkmlizer: Processed model Sao10K/Solstice-Mixtral-v1 in 309.315s
sao10k-solstice-mixtral-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-solstice-mixtral-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-solstice-mixtral-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/config.json
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/tokenizer.model
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/tokenizer.json
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/tokenizer_config.json
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/special_tokens_map.json
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/flywheel_model.3.safetensors
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/flywheel_model.1.safetensors
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/flywheel_model.0.safetensors
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-solstice-mixtral-v1-v1/flywheel_model.2.safetensors
sao10k-solstice-mixtral-v1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-solstice-mixtral-v1-v1-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 9/995 [00:00<00:11, 88.75it/s] Loading 0: 2%|▏ | 18/995 [00:00<00:18, 52.07it/s] Loading 0: 3%|▎ | 25/995 [00:00<00:18, 51.41it/s] Loading 0: 4%|▎ | 37/995 [00:00<00:13, 70.96it/s] Loading 0: 5%|▍ | 46/995 [00:00<00:12, 75.94it/s] Loading 0: 6%|▌ | 55/995 [00:01<00:20, 46.05it/s] Loading 0: 7%|▋ | 67/995 [00:01<00:15, 59.50it/s] Loading 0: 8%|▊ | 75/995 [00:01<00:14, 63.48it/s] Loading 0: 8%|▊ | 83/995 [00:01<00:14, 65.09it/s] Loading 0: 10%|▉ | 98/995 [00:01<00:10, 85.17it/s] Loading 0: 11%|█ | 108/995 [00:01<00:15, 55.69it/s] Loading 0: 12%|█▏ | 118/995 [00:01<00:13, 62.78it/s] Loading 0: 13%|█▎ | 130/995 [00:02<00:11, 73.38it/s] Loading 0: 14%|█▍ | 140/995 [00:02<00:10, 78.37it/s] Loading 0: 15%|█▌ | 150/995 [00:02<00:10, 80.94it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:13, 61.48it/s] Loading 0: 17%|█▋ | 171/995 [00:02<00:12, 65.88it/s] Loading 0: 18%|█▊ | 180/995 [00:02<00:11, 70.96it/s] Loading 0: 19%|█▉ | 192/995 [00:02<00:09, 81.25it/s] Loading 0: 20%|██ | 202/995 [00:02<00:09, 84.35it/s] Loading 0: 21%|██▏ | 212/995 [00:03<00:13, 56.80it/s] Loading 0: 22%|██▏ | 222/995 [00:03<00:12, 62.61it/s] Loading 0: 23%|██▎ | 230/995 [00:03<00:12, 59.71it/s] Loading 0: 24%|██▍ | 238/995 [00:03<00:12, 62.70it/s] Loading 0: 26%|██▌ | 254/995 [00:03<00:08, 83.46it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:12, 57.88it/s] Loading 0: 28%|██▊ | 279/995 [00:04<00:09, 71.72it/s] Loading 0: 29%|██▉ | 289/995 [00:18<04:25, 2.66it/s] Loading 0: 30%|███ | 299/995 [00:18<03:12, 3.62it/s] Loading 0: 31%|███ | 309/995 [00:18<02:18, 4.97it/s] Loading 0: 32%|███▏ | 320/995 [00:18<01:41, 6.66it/s] Loading 0: 33%|███▎ | 330/995 [00:18<01:13, 9.06it/s] Loading 0: 34%|███▍ | 340/995 [00:18<00:53, 12.26it/s] Loading 0: 35%|███▌ | 352/995 [00:18<00:36, 17.40it/s] Loading 0: 36%|███▋ | 362/995 [00:19<00:28, 22.51it/s] Loading 0: 37%|███▋ | 372/995 [00:19<00:25, 24.89it/s] Loading 0: 38%|███▊ | 382/995 [00:19<00:19, 31.73it/s] Loading 0: 39%|███▉ | 392/995 [00:19<00:15, 39.51it/s] Loading 0: 41%|████ | 408/995 [00:19<00:10, 56.54it/s] Loading 0: 42%|████▏ | 421/995 [00:19<00:08, 68.89it/s] Loading 0: 44%|████▎ | 433/995 [00:20<00:12, 43.88it/s] Loading 0: 44%|████▍ | 442/995 [00:20<00:11, 47.51it/s] Loading 0: 45%|████▌ | 452/995 [00:20<00:09, 54.77it/s] Loading 0: 47%|████▋ | 468/995 [00:20<00:07, 73.09it/s] Loading 0: 48%|████▊ | 479/995 [00:20<00:09, 55.33it/s] Loading 0: 49%|████▉ | 489/995 [00:21<00:08, 62.04it/s] Loading 0: 50%|█████ | 501/995 [00:21<00:06, 71.89it/s] Loading 0: 51%|█████▏ | 511/995 [00:21<00:06, 75.34it/s] Loading 0: 52%|█████▏ | 521/995 [00:21<00:06, 78.89it/s] Loading 0: 53%|█████▎ | 531/995 [00:21<00:08, 56.22it/s] Loading 0: 54%|█████▍ | 540/995 [00:21<00:07, 61.93it/s] Loading 0: 55%|█████▌ | 550/995 [00:21<00:06, 68.70it/s] Loading 0: 56%|█████▋ | 561/995 [00:35<02:56, 2.45it/s] Loading 0: 57%|█████▋ | 570/995 [00:35<02:07, 3.33it/s] Loading 0: 58%|█████▊ | 581/995 [00:36<01:29, 4.64it/s] Loading 0: 60%|█████▉ | 593/995 [00:36<00:58, 6.83it/s] Loading 0: 61%|██████ | 602/995 [00:36<00:43, 9.02it/s] Loading 0: 61%|██████▏ | 611/995 [00:36<00:32, 11.93it/s] Loading 0: 63%|██████▎ | 627/995 [00:36<00:19, 19.13it/s] Loading 0: 64%|██████▍ | 638/995 [00:36<00:16, 21.67it/s] Loading 0: 65%|██████▌ | 647/995 [00:37<00:13, 26.76it/s] Loading 0: 66%|██████▌ | 659/995 [00:37<00:09, 35.45it/s] Loading 0: 67%|██████▋ | 669/995 [00:37<00:07, 42.35it/s] Loading 0: 69%|██████▊ | 684/995 [00:37<00:05, 57.37it/s] Loading 0: 70%|██████▉ | 695/995 [00:37<00:06, 47.72it/s] Loading 0: 71%|███████ | 705/995 [00:37<00:05, 54.65it/s] Loading 0: 72%|███████▏ | 717/995 [00:37<00:04, 65.27it/s] Loading 0: 73%|███████▎ | 727/995 [00:37<00:03, 71.50it/s] Loading 0: 74%|███████▍ | 739/995 [00:38<00:04, 54.82it/s] Loading 0: 75%|███████▌ | 751/995 [00:38<00:03, 65.02it/s] Loading 0: 76%|███████▋ | 760/995 [00:38<00:03, 64.48it/s] Loading 0: 77%|███████▋ | 768/995 [00:38<00:03, 64.99it/s] Loading 0: 79%|███████▊ | 782/995 [00:38<00:02, 79.64it/s] Loading 0: 80%|███████▉ | 794/995 [00:39<00:03, 50.91it/s] Loading 0: 81%|████████ | 802/995 [00:39<00:03, 52.89it/s] Loading 0: 81%|████████▏ | 810/995 [00:39<00:03, 57.59it/s] Loading 0: 82%|████████▏ | 818/995 [00:39<00:03, 57.97it/s] Loading 0: 83%|████████▎ | 825/995 [00:39<00:02, 58.79it/s] Loading 0: 84%|████████▍ | 835/995 [00:39<00:02, 68.12it/s] Loading 0: 85%|████████▍ | 841/995 [00:50<00:02, 68.12it/s] Loading 0: 85%|████████▍ | 842/995 [00:53<01:17, 1.98it/s] Loading 0: 85%|████████▌ | 849/995 [00:54<00:56, 2.58it/s] Loading 0: 86%|████████▌ | 856/995 [00:54<00:39, 3.50it/s] Loading 0: 87%|████████▋ | 863/995 [00:54<00:27, 4.77it/s] Loading 0: 88%|████████▊ | 872/995 [00:54<00:17, 6.99it/s] Loading 0: 88%|████████▊ | 879/995 [00:54<00:12, 9.21it/s] Loading 0: 89%|████████▉ | 886/995 [00:54<00:09, 11.82it/s] Loading 0: 90%|████████▉ | 892/995 [00:54<00:07, 14.47it/s] Loading 0: 90%|█████████ | 898/995 [00:55<00:06, 14.98it/s] Loading 0: 91%|█████████▏| 908/995 [00:55<00:03, 22.15it/s] Loading 0: 92%|█████████▏| 916/995 [00:55<00:02, 28.04it/s] Loading 0: 93%|█████████▎| 922/995 [00:55<00:02, 31.54it/s] Loading 0: 94%|█████████▍| 935/995 [00:55<00:01, 46.62it/s] Loading 0: 95%|█████████▍| 943/995 [00:55<00:01, 50.57it/s] Loading 0: 96%|█████████▌| 952/995 [00:57<00:02, 14.44it/s] Loading 0: 96%|█████████▋| 959/995 [00:57<00:02, 17.95it/s] Loading 0: 97%|█████████▋| 968/995 [00:57<00:01, 23.85it/s] Loading 0: 98%|█████████▊| 975/995 [00:57<00:00, 28.17it/s] Loading 0: 99%|█████████▊| 982/995 [00:57<00:00, 33.12it/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-solstice-mixtral-v1-v1-mkmlizer: warnings.warn(
sao10k-solstice-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-solstice-mixtral-v1-v1-mkmlizer: warnings.warn(
sao10k-solstice-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-solstice-mixtral-v1-v1-mkmlizer: warnings.warn(
sao10k-solstice-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-solstice-mixtral-v1-v1_reward/reward.tensors
Job sao10k-solstice-mixtral-v1-v1-mkmlizer completed after 375.35s with status: succeeded
Stopping job with name sao10k-solstice-mixtral-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 379.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-solstice-mixtral-v1-v1
Waiting for inference service sao10k-solstice-mixtral-v1-v1 to be ready
Inference service sao10k-solstice-mixtral-v1-v1 ready after 60.365702867507935s
Pipeline stage ISVCDeployer completed in 67.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3079700469970703s
Received healthy response to inference request in 2.053053379058838s
Received healthy response to inference request in 1.6345853805541992s
Received healthy response to inference request in 2.3993165493011475s
Received healthy response to inference request in 2.0417025089263916s
5 requests
0 failed requests
5th percentile: 1.7160088062286376
10th percentile: 1.7974322319030762
20th percentile: 1.9602790832519532
30th percentile: 2.043972682952881
40th percentile: 2.0485130310058595
50th percentile: 2.053053379058838
60th percentile: 2.1550200462341307
70th percentile: 2.256986713409424
80th percentile: 2.3262393474578857
90th percentile: 2.3627779483795166
95th percentile: 2.381047248840332
99th percentile: 2.3956626892089843
mean time: 2.0873255729675293
Pipeline stage StressChecker completed in 11.25s
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
sao10k-solstice-mixtral-v1_v1 status is now deployed due to DeploymentManager action
sao10k-solstice-mixtral-v1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics