submission_id: sao10k-franziska-mixtral-v1_v1
developer_uid: sao10k
status: inactive
model_repo: Sao10K/Franziska-Mixtral-v1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.32, 'top_p': 0.86, 'top_k': 30, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '###Input', '\n{user_name}:', '\n\n'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': "Below is an instruction that describes a task. Write a response that appropriately completes the request. \n\n### Instruction: Using the skill of an author, you're {bot_name} in a roleplaying session that leaves a lasting impression on {user_name}. Reply as {bot_name}. Stay true to the persona given. Progress and advance the scene at a natural pace, while allowing for {{user}} to input their reply. You are to follow the following prompt: {prompt}. Progress and advance the scene at a natural pace, while allowing for {{user}} to input their reply.", 'bot_template': '### Response: {bot_name}: {message}\n', 'user_template': '### Input: {user_name}: {message}\n', 'response_template': '### Response: {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: 2024-04-02T11:55:06+00:00
model_name: sao10k-franziska-mixtral-v1_v1
model_eval_status: success
safety_score: 0.99
entertaining: 7.06
stay_in_character: 8.65
user_preference: 7.68
double_thumbs_up: 363
thumbs_up: 581
thumbs_down: 238
num_battles: 36860
num_wins: 19280
win_ratio: 0.523060227889311
celo_rating: 1174.29
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-franziska-mixtral-v1-v1-mkmlizer
Waiting for job on sao10k-franziska-mixtral-v1-v1-mkmlizer to finish
sao10k-franziska-mixtral-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ /___/ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ Version: 0.8.6 ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ belonging to: ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ║ ║
sao10k-franziska-mixtral-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-franziska-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-franziska-mixtral-v1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-franziska-mixtral-v1-v1-mkmlizer: Downloaded to shared memory in 88.462s
sao10k-franziska-mixtral-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-franziska-mixtral-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-franziska-mixtral-v1-v1-mkmlizer: quantized model in 48.140s
sao10k-franziska-mixtral-v1-v1-mkmlizer: Processed model Sao10K/Franziska-Mixtral-v1 in 141.758s
sao10k-franziska-mixtral-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-franziska-mixtral-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-franziska-mixtral-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/special_tokens_map.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/tokenizer_config.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/tokenizer.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/tokenizer.model
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/config.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/flywheel_model.3.safetensors
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/flywheel_model.2.safetensors
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/flywheel_model.0.safetensors
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-franziska-mixtral-v1-v1/flywheel_model.1.safetensors
sao10k-franziska-mixtral-v1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-franziska-mixtral-v1-v1-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 9/995 [00:00<00:11, 87.37it/s] Loading 0: 2%|▏ | 18/995 [00:00<00:12, 79.03it/s] Loading 0: 3%|▎ | 34/995 [00:00<00:08, 109.09it/s] Loading 0: 5%|▍ | 46/995 [00:00<00:09, 102.19it/s] Loading 0: 6%|▌ | 57/995 [00:00<00:09, 101.58it/s] Loading 0: 7%|▋ | 71/995 [00:00<00:08, 113.14it/s] Loading 0: 8%|▊ | 83/995 [00:00<00:09, 93.83it/s] Loading 0: 10%|▉ | 99/995 [00:00<00:08, 108.68it/s] Loading 0: 11%|█▏ | 114/995 [00:01<00:15, 56.74it/s] Loading 0: 12%|█▏ | 124/995 [00:01<00:13, 62.77it/s] Loading 0: 14%|█▎ | 136/995 [00:01<00:11, 71.59it/s] Loading 0: 15%|█▍ | 146/995 [00:01<00:11, 73.24it/s] Loading 0: 16%|█▌ | 156/995 [00:01<00:10, 77.92it/s] Loading 0: 17%|█▋ | 170/995 [00:02<00:08, 92.10it/s] Loading 0: 18%|█▊ | 181/995 [00:02<00:08, 92.78it/s] Loading 0: 19%|█▉ | 192/995 [00:02<00:08, 95.56it/s] Loading 0: 20%|██ | 203/995 [00:02<00:08, 92.67it/s] Loading 0: 22%|██▏ | 216/995 [00:02<00:16, 48.40it/s] Loading 0: 24%|██▎ | 234/995 [00:03<00:11, 68.03it/s] Loading 0: 25%|██▍ | 246/995 [00:03<00:09, 76.68it/s] Loading 0: 26%|██▌ | 257/995 [00:03<00:09, 78.83it/s] Loading 0: 27%|██▋ | 272/995 [00:03<00:07, 92.66it/s] Loading 0: 29%|██▊ | 284/995 [00:03<00:07, 92.21it/s] Loading 0: 30%|██▉ | 295/995 [00:12<02:38, 4.41it/s] Loading 0: 31%|███ | 305/995 [00:12<01:57, 5.85it/s] Loading 0: 32%|███▏ | 315/995 [00:12<01:26, 7.82it/s] Loading 0: 33%|███▎ | 326/995 [00:13<01:10, 9.54it/s] Loading 0: 34%|███▍ | 336/995 [00:13<00:51, 12.72it/s] Loading 0: 35%|███▍ | 345/995 [00:13<00:39, 16.43it/s] Loading 0: 36%|███▌ | 355/995 [00:13<00:29, 21.78it/s] Loading 0: 37%|███▋ | 364/995 [00:13<00:23, 27.38it/s] Loading 0: 38%|███▊ | 376/995 [00:13<00:16, 36.89it/s] Loading 0: 39%|███▉ | 386/995 [00:13<00:13, 44.53it/s] Loading 0: 40%|███▉ | 396/995 [00:13<00:11, 51.89it/s] Loading 0: 41%|████▏ | 411/995 [00:14<00:08, 68.49it/s] Loading 0: 43%|████▎ | 428/995 [00:14<00:06, 88.65it/s] Loading 0: 44%|████▍ | 441/995 [00:14<00:11, 48.39it/s] Loading 0: 45%|████▌ | 451/995 [00:14<00:09, 55.40it/s] Loading 0: 46%|████▋ | 461/995 [00:14<00:08, 60.80it/s] Loading 0: 48%|████▊ | 476/995 [00:15<00:06, 75.86it/s] Loading 0: 49%|████▉ | 487/995 [00:15<00:06, 78.75it/s] Loading 0: 50%|█████ | 499/995 [00:15<00:05, 85.83it/s] Loading 0: 51%|█████▏ | 510/995 [00:15<00:05, 86.90it/s] Loading 0: 52%|█████▏ | 520/995 [00:15<00:05, 85.53it/s] Loading 0: 54%|█████▎ | 534/995 [00:16<00:09, 47.58it/s] Loading 0: 54%|█████▍ | 542/995 [00:16<00:08, 50.69it/s] Loading 0: 55%|█████▌ | 550/995 [00:16<00:09, 47.56it/s] Loading 0: 56%|█████▌ | 557/995 [00:16<00:09, 48.04it/s] Loading 0: 57%|█████▋ | 563/995 [00:25<02:31, 2.86it/s] Loading 0: 58%|█████▊ | 576/995 [00:25<01:28, 4.74it/s] Loading 0: 59%|█████▉ | 586/995 [00:25<01:01, 6.70it/s] Loading 0: 60%|██████ | 598/995 [00:25<00:39, 9.94it/s] Loading 0: 61%|██████ | 608/995 [00:26<00:28, 13.46it/s] Loading 0: 63%|██████▎ | 624/995 [00:26<00:17, 21.24it/s] Loading 0: 65%|██████▌ | 647/995 [00:26<00:09, 35.89it/s] Loading 0: 67%|██████▋ | 662/995 [00:26<00:10, 31.53it/s] Loading 0: 68%|██████▊ | 673/995 [00:26<00:08, 37.75it/s] Loading 0: 69%|██████▊ | 684/995 [00:27<00:06, 44.64it/s] Loading 0: 70%|██████▉ | 695/995 [00:27<00:05, 52.01it/s] Loading 0: 71%|███████ | 706/995 [00:27<00:04, 59.38it/s] Loading 0: 72%|███████▏ | 717/995 [00:27<00:04, 67.65it/s] Loading 0: 73%|███████▎ | 728/995 [00:27<00:03, 73.32it/s] Loading 0: 75%|███████▌ | 747/995 [00:28<00:04, 50.52it/s] Loading 0: 76%|███████▋ | 759/995 [00:28<00:03, 59.11it/s] Loading 0: 77%|███████▋ | 768/995 [00:28<00:03, 63.47it/s] Loading 0: 79%|███████▊ | 783/995 [00:28<00:02, 79.39it/s] Loading 0: 80%|███████▉ | 794/995 [00:28<00:02, 83.69it/s] Loading 0: 81%|████████ | 805/995 [00:28<00:02, 86.38it/s] Loading 0: 82%|████████▏ | 816/995 [00:28<00:01, 90.72it/s] Loading 0: 83%|████████▎ | 827/995 [00:28<00:01, 90.01it/s] Loading 0: 85%|████████▍ | 843/995 [00:37<00:33, 4.54it/s] Loading 0: 86%|████████▌ | 857/995 [00:39<00:26, 5.29it/s] Loading 0: 87%|████████▋ | 867/995 [00:39<00:18, 6.88it/s] Loading 0: 88%|████████▊ | 876/995 [00:39<00:13, 8.83it/s] Loading 0: 89%|████████▉ | 887/995 [00:39<00:08, 12.12it/s] Loading 0: 90%|█████████ | 896/995 [00:40<00:06, 15.37it/s] Loading 0: 91%|█████████ | 907/995 [00:40<00:04, 20.92it/s] Loading 0: 92%|█████████▏| 916/995 [00:40<00:03, 26.20it/s] Loading 0: 93%|█████████▎| 925/995 [00:40<00:02, 32.42it/s] Loading 0: 94%|█████████▍| 940/995 [00:40<00:01, 46.75it/s] Loading 0: 96%|█████████▌| 952/995 [00:40<00:00, 57.68it/s] Loading 0: 97%|█████████▋| 963/995 [00:41<00:00, 38.62it/s] Loading 0: 98%|█████████▊| 974/995 [00:41<00:00, 47.58it/s] Loading 0: 99%|█████████▉| 984/995 [00:41<00:00, 54.83it/s] Loading 0: 100%|█████████▉| 994/995 [00:41<00:00, 61.94it/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-franziska-mixtral-v1-v1-mkmlizer: warnings.warn(
sao10k-franziska-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-franziska-mixtral-v1-v1-mkmlizer: warnings.warn(
sao10k-franziska-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-franziska-mixtral-v1-v1-mkmlizer: warnings.warn(
sao10k-franziska-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-franziska-mixtral-v1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-franziska-mixtral-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-franziska-mixtral-v1-v1-mkmlizer: Saving duration: 0.246s
sao10k-franziska-mixtral-v1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.609s
sao10k-franziska-mixtral-v1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-franziska-mixtral-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-franziska-mixtral-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/special_tokens_map.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/config.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/tokenizer_config.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/merges.txt
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/vocab.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/tokenizer.json
sao10k-franziska-mixtral-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-franziska-mixtral-v1-v1_reward/reward.tensors
Job sao10k-franziska-mixtral-v1-v1-mkmlizer completed after 179.92s with status: succeeded
Stopping job with name sao10k-franziska-mixtral-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 188.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-franziska-mixtral-v1-v1
Waiting for inference service sao10k-franziska-mixtral-v1-v1 to be ready
Inference service sao10k-franziska-mixtral-v1-v1 ready after 60.3336238861084s
Pipeline stage ISVCDeployer completed in 68.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9147117137908936s
Received healthy response to inference request in 2.5516369342803955s
Received healthy response to inference request in 2.6563072204589844s
Received healthy response to inference request in 2.8601396083831787s
Received healthy response to inference request in 2.663034439086914s
5 requests
0 failed requests
5th percentile: 2.5725709915161135
10th percentile: 2.593505048751831
20th percentile: 2.6353731632232664
30th percentile: 2.65765266418457
40th percentile: 2.660343551635742
50th percentile: 2.663034439086914
60th percentile: 2.74187650680542
70th percentile: 2.8207185745239256
80th percentile: 3.071054029464722
90th percentile: 3.4928828716278075
95th percentile: 3.7037972927093503
99th percentile: 3.872528829574585
mean time: 2.929165983200073
Pipeline stage StressChecker completed in 16.04s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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-franziska-mixtral-v1_v1 status is now deployed due to DeploymentManager action
sao10k-franziska-mixtral-v1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics