submission_id: sao10k-typhon-mixtral-v1_v3
developer_uid: chai_backend_admin
status: torndown
model_repo: Sao10K/Typhon-Mixtral-v1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, '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}:', 'truncate_by_message': False}
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}:', 'truncate_by_message': False}
timestamp: 2024-04-02T04:00:38+00:00
model_name: auto_submit_bolan_morudesi
model_eval_status: success
model_group: Sao10K/Typhon-Mixtral-v1
num_battles: 5723
num_wins: 2587
celo_rating: 1128.34
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: auto_submit_bolan_morudesi
ineligible_reason: propriety_total_count < 800
language_model: Sao10K/Typhon-Mixtral-v1
model_size: 47B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-01
win_ratio: 0.4520356456403984
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-typhon-mixtral-v1-v3-mkmlizer
Waiting for job on sao10k-typhon-mixtral-v1-v3-mkmlizer to finish
sao10k-typhon-mixtral-v1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ _____ __ __ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ /___/ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ Version: 0.8.6 ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ belonging to: ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ Chai Research Corp. ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ║ ║
sao10k-typhon-mixtral-v1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-typhon-mixtral-v1-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-typhon-mixtral-v1-v3-mkmlizer: Downloaded to shared memory in 87.069s
sao10k-typhon-mixtral-v1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-typhon-mixtral-v1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Exception raised while processing tagging_function
Traceback (most recent call last): File "/code/guanaco/guanaco_services/src/guanaco_model_service/chat_api.py", line 274, in resolve_chat_api conversation_tag = self.tagging_function(conversation_state) File "/home/zongyi/gitlab/zztools/zztools/llm/guanaco/submit_routing_model.py", line 176, in last_user_message_length TypeError: 'ConversationState' object is not subscriptable
sao10k-typhon-mixtral-v1-v3-mkmlizer: quantized model in 47.568s
sao10k-typhon-mixtral-v1-v3-mkmlizer: Processed model Sao10K/Typhon-Mixtral-v1 in 139.871s
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v3/flywheel_model.3.safetensors
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v3/flywheel_model.2.safetensors
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v3/flywheel_model.0.safetensors
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-typhon-mixtral-v1-v3/flywheel_model.1.safetensors
Exception raised while processing tagging_function
Traceback (most recent call last): File "/code/guanaco/guanaco_services/src/guanaco_model_service/chat_api.py", line 274, in resolve_chat_api conversation_tag = self.tagging_function(conversation_state) File "/home/zongyi/gitlab/zztools/zztools/llm/guanaco/submit_routing_model.py", line 176, in last_user_message_length TypeError: 'ConversationMessage' object is not subscriptable
sao10k-typhon-mixtral-v1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-typhon-mixtral-v1-v3-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 10/995 [00:00<00:10, 97.91it/s] Loading 0: 2%|▏ | 20/995 [00:00<00:10, 89.44it/s] Loading 0: 4%|▎ | 35/995 [00:00<00:08, 112.17it/s] Loading 0: 5%|▍ | 47/995 [00:00<00:08, 105.39it/s] Loading 0: 6%|▌ | 62/995 [00:00<00:07, 118.96it/s] Loading 0: 8%|▊ | 75/995 [00:00<00:08, 110.99it/s] Loading 0: 9%|▊ | 87/995 [00:00<00:09, 99.38it/s] Loading 0: 11%|█ | 111/995 [00:00<00:06, 136.70it/s] Loading 0: 13%|█▎ | 126/995 [00:01<00:14, 59.27it/s] Loading 0: 14%|█▍ | 138/995 [00:01<00:12, 67.40it/s] Loading 0: 15%|█▍ | 149/995 [00:01<00:11, 70.65it/s] Loading 0: 16%|█▋ | 163/995 [00:01<00:10, 82.48it/s] Loading 0: 18%|█▊ | 175/995 [00:02<00:09, 84.00it/s] Loading 0: 19%|█▊ | 186/995 [00:02<00:09, 87.28it/s] Loading 0: 20%|█▉ | 197/995 [00:02<00:09, 88.49it/s] Loading 0: 21%|██ | 210/995 [00:02<00:08, 96.11it/s] Loading 0: 22%|██▏ | 221/995 [00:02<00:16, 48.05it/s] Loading 0: 23%|██▎ | 232/995 [00:02<00:13, 57.15it/s] Loading 0: 24%|██▍ | 242/995 [00:03<00:11, 63.81it/s] Loading 0: 25%|██▌ | 252/995 [00:03<00:10, 70.65it/s] Loading 0: 27%|██▋ | 267/995 [00:03<00:08, 87.41it/s] Loading 0: 28%|██▊ | 278/995 [00:03<00:08, 86.91it/s] Loading 0: 29%|██▉ | 289/995 [00:12<02:48, 4.20it/s] Loading 0: 30%|███ | 300/995 [00:12<01:59, 5.82it/s] Loading 0: 31%|███ | 310/995 [00:12<01:27, 7.83it/s] Loading 0: 32%|███▏ | 322/995 [00:13<01:08, 9.87it/s] Loading 0: 33%|███▎ | 332/995 [00:13<00:50, 13.11it/s] Loading 0: 34%|███▍ | 341/995 [00:13<00:38, 16.86it/s] Loading 0: 35%|███▌ | 352/995 [00:13<00:28, 22.80it/s] Loading 0: 36%|███▋ | 362/995 [00:13<00:21, 29.20it/s] Loading 0: 38%|███▊ | 377/995 [00:13<00:14, 41.98it/s] Loading 0: 39%|███▉ | 388/995 [00:13<00:12, 48.98it/s] Loading 0: 40%|████ | 398/995 [00:13<00:10, 56.13it/s] Loading 0: 42%|████▏ | 413/995 [00:13<00:08, 71.63it/s] Loading 0: 43%|████▎ | 426/995 [00:14<00:12, 45.33it/s] Loading 0: 44%|████▍ | 436/995 [00:14<00:10, 52.35it/s] Loading 0: 45%|████▌ | 448/995 [00:14<00:08, 62.53it/s] Loading 0: 46%|████▌ | 458/995 [00:14<00:07, 68.12it/s] Loading 0: 48%|████▊ | 473/995 [00:14<00:06, 84.03it/s] Loading 0: 49%|████▊ | 484/995 [00:14<00:05, 86.20it/s] Loading 0: 50%|█████ | 499/995 [00:15<00:04, 100.40it/s] Loading 0: 51%|█████▏ | 511/995 [00:15<00:04, 98.13it/s] Loading 0: 52%|█████▏ | 522/995 [00:15<00:04, 98.16it/s] Loading 0: 54%|█████▎ | 533/995 [00:15<00:09, 49.02it/s] Loading 0: 54%|█████▍ | 542/995 [00:15<00:08, 54.81it/s] Loading 0: 55%|█████▌ | 552/995 [00:16<00:07, 62.38it/s] Loading 0: 56%|█████▋ | 561/995 [00:24<01:57, 3.68it/s] Loading 0: 58%|█████▊ | 573/995 [00:24<01:17, 5.45it/s] Loading 0: 58%|█████▊ | 582/995 [00:25<00:56, 7.25it/s] Loading 0: 60%|██████ | 597/995 [00:25<00:34, 11.44it/s] Loading 0: 61%|██████ | 607/995 [00:25<00:25, 14.96it/s] Loading 0: 63%|██████▎ | 623/995 [00:25<00:16, 22.75it/s] Loading 0: 64%|██████▍ | 638/995 [00:25<00:11, 31.68it/s] Loading 0: 65%|██████▌ | 650/995 [00:26<00:13, 25.13it/s] Loading 0: 67%|██████▋ | 662/995 [00:26<00:10, 32.24it/s] Loading 0: 68%|██████▊ | 672/995 [00:26<00:08, 38.47it/s] Loading 0: 69%|██████▊ | 682/995 [00:26<00:06, 45.43it/s] Loading 0: 70%|██████▉ | 696/995 [00:26<00:05, 59.29it/s] Loading 0: 71%|███████ | 707/995 [00:26<00:04, 64.59it/s] Loading 0: 72%|███████▏ | 718/995 [00:26<00:03, 72.88it/s] Loading 0: 73%|███████▎ | 729/995 [00:26<00:03, 76.69it/s] Loading 0: 75%|███████▍ | 743/995 [00:27<00:05, 43.14it/s] Loading 0: 76%|███████▌ | 753/995 [00:27<00:04, 49.83it/s] Loading 0: 77%|███████▋ | 762/995 [00:27<00:04, 55.55it/s] Loading 0: 78%|███████▊ | 772/995 [00:27<00:03, 62.94it/s] Loading 0: 79%|███████▉ | 788/995 [00:28<00:02, 81.33it/s] Loading 0: 80%|████████ | 799/995 [00:28<00:02, 82.45it/s] Loading 0: 82%|████████▏ | 813/995 [00:28<00:01, 94.02it/s] Loading 0: 83%|████████▎ | 824/995 [00:28<00:01, 93.73it/s] Loading 0: 84%|████████▍ | 840/995 [00:28<00:01, 109.24it/s] Loading 0: 86%|████████▌ | 852/995 [00:37<00:30, 4.62it/s] Loading 0: 87%|████████▋ | 861/995 [00:39<00:28, 4.71it/s] Loading 0: 88%|████████▊ | 871/995 [00:39<00:19, 6.32it/s] Loading 0: 89%|████████▊ | 883/995 [00:39<00:12, 9.00it/s] Loading 0: 90%|████████▉ | 893/995 [00:39<00:08, 11.93it/s] Loading 0: 91%|█████████▏| 908/995 [00:39<00:04, 17.99it/s] Loading 0: 92%|█████████▏| 919/995 [00:39<00:03, 23.03it/s] Loading 0: 94%|█████████▍| 935/995 [00:39<00:01, 33.44it/s] Loading 0: 95%|█████████▌| 947/995 [00:40<00:01, 40.86it/s] Loading 0: 96%|█████████▋| 958/995 [00:40<00:01, 32.59it/s] Loading 0: 97%|█████████▋| 969/995 [00:40<00:00, 40.19it/s] Loading 0: 98%|█████████▊| 978/995 [00:40<00:00, 45.63it/s] Loading 0: 99%|█████████▉| 987/995 [00:40<00:00, 52.24it/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-v3-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v3-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-v3-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v3-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-v3-mkmlizer: warnings.warn(
sao10k-typhon-mixtral-v1-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-typhon-mixtral-v1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-typhon-mixtral-v1-v3-mkmlizer: Saving duration: 0.221s
sao10k-typhon-mixtral-v1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.186s
sao10k-typhon-mixtral-v1-v3-mkmlizer: creating bucket guanaco-reward-models
sao10k-typhon-mixtral-v1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-typhon-mixtral-v1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/tokenizer_config.json
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/config.json
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/special_tokens_map.json
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/vocab.json
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/merges.txt
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/tokenizer.json
sao10k-typhon-mixtral-v1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-typhon-mixtral-v1-v3_reward/reward.tensors
Job sao10k-typhon-mixtral-v1-v3-mkmlizer completed after 218.7s with status: succeeded
Stopping job with name sao10k-typhon-mixtral-v1-v3-mkmlizer
Pipeline stage MKMLizer completed in 222.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-typhon-mixtral-v1-v3
Waiting for inference service sao10k-typhon-mixtral-v1-v3 to be ready
Inference service sao10k-typhon-mixtral-v1-v3 ready after 60.51905798912048s
Pipeline stage ISVCDeployer completed in 68.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9488005638122559s
Received healthy response to inference request in 1.074700117111206s
Received healthy response to inference request in 1.338125467300415s
Received healthy response to inference request in 1.3543686866760254s
Received healthy response to inference request in 1.1573712825775146s
5 requests
0 failed requests
5th percentile: 1.0912343502044677
10th percentile: 1.1077685832977295
20th percentile: 1.140837049484253
30th percentile: 1.1935221195220946
40th percentile: 1.2658237934112548
50th percentile: 1.338125467300415
60th percentile: 1.344622755050659
70th percentile: 1.3511200428009034
80th percentile: 1.4732550621032716
90th percentile: 1.7110278129577638
95th percentile: 1.8299141883850096
99th percentile: 1.9250232887268066
mean time: 1.3746732234954835
Pipeline stage StressChecker completed in 7.69s
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-typhon-mixtral-v1_v3 status is now deployed due to DeploymentManager action
sao10k-typhon-mixtral-v1_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-typhon-mixtral-v1_v3
Running pipeline stage ISVCDeleter
Checking if service sao10k-typhon-mixtral-v1-v3 is running
Tearing down inference service sao10k-typhon-mixtral-v1-v3
Toredown service sao10k-typhon-mixtral-v1-v3
Pipeline stage ISVCDeleter completed in 5.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-typhon-mixtral-v1-v3/config.json from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key sao10k-typhon-mixtral-v1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-typhon-mixtral-v1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-typhon-mixtral-v1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-typhon-mixtral-v1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-typhon-mixtral-v1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-typhon-mixtral-v1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-typhon-mixtral-v1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-typhon-mixtral-v1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.01s
sao10k-typhon-mixtral-v1_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics