submission_id: neversleep-noromaid-v0-_8068_v29
developer_uid: chai_backend_admin
status: torndown
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, '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}:'}
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: 2024-04-01T19:33:54+00:00
model_name: auto_submit_ukiji_avisojem
model_eval_status: success
safety_score: 0.96
entertaining: 6.8
stay_in_character: 8.46
user_preference: 7.12
double_thumbs_up: 44
thumbs_up: 93
thumbs_down: 57
num_battles: 5025
num_wins: 2266
win_ratio: 0.4509452736318408
celo_rating: 1125.98
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v29-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v29-mkmlizer to finish
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
neversleep-noromaid-v0-8068-v29-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v29-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v29-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.
neversleep-noromaid-v0-8068-v29-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v29-mkmlizer: Downloaded to shared memory in 54.211s
neversleep-noromaid-v0-8068-v29-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v29-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v29-mkmlizer: quantized model in 53.656s
neversleep-noromaid-v0-8068-v29-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 113.648s
neversleep-noromaid-v0-8068-v29-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v29-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v29-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/tokenizer.model
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/tokenizer_config.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/special_tokens_map.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/tokenizer.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/config.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v29/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v29-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v29-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:15, 59.56it/s] Loading 0: 11%|█ | 107/995 [00:01<00:13, 63.59it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:12, 65.59it/s] Loading 0: 21%|██ | 210/995 [00:03<00:12, 61.06it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:11, 62.44it/s] Loading 0: 28%|██▊ | 278/995 [00:13<01:10, 10.24it/s] Loading 0: 32%|███▏ | 320/995 [00:15<00:49, 13.50it/s] Loading 0: 37%|███▋ | 368/995 [00:15<00:33, 18.62it/s] Loading 0: 43%|████▎ | 423/995 [00:16<00:22, 25.06it/s] Loading 0: 48%|████▊ | 478/995 [00:17<00:16, 31.95it/s] Loading 0: 53%|█████▎ | 526/995 [00:18<00:12, 37.17it/s] Loading 0: 57%|█████▋ | 565/995 [00:27<00:35, 12.06it/s] Loading 0: 58%|█████▊ | 581/995 [00:28<00:33, 12.39it/s] Loading 0: 64%|██████▍ | 636/995 [00:29<00:19, 18.14it/s] Loading 0: 69%|██████▉ | 691/995 [00:30<00:12, 24.51it/s] Loading 0: 74%|███████▍ | 739/995 [00:31<00:08, 29.77it/s] Loading 0: 80%|███████▉ | 794/995 [00:32<00:05, 35.31it/s] Loading 0: 85%|████████▌ | 846/995 [00:41<00:11, 13.30it/s] Loading 0: 85%|████████▌ | 850/995 [00:42<00:11, 12.17it/s] Loading 0: 90%|█████████ | 897/995 [00:43<00:05, 16.56it/s] Loading 0: 96%|█████████▌| 952/995 [00:44<00:01, 22.85it/s] Loading 0: 100%|██████████| 995/995 [00:46<00:00, 25.59it/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.
neversleep-noromaid-v0-8068-v29-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v29-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.
neversleep-noromaid-v0-8068-v29-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v29-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.
neversleep-noromaid-v0-8068-v29-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v29-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()
neversleep-noromaid-v0-8068-v29-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v29-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v29-mkmlizer: Saving duration: 0.251s
neversleep-noromaid-v0-8068-v29-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.239s
neversleep-noromaid-v0-8068-v29-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v29-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v29-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/config.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/merges.txt
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/vocab.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/tokenizer.json
neversleep-noromaid-v0-8068-v29-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v29_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v29-mkmlizer completed after 261.47s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v29-mkmlizer
Pipeline stage MKMLizer completed in 265.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v29
Waiting for inference service neversleep-noromaid-v0-8068-v29 to be ready
Inference service neversleep-noromaid-v0-8068-v29 ready after 50.34166669845581s
Pipeline stage ISVCDeployer completed in 57.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.773282766342163s
Received healthy response to inference request in 0.48142099380493164s
Received healthy response to inference request in 0.9065852165222168s
Received healthy response to inference request in 0.6092431545257568s
Received healthy response to inference request in 1.0685973167419434s
5 requests
0 failed requests
5th percentile: 0.5069854259490967
10th percentile: 0.5325498580932617
20th percentile: 0.5836787223815918
30th percentile: 0.6687115669250489
40th percentile: 0.7876483917236329
50th percentile: 0.9065852165222168
60th percentile: 0.9713900566101075
70th percentile: 1.036194896697998
80th percentile: 1.2095344066619875
90th percentile: 1.4914085865020752
95th percentile: 1.632345676422119
99th percentile: 1.7450953483581542
mean time: 0.9678258895874023
Pipeline stage StressChecker completed in 5.69s
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
neversleep-noromaid-v0-_8068_v29 status is now deployed due to DeploymentManager action
admin requested tearing down of neversleep-noromaid-v0-_8068_v29
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v29 is running
Tearing down inference service neversleep-noromaid-v0-8068-v29
Toredown service neversleep-noromaid-v0-8068-v29
Pipeline stage ISVCDeleter completed in 6.70s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v29/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v29/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v29_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v29_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v29_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v29_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v29_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v29_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v29_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.01s
neversleep-noromaid-v0-_8068_v29 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics