submission_id: bbchicago-test-lora-blac_1874_v2
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/test_lora_Blackroot_Abomination
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-06-11T09:33:47+00:00
model_name: bbchicago-test-lora-blac_1874_v2
model_eval_status: success
model_group: BBChicago/test_lora_Blac
num_battles: 16202
num_wins: 8313
celo_rating: 1170.73
propriety_score: 0.6677413576929966
propriety_total_count: 5583.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bbchicago-test-lora-blac_1874_v2
ineligible_reason: None
language_model: BBChicago/test_lora_Blackroot_Abomination
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5130848043451426
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-blac-1874-v2-mkmlizer
Waiting for job on bbchicago-test-lora-blac-1874-v2-mkmlizer to finish
bbchicago-test-lora-blac-1874-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ _____ __ __ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ /___/ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ belonging to: ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ║ ║
bbchicago-test-lora-blac-1874-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-blac-1874-v2-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.
bbchicago-test-lora-blac-1874-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-blac-1874-v2-mkmlizer: Downloaded to shared memory in 15.098s
bbchicago-test-lora-blac-1874-v2-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-blac-1874-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-blac-1874-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 209.02it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 196.21it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 210.07it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 105.27it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 130.29it/s] Loading 0: 45%|████▍ | 130/291 [00:00<00:01, 143.64it/s] Loading 0: 52%|█████▏ | 150/291 [00:00<00:00, 157.19it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 172.33it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:00, 108.55it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 128.68it/s] Loading 0: 81%|████████▏ | 237/291 [00:01<00:00, 147.36it/s] Loading 0: 88%|████████▊ | 257/291 [00:01<00:00, 156.57it/s] Loading 0: 97%|█████████▋| 281/291 [00:01<00:00, 173.54it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-blac-1874-v2-mkmlizer: quantized model in 16.573s
bbchicago-test-lora-blac-1874-v2-mkmlizer: Processed model BBChicago/test_lora_Blackroot_Abomination in 32.575s
bbchicago-test-lora-blac-1874-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-blac-1874-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-blac-1874-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-blac-1874-v2
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-1874-v2/special_tokens_map.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-1874-v2/config.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-1874-v2/tokenizer_config.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-blac-1874-v2/tokenizer.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-blac-1874-v2/flywheel_model.0.safetensors
bbchicago-test-lora-blac-1874-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-blac-1874-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-lora-blac-1874-v2-mkmlizer: warnings.warn(
bbchicago-test-lora-blac-1874-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-lora-blac-1874-v2-mkmlizer: warnings.warn(
bbchicago-test-lora-blac-1874-v2-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()
bbchicago-test-lora-blac-1874-v2-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-lora-blac-1874-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-blac-1874-v2-mkmlizer: Saving duration: 0.212s
bbchicago-test-lora-blac-1874-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.015s
bbchicago-test-lora-blac-1874-v2-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-blac-1874-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-blac-1874-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/config.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/special_tokens_map.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/merges.txt
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/vocab.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/tokenizer_config.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/tokenizer.json
bbchicago-test-lora-blac-1874-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-blac-1874-v2_reward/reward.tensors
Job bbchicago-test-lora-blac-1874-v2-mkmlizer completed after 62.46s with status: succeeded
Stopping job with name bbchicago-test-lora-blac-1874-v2-mkmlizer
Pipeline stage MKMLizer completed in 65.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-blac-1874-v2
Waiting for inference service bbchicago-test-lora-blac-1874-v2 to be ready
Inference service bbchicago-test-lora-blac-1874-v2 ready after 30.170643091201782s
Pipeline stage ISVCDeployer completed in 37.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0334877967834473s
Received healthy response to inference request in 1.2175421714782715s
Received healthy response to inference request in 1.2252309322357178s
Received healthy response to inference request in 1.2380459308624268s
Received healthy response to inference request in 1.2063543796539307s
5 requests
0 failed requests
5th percentile: 1.2085919380187988
10th percentile: 1.210829496383667
20th percentile: 1.2153046131134033
30th percentile: 1.2190799236297607
40th percentile: 1.2221554279327393
50th percentile: 1.2252309322357178
60th percentile: 1.2303569316864014
70th percentile: 1.235482931137085
80th percentile: 1.397134304046631
90th percentile: 1.715311050415039
95th percentile: 1.874399423599243
99th percentile: 2.0016701221466064
mean time: 1.3841322422027589
Pipeline stage StressChecker completed in 7.52s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-test-lora-blac_1874_v2 status is now deployed due to DeploymentManager action
bbchicago-test-lora-blac_1874_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics