submission_id: bbchicago-test-lora-004_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Test_Lora_004
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: 2024-06-13T04:20:57+00:00
model_name: bbchicago-test-lora-004_v1
model_eval_status: success
model_group: BBChicago/Test_Lora_004
num_battles: 24207
num_wins: 12432
celo_rating: 1190.59
propriety_score: 0.6765519214265281
propriety_total_count: 10487.0
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-004_v1
ineligible_reason: None
language_model: BBChicago/Test_Lora_004
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.5135704548271162
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-004-v1-mkmlizer
Waiting for job on bbchicago-test-lora-004-v1-mkmlizer to finish
bbchicago-test-lora-004-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-004-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-test-lora-004-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-lora-004-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-lora-004-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-lora-004-v1-mkmlizer: ║ /___/ ║
bbchicago-test-lora-004-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-lora-004-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-lora-004-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-lora-004-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-lora-004-v1-mkmlizer: ║ belonging to: ║
bbchicago-test-lora-004-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-lora-004-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-lora-004-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-lora-004-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-004-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.
bbchicago-test-lora-004-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-004-v1-mkmlizer: Downloaded to shared memory in 34.235s
bbchicago-test-lora-004-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-004-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-004-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 132.29it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 149.48it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 153.20it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 156.45it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 81.15it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 98.20it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 112.81it/s] Loading 0: 47%|████▋ | 136/291 [00:01<00:01, 123.66it/s] Loading 0: 52%|█████▏ | 151/291 [00:01<00:01, 129.12it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 133.18it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 88.89it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 97.99it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 111.78it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 124.37it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 134.74it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 142.43it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.75it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-004-v1-mkmlizer: quantized model in 23.365s
bbchicago-test-lora-004-v1-mkmlizer: Processed model BBChicago/Test_Lora_004 in 60.260s
bbchicago-test-lora-004-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-004-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-004-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-004-v1
bbchicago-test-lora-004-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-004-v1/config.json
bbchicago-test-lora-004-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-004-v1/tokenizer_config.json
bbchicago-test-lora-004-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-004-v1/tokenizer.json
bbchicago-test-lora-004-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-004-v1/special_tokens_map.json
bbchicago-test-lora-004-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-004-v1/flywheel_model.0.safetensors
bbchicago-test-lora-004-v1-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-004-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-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()
bbchicago-test-lora-004-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-lora-004-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-004-v1-mkmlizer: Saving duration: 0.418s
bbchicago-test-lora-004-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.907s
bbchicago-test-lora-004-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-004-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-004-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/config.json
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/tokenizer_config.json
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/merges.txt
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/special_tokens_map.json
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/vocab.json
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/tokenizer.json
bbchicago-test-lora-004-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-004-v1_reward/reward.tensors
Job bbchicago-test-lora-004-v1-mkmlizer completed after 83.35s with status: succeeded
Stopping job with name bbchicago-test-lora-004-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-004-v1
Waiting for inference service bbchicago-test-lora-004-v1 to be ready
Inference service bbchicago-test-lora-004-v1 ready after 40.220635652542114s
Pipeline stage ISVCDeployer completed in 47.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.146805763244629s
Received healthy response to inference request in 1.268937587738037s
Received healthy response to inference request in 1.2772841453552246s
Received healthy response to inference request in 1.2698609828948975s
Received healthy response to inference request in 1.2499027252197266s
5 requests
0 failed requests
5th percentile: 1.2537096977233886
10th percentile: 1.2575166702270508
20th percentile: 1.265130615234375
30th percentile: 1.269122266769409
40th percentile: 1.2694916248321533
50th percentile: 1.2698609828948975
60th percentile: 1.2728302478790283
70th percentile: 1.2757995128631592
80th percentile: 1.4511884689331056
90th percentile: 1.7989971160888674
95th percentile: 1.972901439666748
99th percentile: 2.112024898529053
mean time: 1.4425582408905029
Pipeline stage StressChecker completed in 7.83s
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-004_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-004_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics