submission_id: bbchicago-brt-8b-l3-v0-3_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Brt-8B-L3_v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, '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: 2024-06-07T09:14:39+00:00
model_name: bbchicago-brt-8b-l3-v0-3_v1
model_eval_status: success
model_group: BBChicago/Brt-8B-L3_v0.3
num_battles: 11970
num_wins: 6351
celo_rating: 1212.7
propriety_score: 0.6612244897959184
propriety_total_count: 735.0
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-brt-8b-l3-v0-3_v1
ineligible_reason: propriety_total_count < 5000
language_model: BBChicago/Brt-8B-L3_v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-07
win_ratio: 0.5305764411027569
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v0-3-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v0-3-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v0-3-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-brt-8b-l3-v0-3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Downloaded to shared memory in 44.164s
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:11, 2.32s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:09, 3.98it/s] Loading 0: 10%|▉ | 28/291 [00:04<00:27, 9.50it/s] Loading 0: 14%|█▍ | 41/291 [00:04<00:15, 16.00it/s] Loading 0: 19%|█▊ | 54/291 [00:05<00:09, 24.17it/s] Loading 0: 23%|██▎ | 66/291 [00:05<00:08, 27.25it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:06, 34.95it/s] Loading 0: 31%|███ | 90/291 [00:05<00:04, 46.51it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 59.12it/s] Loading 0: 41%|████ | 118/291 [00:05<00:02, 72.73it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 81.61it/s] Loading 0: 49%|████▉ | 144/291 [00:06<00:01, 91.66it/s] Loading 0: 54%|█████▍ | 157/291 [00:06<00:01, 100.45it/s] Loading 0: 58%|█████▊ | 170/291 [00:06<00:01, 67.05it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 79.73it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:01, 84.67it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:00, 100.91it/s] Loading 0: 77%|███████▋ | 224/291 [00:06<00:00, 105.41it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 111.76it/s] Loading 0: 87%|████████▋ | 254/291 [00:07<00:00, 121.47it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 75.63it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 88.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: quantized model in 23.499s
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v0.3 in 70.135s
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-3-v1
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-3-v1/config.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-3-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-3-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-3-v1/tokenizer.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-3-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v0-3-v1-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-brt-8b-l3-v0-3-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-3-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-brt-8b-l3-v0-3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Saving duration: 0.384s
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 17.392s
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/config.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/merges.txt
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/vocab.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v0-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-3-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v0-3-v1-mkmlizer completed after 123.88s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v0-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v0-3-v1
Waiting for inference service bbchicago-brt-8b-l3-v0-3-v1 to be ready
Inference service bbchicago-brt-8b-l3-v0-3-v1 ready after 70.33383131027222s
Pipeline stage ISVCDeployer completed in 77.69s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2174696922302246s
Received healthy response to inference request in 1.2762298583984375s
Received healthy response to inference request in 1.2550380229949951s
Received healthy response to inference request in 1.2641818523406982s
Received healthy response to inference request in 1.2934105396270752s
5 requests
0 failed requests
5th percentile: 1.2568667888641358
10th percentile: 1.2586955547332763
20th percentile: 1.2623530864715575
30th percentile: 1.266591453552246
40th percentile: 1.2714106559753418
50th percentile: 1.2762298583984375
60th percentile: 1.2831021308898927
70th percentile: 1.2899744033813476
80th percentile: 1.4782223701477053
90th percentile: 1.8478460311889648
95th percentile: 2.0326578617095947
99th percentile: 2.1805073261260985
mean time: 1.461265993118286
Pipeline stage StressChecker completed in 8.22s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-brt-8b-l3-v0-3_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v0-3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics