submission_id: bbchicago-brt-8b-l3-v0-4_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Brt-8B-L3_v0.4
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: 2024-06-07T09:15:05+00:00
model_name: bbchicago-brt-8b-l3-v0-4_v1
model_eval_status: success
model_group: BBChicago/Brt-8B-L3_v0.4
num_battles: 11932
num_wins: 6413
celo_rating: 1216.97
safety_score: 0.82
propriety_score: 0.6370967741935484
propriety_total_count: 744.0
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-v0-4_v1
ineligible_reason: propriety_total_count < 5000
language_model: BBChicago/Brt-8B-L3_v0.4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-07
win_ratio: 0.5374622862889709
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v0-4-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v0-4-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Downloaded to shared memory in 43.550s
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:21, 2.36s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:10, 3.93it/s] Loading 0: 10%|▉ | 28/291 [00:04<00:27, 9.40it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 15.90it/s] Loading 0: 19%|█▉ | 55/291 [00:05<00:09, 24.79it/s] Loading 0: 23%|██▎ | 67/291 [00:05<00:08, 25.87it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.47it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:04, 48.09it/s] Loading 0: 36%|███▋ | 106/291 [00:05<00:03, 57.67it/s] Loading 0: 42%|████▏ | 122/291 [00:05<00:02, 72.70it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 88.15it/s] Loading 0: 52%|█████▏ | 152/291 [00:06<00:01, 95.32it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 68.76it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 75.10it/s] Loading 0: 66%|██████▋ | 193/291 [00:06<00:01, 90.19it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:00, 94.57it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 106.63it/s] Loading 0: 80%|████████ | 233/291 [00:07<00:00, 108.75it/s] Loading 0: 85%|████████▍ | 247/291 [00:07<00:00, 115.90it/s] Loading 0: 89%|████████▉ | 260/291 [00:07<00:00, 115.58it/s] Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 73.91it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 79.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: quantized model in 24.146s
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v0.4 in 70.148s
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-4-v1
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-4-v1/config.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-4-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-4-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-4-v1/tokenizer.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v0-4-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v0-4-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-v0-4-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-4-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-v0-4-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-4-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-brt-8b-l3-v0-4-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v0-4-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-v0-4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Saving duration: 0.573s
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 30.060s
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/config.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/merges.txt
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/vocab.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v0-4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v0-4-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v0-4-v1-mkmlizer completed after 155.45s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v0-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 160.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v0-4-v1
Waiting for inference service bbchicago-brt-8b-l3-v0-4-v1 to be ready
Inference service bbchicago-brt-8b-l3-v0-4-v1 ready after 30.165290117263794s
Pipeline stage ISVCDeployer completed in 37.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.100041389465332s
Received healthy response to inference request in 11.481163024902344s
Received healthy response to inference request in 1.2692406177520752s
Received healthy response to inference request in 1.2624685764312744s
Received healthy response to inference request in 1.3083863258361816s
5 requests
0 failed requests
5th percentile: 1.2638229846954345
10th percentile: 1.2651773929595946
20th percentile: 1.267886209487915
30th percentile: 1.2770697593688964
40th percentile: 1.2927280426025392
50th percentile: 1.3083863258361816
60th percentile: 1.6250483512878418
70th percentile: 1.9417103767395019
80th percentile: 3.976265716552736
90th percentile: 7.728714370727539
95th percentile: 9.60493869781494
99th percentile: 11.105918159484863
mean time: 3.4842599868774413
Pipeline stage StressChecker completed in 18.01s
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-brt-8b-l3-v0-4_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v0-4_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics