submission_id: bbchicago-brt-8b-l3-v1-3-dpo_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Brt-8B-L3_v1.3-DPO
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.08, '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: 2024-06-27T04:14:09+00:00
model_name: bbchicago-brt-8b-l3-v1-3-dpo_v1
model_group: BBChicago/Brt-8B-L3_v1.3
num_battles: 26865
num_wins: 14594
celo_rating: 1212.93
propriety_score: 0.6830693526064893
propriety_total_count: 13006.0
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-v1-3-dpo_v1
ineligible_reason: None
language_model: BBChicago/Brt-8B-L3_v1.3-DPO
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-26
win_ratio: 0.5432346919784106
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-3-dpo-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-v1-3-dpo-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Downloaded to shared memory in 34.806s
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:01, 138.94it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 156.56it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 162.43it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 164.23it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.81it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 106.60it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 121.30it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 133.22it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 142.00it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 153.54it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 89.17it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 96.32it/s] Loading 0: 77%|███████▋ | 223/291 [00:01<00:00, 111.30it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 121.56it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 133.30it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 143.91it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.71it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: quantized model in 23.071s
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.3-DPO in 60.341s
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-dpo-v1
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-dpo-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-dpo-v1/config.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-dpo-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-dpo-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-dpo-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-3-dpo-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-v1-3-dpo-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-dpo-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-v1-3-dpo-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Saving duration: 0.434s
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.217s
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/config.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-dpo-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer completed after 83.92s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-3-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.98s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-3-dpo-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-3-dpo-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-3-dpo-v1 ready after 40.282835960388184s
Pipeline stage ISVCDeployer completed in 47.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0479094982147217s
Received healthy response to inference request in 1.2726798057556152s
Received healthy response to inference request in 1.2591454982757568s
Received healthy response to inference request in 1.252558946609497s
Received healthy response to inference request in 1.3281612396240234s
5 requests
0 failed requests
5th percentile: 1.253876256942749
10th percentile: 1.255193567276001
20th percentile: 1.2578281879425048
30th percentile: 1.2618523597717286
40th percentile: 1.267266082763672
50th percentile: 1.2726798057556152
60th percentile: 1.2948723793029786
70th percentile: 1.3170649528503418
80th percentile: 1.4721108913421632
90th percentile: 1.7600101947784426
95th percentile: 1.903959846496582
99th percentile: 2.0191195678710936
mean time: 1.4320909976959229
Pipeline stage StressChecker completed in 8.06s
bbchicago-brt-8b-l3-v1-3-dpo_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-3-dpo_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics