submission_id: bbchicago-brt-8b-l3-v1-3_6714_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Brt-8B-L3_v1.3-DPO_v4.0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, '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: 2024-07-02T04:28:56+00:00
model_name: bbchicago-brt-8b-l3-v1-3_6714_v1
model_group: BBChicago/Brt-8B-L3_v1.3
num_battles: 11791
num_wins: 6510
celo_rating: 1210.38
propriety_score: 0.707716155700999
propriety_total_count: 5806.0
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_6714_v1
ineligible_reason: None
language_model: BBChicago/Brt-8B-L3_v1.3-DPO_v4.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.5521160206937494
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission neversleep-noromaid-v0-_8068_v107: no entry with id "neversleep-noromaid-v0-_8068_v107" found on database!
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Downloaded to shared memory in 47.361s
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission neversleep-noromaid-v0-_8068_v106: no entry with id "neversleep-noromaid-v0-_8068_v106" found on database!
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:29, 2.39s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:06, 4.18it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:38, 6.94it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 15.84it/s] Loading 0: 20%|██ | 59/291 [00:05<00:08, 26.99it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:06, 32.94it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 44.84it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 52.13it/s] Loading 0: 40%|████ | 117/291 [00:05<00:02, 63.93it/s] Loading 0: 45%|████▌ | 132/291 [00:06<00:02, 77.49it/s] Loading 0: 50%|████▉ | 145/291 [00:06<00:01, 73.13it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 84.47it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 102.15it/s] Loading 0: 65%|██████▌ | 190/291 [00:06<00:01, 85.04it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 95.40it/s] Loading 0: 76%|███████▋ | 222/291 [00:07<00:00, 86.23it/s] Loading 0: 82%|████████▏ | 240/291 [00:07<00:00, 101.91it/s] Loading 0: 89%|████████▊ | 258/291 [00:07<00:00, 116.47it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 99.40it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 105.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: quantized model in 24.076s
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.3-DPO_v4.0 in 71.437s
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6714-v1
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6714-v1/config.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6714-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6714-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6714-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6714-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-3-6714-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-v1-3-6714-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-6714-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-v1-3-6714-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Saving duration: 1.376s
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.078s
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/config.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6714-v1_reward/reward.tensors
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
Job bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer completed after 158.22s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-3-6714-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.28s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-3-6714-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-3-6714-v1 to be ready
Failed to get response for submission neversleep-noromaid-v0-_8068_v108: no entry with id "neversleep-noromaid-v0-_8068_v108" found on database!
Connection pool is full, discarding connection: %s
Inference service bbchicago-brt-8b-l3-v1-3-6714-v1 ready after 50.2142436504364s
Pipeline stage ISVCDeployer completed in 56.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.113161325454712s
Received healthy response to inference request in 1.3139808177947998s
Received healthy response to inference request in 1.3386898040771484s
Received healthy response to inference request in 1.298607587814331s
Received healthy response to inference request in 1.2579851150512695s
5 requests
0 failed requests
5th percentile: 1.2661096096038817
10th percentile: 1.2742341041564942
20th percentile: 1.2904830932617188
30th percentile: 1.3016822338104248
40th percentile: 1.3078315258026123
50th percentile: 1.3139808177947998
60th percentile: 1.3238644123077392
70th percentile: 1.3337480068206786
80th percentile: 1.4935841083526613
90th percentile: 1.8033727169036866
95th percentile: 1.958267021179199
99th percentile: 2.0821824645996094
mean time: 1.4644849300384521
Pipeline stage StressChecker completed in 8.98s
bbchicago-brt-8b-l3-v1-3_6714_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-3_6714_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics