developer_uid: Bbbrun0
submission_id: bbchicago-brt-8b-l3-v1-6_3543_v1
model_name: bbchicago-brt-v1_6-dpo-s4500
model_group: BBChicago/Brt-8B-L3_v1.6
status: torndown
timestamp: 2024-07-18T04:58:11+00:00
num_battles: 14503
num_wins: 7830
celo_rating: 1218.93
family_friendly_score: 0.0
submission_type: basic
model_repo: BBChicago/Brt-8B-L3_v1.6_DPO_steps_4500
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bbchicago-brt-v1_6-dpo-s4500
is_internal_developer: False
language_model: BBChicago/Brt-8B-L3_v1.6_DPO_steps_4500
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-17
win_ratio: 0.5398882989726264
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], '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: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  Version: 0.9.5.post3                                               ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Downloaded to shared memory in 27.772s
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8g3gaabt, device:0
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 124.00it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 149.43it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:01, 155.54it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 158.10it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 78.76it/s] 
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 86.07it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 103.20it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 116.46it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 126.98it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:00, 135.84it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 137.73it/s]
Loading 0:  67%|██████▋   | 196/291 [00:01<00:01, 80.20it/s] 
Loading 0:  73%|███████▎  | 212/291 [00:01<00:00, 92.95it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 108.21it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 121.58it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 131.27it/s]
Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 137.38it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: quantized model in 23.694s
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.6_DPO_steps_4500 in 51.466s
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-3543-v1
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-3543-v1/config.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-3543-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-3543-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-3543-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Saving duration: 1.700s
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.907s
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/config.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-3543-v1_reward/reward.tensors
Failed to get response for submission hastagaras-dirtybu8bl3-r_5954_v3: ('http://hastagaras-dirtybu8bl3-r-5954-v3-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Job bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer completed after 98.69s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-6-3543-v1-mkmlizer
Pipeline stage MKMLizer completed in 99.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-6-3543-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-6-3543-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-6-3543-v1 ready after 31.280306100845337s
Pipeline stage ISVCDeployer completed in 33.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.242656946182251s
Received healthy response to inference request in 1.4147813320159912s
Received healthy response to inference request in 1.3872458934783936s
Received healthy response to inference request in 1.4442968368530273s
Received healthy response to inference request in 1.4334533214569092s
5 requests
0 failed requests
5th percentile: 1.3927529811859132
10th percentile: 1.3982600688934326
20th percentile: 1.4092742443084716
30th percentile: 1.4185157299041748
40th percentile: 1.425984525680542
50th percentile: 1.4334533214569092
60th percentile: 1.4377907276153565
70th percentile: 1.4421281337738037
80th percentile: 1.6039688587188723
90th percentile: 1.9233129024505615
95th percentile: 2.0829849243164062
99th percentile: 2.210722541809082
mean time: 1.5844868659973144
Pipeline stage StressChecker completed in 8.71s
bbchicago-brt-8b-l3-v1-6_3543_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-6_3543_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-6_3543_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-6-3543-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-6-3543-v1
Service bbchicago-brt-8b-l3-v1-6-3543-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.15s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-3543-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.54s
bbchicago-brt-8b-l3-v1-6_3543_v1 status is now torndown due to DeploymentManager action