bbchicago-brt-8b-l3-v1-7_4895

developer_uid: Bbbrun0

submission_id: bbchicago-brt-8b-l3-v1-7_4895_v2

model_name: bbchicago-brt-v1_7-dpo-s2500

model_group: BBChicago/Brt-8B-L3_v1.7

status: torndown

timestamp: 2024-07-19T04:32:29+00:00

num_battles: 65580

num_wins: 33482

celo_rating: 1235.31

family_friendly_score: 0.0

submission_type: basic

model_repo: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500

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_7-dpo-s2500

is_internal_developer: False

language_model: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-18

win_ratio: 0.5105519975602317

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-v1-7-4895-v2-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer to finish
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║     _____            __           __                                ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║       /___/                                                         ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  Version: 0.9.5.post3                                               ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  belonging to:                                                      ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: Downloaded to shared memory in 49.771s
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfe2ojgn7, device:0
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 40.10it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 60.58it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:03, 68.88it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:03, 71.70it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:08, 30.25it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:07, 34.57it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:06, 38.68it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 47.05it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 53.96it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:03, 57.47it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:06, 31.36it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:05, 34.68it/s]
Loading 0:  32%|███▏      | 92/291 [00:02<00:05, 37.51it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 45.81it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 53.07it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 57.01it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 58.01it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:02, 58.88it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:05, 30.79it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:04, 33.27it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 39.21it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:02, 46.02it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 51.58it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 57.51it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 37.92it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 36.26it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:02, 39.62it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 39.85it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.91it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 52.21it/s]
Loading 0:  77%|███████▋  | 225/291 [00:05<00:01, 53.14it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 53.51it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 27.35it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 32.30it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 34.25it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 42.23it/s]
Loading 0:  91%|█████████ | 264/291 [00:06<00:00, 49.24it/s]
Loading 0:  93%|█████████▎| 270/291 [00:06<00:00, 44.27it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 43.50it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  3.19it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: quantized model in 33.688s
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500 in 83.459s
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')
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-7-4895-v2/special_tokens_map.json
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-7-4895-v2/tokenizer_config.json
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-7-4895-v2/tokenizer.json
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-7-4895-v2/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-7-4895-v2-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-v1-7-4895-v2-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-7-4895-v2-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-v1-7-4895-v2-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-7-4895-v2-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-v1-7-4895-v2-mkmlizer:   warnings.warn(
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')
bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer: Saving model to /tmp/reward_cache/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-v1-7-4895-v2-mkmlizer completed after 164.7s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-7-4895-v2-mkmlizer
Pipeline stage MKMLizer completed in 166.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-7-4895-v2
Waiting for inference service bbchicago-brt-8b-l3-v1-7-4895-v2 to be ready
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')
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')
Inference service bbchicago-brt-8b-l3-v1-7-4895-v2 ready after 82.5040955543518s
Pipeline stage ISVCDeployer completed in 84.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.224045753479004s
Received healthy response to inference request in 1.4260303974151611s
Received healthy response to inference request in 1.4286091327667236s
Received healthy response to inference request in 1.3964028358459473s
Received healthy response to inference request in 1.3768236637115479s
5 requests
0 failed requests
5th percentile: 1.3807394981384278
10th percentile: 1.3846553325653077
20th percentile: 1.3924870014190673
30th percentile: 1.4023283481597901
40th percentile: 1.4141793727874756
50th percentile: 1.4260303974151611
60th percentile: 1.4270618915557862
70th percentile: 1.428093385696411
80th percentile: 1.5876964569091798
90th percentile: 1.905871105194092
95th percentile: 2.0649584293365475
99th percentile: 2.1922282886505124
mean time: 1.5703823566436768
Pipeline stage StressChecker completed in 8.50s
bbchicago-brt-8b-l3-v1-7_4895_v2 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-7_4895_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-7_4895_v2
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-7-4895-v2 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-7-4895-v2
Service bbchicago-brt-8b-l3-v1-7-4895-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-7-4895-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.90s
bbchicago-brt-8b-l3-v1-7_4895_v2 status is now torndown due to DeploymentManager action