submission_id: bbchicago-brt-8b-l3-v1-_4895_v32
developer_uid: Bbbrun0
alignment_samples: 0
best_of: 16
celo_rating: 1242.06
display_name: brt-v1_7-dpo-s2500-b16-pair
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}
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, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: BBChicago/Brt-8B-L3_v1.7
model_name: brt-v1_7-dpo-s2500-b16-pair
model_num_parameters: 8030261248.0
model_repo: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500
model_size: 8B
num_battles: 11770
num_wins: 6525
propriety_score: 0.7273622047244095
propriety_total_count: 1016.0
ranking_group: single
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'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-26T08:48:36+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.554375531011045
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer to finish
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ Version: 0.9.7 ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Downloaded to shared memory in 38.884s
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe0ju7p4r, device:0
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: quantized model in 28.557s
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500 in 67.442s
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v32
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v32/config.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v32/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v32/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v32/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v32/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.64it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 42.68it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 39.22it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:07, 38.38it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:06, 38.08it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 38.92it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 24.48it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.84it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 34.70it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.40it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 35.00it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 34.14it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 37.06it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.54it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 35.79it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:05, 35.97it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.59it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 25.53it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.40it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 29.36it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.73it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.44it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.55it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.68it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.94it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.41it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.04it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.36it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.76it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.25it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.15it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.58it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.41it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.05it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 35.05it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.29it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 35.51it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.07it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 39.64it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.30it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.86it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.34it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.62it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.00it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.32it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.80it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.07it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 33.41it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.70it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.17it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.42it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.22it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.49it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.37it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 34.34it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.88it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.16it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.82it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.40it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.41it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.21it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v32-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-v1-4895-v32-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Saving duration: 1.425s
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.910s
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/config.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/merges.txt
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/vocab.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v32_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer completed after 105.97s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-4895-v32-mkmlizer
Pipeline stage MKMLizer completed in 106.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-4895-v32
Waiting for inference service bbchicago-brt-8b-l3-v1-4895-v32 to be ready
Inference service bbchicago-brt-8b-l3-v1-4895-v32 ready after 80.56070613861084s
Pipeline stage ISVCDeployer completed in 82.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2839443683624268s
Received healthy response to inference request in 1.427670955657959s
Received healthy response to inference request in 1.3799805641174316s
Received healthy response to inference request in 1.4209260940551758s
Received healthy response to inference request in 1.4223854541778564s
5 requests
0 failed requests
5th percentile: 1.3881696701049804
10th percentile: 1.3963587760925293
20th percentile: 1.412736988067627
30th percentile: 1.421217966079712
40th percentile: 1.421801710128784
50th percentile: 1.4223854541778564
60th percentile: 1.4244996547698974
70th percentile: 1.4266138553619385
80th percentile: 1.5989256381988528
90th percentile: 1.9414350032806398
95th percentile: 2.112689685821533
99th percentile: 2.249693431854248
mean time: 1.5869814872741699
Pipeline stage StressChecker completed in 8.81s
bbchicago-brt-8b-l3-v1-_4895_v32 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-_4895_v32 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-_4895_v32
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-4895-v32 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-4895-v32
Service bbchicago-brt-8b-l3-v1-4895-v32 has been torndown
Pipeline stage ISVCDeleter completed in 5.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v32/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v32_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.78s
bbchicago-brt-8b-l3-v1-_4895_v32 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics