submission_id: bbchicago-brt-8b-l3-v1-_4895_v28
developer_uid: Bbbrun0
best_of: 16
celo_rating: 1230.6
display_name: brt-v1_7-dpo-s2500-cf
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n### Instruction:\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '### Input:\n{prompt}<START>\n<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n### Response:\n{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-cf
model_num_parameters: 8030261248.0
model_repo: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500
model_size: 8B
num_battles: 10707
num_wins: 5873
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: 2024-07-25T08:13:08+00:00
us_pacific_date: 2024-07-25
win_ratio: 0.5485196600354908
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ Version: 0.9.7 ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Downloaded to shared memory in 37.609s
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphfwaby20, device:0
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v28
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v28/config.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v28/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v28/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v28/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v28/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.76it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:08, 33.81it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 30.73it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:08, 33.31it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:08, 31.42it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:07, 33.61it/s] Loading 0: 11%|█▏ | 33/291 [00:01<00:10, 23.79it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:11, 21.52it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 23.50it/s] Loading 0: 16%|█▌ | 46/291 [00:01<00:08, 28.34it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:09, 26.40it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 33.02it/s] Loading 0: 21%|██ | 61/291 [00:02<00:07, 31.32it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 32.82it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:07, 31.16it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 31.13it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 30.86it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 21.42it/s] Loading 0: 29%|██▉ | 85/291 [00:03<00:09, 22.72it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 26.44it/s] Loading 0: 32%|███▏ | 93/291 [00:03<00:08, 24.63it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 29.94it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 29.37it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 31.30it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 30.02it/s] Loading 0: 40%|███▉ | 116/291 [00:04<00:05, 30.57it/s] Loading 0: 42%|████▏ | 122/291 [00:04<00:04, 34.20it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:05, 32.56it/s] Loading 0: 45%|████▌ | 132/291 [00:04<00:04, 36.43it/s] Loading 0: 47%|████▋ | 136/291 [00:04<00:06, 23.51it/s] Loading 0: 48%|████▊ | 140/291 [00:04<00:06, 23.50it/s] Loading 0: 50%|████▉ | 145/291 [00:05<00:05, 28.40it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:05, 26.44it/s] Loading 0: 54%|█████▎ | 156/291 [00:05<00:04, 32.95it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 31.93it/s] Loading 0: 56%|█████▋ | 164/291 [00:05<00:03, 33.60it/s] Loading 0: 58%|█████▊ | 168/291 [00:05<00:04, 29.77it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 34.19it/s] Loading 0: 61%|██████ | 178/291 [00:06<00:03, 32.62it/s] Loading 0: 63%|██████▎ | 182/291 [00:06<00:03, 34.28it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:04, 24.69it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 22.17it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:04, 24.24it/s] Loading 0: 68%|██████▊ | 199/291 [00:06<00:03, 29.26it/s] Loading 0: 70%|██████▉ | 203/291 [00:07<00:03, 26.82it/s] Loading 0: 71%|███████▏ | 208/291 [00:07<00:02, 31.61it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:02, 28.80it/s] Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 35.02it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 33.07it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 32.60it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 32.36it/s] Loading 0: 81%|████████ | 235/291 [00:08<00:02, 23.49it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:02, 23.51it/s] Loading 0: 85%|████████▍ | 246/291 [00:08<00:01, 30.49it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 29.98it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 32.12it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:01, 30.94it/s] Loading 0: 91%|█████████ | 264/291 [00:09<00:00, 33.26it/s] Loading 0: 92%|█████████▏| 268/291 [00:09<00:00, 31.62it/s] Loading 0: 94%|█████████▍| 273/291 [00:09<00:00, 33.23it/s] Loading 0: 95%|█████████▌| 277/291 [00:09<00:00, 31.91it/s] Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 31.22it/s] Loading 0: 98%|█████████▊| 286/291 [00:15<00:01, 2.54it/s] Loading 0: 99%|█████████▉| 289/291 [00:15<00:00, 3.15it/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-v28-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v28-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-v28-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Saving duration: 1.418s
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.207s
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/config.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/merges.txt
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/vocab.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v28_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer completed after 167.58s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-4895-v28-mkmlizer
Pipeline stage MKMLizer completed in 168.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-4895-v28
Waiting for inference service bbchicago-brt-8b-l3-v1-4895-v28 to be ready
Inference service bbchicago-brt-8b-l3-v1-4895-v28 ready after 70.59184455871582s
Pipeline stage ISVCDeployer completed in 72.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2763025760650635s
Received healthy response to inference request in 1.496488332748413s
Received healthy response to inference request in 1.462538480758667s
Received healthy response to inference request in 1.4284007549285889s
Received healthy response to inference request in 1.394763469696045s
5 requests
0 failed requests
5th percentile: 1.4014909267425537
10th percentile: 1.4082183837890625
20th percentile: 1.42167329788208
30th percentile: 1.4352283000946044
40th percentile: 1.4488833904266358
50th percentile: 1.462538480758667
60th percentile: 1.4761184215545655
70th percentile: 1.4896983623504638
80th percentile: 1.6524511814117433
90th percentile: 1.9643768787384035
95th percentile: 2.120339727401733
99th percentile: 2.245110006332397
mean time: 1.6116987228393556
Pipeline stage StressChecker completed in 8.73s
bbchicago-brt-8b-l3-v1-_4895_v28 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-_4895_v28 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-_4895_v28
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-4895-v28 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-4895-v28
Service bbchicago-brt-8b-l3-v1-4895-v28 has been torndown
Pipeline stage ISVCDeleter completed in 4.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v28/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v28_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.45s
bbchicago-brt-8b-l3-v1-_4895_v28 status is now torndown due to DeploymentManager action