submission_id: bbchicago-brt-8b-l3-v1-_4895_v30
developer_uid: Bbbrun0
alignment_samples: 0
best_of: 4
celo_rating: 1205.2
display_name: brt-v1_7-dpo-s2500-best4
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': 4, '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-best4
model_num_parameters: 8030261248.0
model_repo: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500
model_size: 8B
num_battles: 10701
num_wins: 5333
propriety_score: 0.7393162393162394
propriety_total_count: 936.0
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: 2024-07-26T08:44:11+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.498364638818802
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer to finish
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ Version: 0.9.7 ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Downloaded to shared memory in 40.190s
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3b8lwtau, device:0
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: quantized model in 28.197s
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500 in 68.387s
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v30
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v30/config.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v30/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v30/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v30/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v30/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.68it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 43.06it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 39.43it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 39.23it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 41.59it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 40.81it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:09, 26.58it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.22it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 34.18it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.93it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 35.91it/s] Loading 0: 22%|██▏ | 63/291 [00:01<00:05, 38.57it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:06, 33.21it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:05, 38.61it/s] Loading 0: 27%|██▋ | 79/291 [00:02<00:05, 35.69it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:08, 24.76it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 32.48it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 33.82it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 35.04it/s] Loading 0: 36%|███▌ | 105/291 [00:03<00:04, 37.71it/s] Loading 0: 38%|███▊ | 110/291 [00:03<00:05, 32.13it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 36.86it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 40.10it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 37.87it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 32.28it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 32.36it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 30.25it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 35.07it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 34.17it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.83it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 35.37it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.93it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 36.30it/s] Loading 0: 60%|█████▉ | 174/291 [00:04<00:03, 38.36it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 36.28it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 42.18it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.56it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.05it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 32.51it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 32.05it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.81it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.22it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 35.54it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 34.67it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 35.01it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 34.63it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.84it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.13it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 32.73it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.31it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.35it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 34.37it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 37.22it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 35.13it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.43it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.38it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.76it/s] Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.58it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<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-v30-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v30-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-v30-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v30-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-v30-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Saving duration: 1.395s
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.864s
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/config.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/merges.txt
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/vocab.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v30_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer completed after 115.45s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-4895-v30-mkmlizer
Pipeline stage MKMLizer completed in 116.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-4895-v30
Waiting for inference service bbchicago-brt-8b-l3-v1-4895-v30 to be ready
Inference service bbchicago-brt-8b-l3-v1-4895-v30 ready after 81.0722062587738s
Pipeline stage ISVCDeployer completed in 82.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9688458442687988s
Received healthy response to inference request in 1.1465284824371338s
Received healthy response to inference request in 1.139127254486084s
Received healthy response to inference request in 1.1428227424621582s
Received healthy response to inference request in 1.119250774383545s
5 requests
0 failed requests
5th percentile: 1.1232260704040526
10th percentile: 1.1272013664245606
20th percentile: 1.1351519584655763
30th percentile: 1.1398663520812988
40th percentile: 1.1413445472717285
50th percentile: 1.1428227424621582
60th percentile: 1.1443050384521485
70th percentile: 1.1457873344421388
80th percentile: 1.310991954803467
90th percentile: 1.639918899536133
95th percentile: 1.8043823719024656
99th percentile: 1.9359531497955322
mean time: 1.303315019607544
Pipeline stage StressChecker completed in 7.18s
bbchicago-brt-8b-l3-v1-_4895_v30 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-_4895_v30 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-_4895_v30
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-4895-v30 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-4895-v30
Service bbchicago-brt-8b-l3-v1-4895-v30 has been torndown
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v30/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v30_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.65s
bbchicago-brt-8b-l3-v1-_4895_v30 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics