submission_id: bbchicago-brt-8b-l3-v1-9_2176_v3
developer_uid: Bbbrun0
alignment_samples: 11841
alignment_score: 0.4074908403875638
best_of: 16
celo_rating: 1250.49
display_name: bbchicago-brt-8b-l3-v1-9_2176_v3
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: BBChicago/Brt-8B-L3_v1.9_with_dpo_lora_s5900
latencies: [{'batch_size': 1, 'throughput': 0.9023399556893698, 'latency_mean': 1.1081257843971253, 'latency_p50': 1.121473789215088, 'latency_p90': 1.2125359535217284}, {'batch_size': 4, 'throughput': 1.8216440967032852, 'latency_mean': 2.1845349514484407, 'latency_p50': 2.1690679788589478, 'latency_p90': 2.4459200620651247}, {'batch_size': 5, 'throughput': 1.912478160303823, 'latency_mean': 2.600224437713623, 'latency_p50': 2.6263976097106934, 'latency_p90': 2.8902822017669676}, {'batch_size': 8, 'throughput': 2.011627245227434, 'latency_mean': 3.9467742896080016, 'latency_p50': 3.9693976640701294, 'latency_p90': 4.417066192626953}, {'batch_size': 10, 'throughput': 2.047638223918485, 'latency_mean': 4.836660273075104, 'latency_p50': 4.793946623802185, 'latency_p90': 5.677063345909119}, {'batch_size': 12, 'throughput': 2.05315275677152, 'latency_mean': 5.761261956691742, 'latency_p50': 5.740974545478821, 'latency_p90': 6.692778658866882}, {'batch_size': 15, 'throughput': 2.0478578148720774, 'latency_mean': 7.17384488940239, 'latency_p50': 7.252038359642029, 'latency_p90': 7.980904364585877}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: BBChicago/Brt-8B-L3_v1.9
model_name: bbchicago-brt-8b-l3-v1-9_2176_v3
model_num_parameters: 8030261248.0
model_repo: BBChicago/Brt-8B-L3_v1.9_with_dpo_lora_s5900
model_size: 8B
num_battles: 11841
num_wins: 6011
propriety_score: 0.7085828343313373
propriety_total_count: 1002.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.01
timestamp: 2024-09-13T02:02:51+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.5076429355628748
Download Preference Data
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer to finish
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ Version: 0.10.1 ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: Downloaded to shared memory in 85.698s
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_gqsvk1p, device:0
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: quantized model in 29.089s
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.9_with_dpo_lora_s5900 in 114.788s
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-2176-v3
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-2176-v3/config.json
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-2176-v3/tokenizer_config.json
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-2176-v3/special_tokens_map.json
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-2176-v3/tokenizer.json
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-2176-v3/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 24.18it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:08, 34.02it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.08it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.19it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 33.31it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:07, 35.01it/s] Loading 0: 11%|█▏ | 33/291 [00:01<00:10, 25.22it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:11, 22.74it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 24.77it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.35it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.63it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.26it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 32.65it/s] Loading 0: 22%|██▏ | 65/291 [00:02<00:06, 34.16it/s] Loading 0: 24%|██▎ | 69/291 [00:02<00:07, 30.50it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.84it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.38it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 25.29it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 27.76it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:06, 30.51it/s] Loading 0: 33%|███▎ | 95/291 [00:03<00:06, 32.00it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.46it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.13it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.47it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 31.75it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.21it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.43it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 34.53it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.44it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.69it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.26it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.76it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.12it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.08it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.38it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 34.79it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.51it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.90it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.54it/s] Loading 0: 63%|██████▎ | 182/291 [00:05<00:03, 35.87it/s] Loading 0: 64%|██████▍ | 186/291 [00:05<00:03, 28.11it/s] Loading 0: 65%|██████▌ | 190/291 [00:06<00:03, 26.46it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.77it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.53it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.33it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.23it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.39it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.11it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:01, 35.23it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 35.76it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 36.06it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 27.05it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.42it/s] Loading 0: 84%|████████▍ | 244/291 [00:07<00:01, 30.48it/s] Loading 0: 85%|████████▌ | 248/291 [00:07<00:01, 28.02it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 35.89it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 34.42it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.07it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 33.05it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 33.78it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 32.64it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 32.08it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.20it/s]
Job bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer completed after 135.76s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-9-2176-v3-mkmlizer
Pipeline stage MKMLizer completed in 138.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service bbchicago-brt-8b-l3-v1-9-2176-v3
Waiting for inference service bbchicago-brt-8b-l3-v1-9-2176-v3 to be ready
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
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
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service bbchicago-brt-8b-l3-v1-9-2176-v3 ready after 170.66966152191162s
Pipeline stage MKMLDeployer completed in 171.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2651987075805664s
Received healthy response to inference request in 1.388094425201416s
Received healthy response to inference request in 1.5980913639068604s
Received healthy response to inference request in 1.5768451690673828s
Received healthy response to inference request in 1.4930353164672852s
5 requests
0 failed requests
5th percentile: 1.4090826034545898
10th percentile: 1.4300707817077636
20th percentile: 1.4720471382141114
30th percentile: 1.5097972869873046
40th percentile: 1.5433212280273438
50th percentile: 1.5768451690673828
60th percentile: 1.5853436470031739
70th percentile: 1.593842124938965
80th percentile: 1.7315128326416016
90th percentile: 1.9983557701110841
95th percentile: 2.131777238845825
99th percentile: 2.238514413833618
mean time: 1.6642529964447021
Pipeline stage StressChecker completed in 9.10s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.31s
Shutdown handler de-registered
bbchicago-brt-8b-l3-v1-9_2176_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service bbchicago-brt-8b-l3-v1-9-2176-v3-profiler
Waiting for inference service bbchicago-brt-8b-l3-v1-9-2176-v3-profiler to be ready
Inference service bbchicago-brt-8b-l3-v1-9-2176-v3-profiler ready after 180.42860889434814s
Pipeline stage MKMLProfilerDeployer completed in 181.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/bbchicago-brt-8b-l3-c8d2069233dda5387e9ba680ace42312-deplock4mf:/code/chaiverse_profiler_1726193520 --namespace tenant-chaiml-guanaco
kubectl exec -it bbchicago-brt-8b-l3-c8d2069233dda5387e9ba680ace42312-deplock4mf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726193520 && python profiles.py profile --best_of_n 16 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726193520/summary.json'
kubectl exec -it bbchicago-brt-8b-l3-c8d2069233dda5387e9ba680ace42312-deplock4mf --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726193520/summary.json'
Pipeline stage MKMLProfilerRunner completed in 833.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service bbchicago-brt-8b-l3-v1-9-2176-v3-profiler is running
Tearing down inference service bbchicago-brt-8b-l3-v1-9-2176-v3-profiler
Service bbchicago-brt-8b-l3-v1-9-2176-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
bbchicago-brt-8b-l3-v1-9_2176_v3 status is now inactive due to auto deactivation removed underperforming models