developer_uid: BBChicago
submission_id: bbchicago-tang82mv-flpc_99370_v1
model_name: tang82mv-flpchatai-591k-dpo-ep2
model_group: BBChicago/tang82mv-flpch
status: torndown
timestamp: 2025-05-12T03:21:02+00:00
num_battles: 8972
num_wins: 4529
celo_rating: 1289.11
family_friendly_score: 0.5442
family_friendly_standard_error: 0.00704338498166897
submission_type: basic
model_repo: BBChicago/tang82mv-flpchatai-591k-dpo-ep2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6118660126279452, 'latency_mean': 1.6342776250839233, 'latency_p50': 1.6202987432479858, 'latency_p90': 1.8339641571044922}, {'batch_size': 3, 'throughput': 1.11083283596114, 'latency_mean': 2.6894127309322355, 'latency_p50': 2.6928011178970337, 'latency_p90': 2.968413209915161}, {'batch_size': 5, 'throughput': 1.3343041065378285, 'latency_mean': 3.7267995154857636, 'latency_p50': 3.720669388771057, 'latency_p90': 4.113869404792785}, {'batch_size': 6, 'throughput': 1.397725661948086, 'latency_mean': 4.268420639038086, 'latency_p50': 4.286680340766907, 'latency_p90': 4.833266806602478}, {'batch_size': 8, 'throughput': 1.4736201101273065, 'latency_mean': 5.392509281635284, 'latency_p50': 5.367605686187744, 'latency_p90': 6.152643895149231}, {'batch_size': 10, 'throughput': 1.5177861859514825, 'latency_mean': 6.529293087720871, 'latency_p50': 6.485844731330872, 'latency_p90': 7.571904325485229}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tang82mv-flpchatai-591k-dpo-ep2
is_internal_developer: False
language_model: BBChicago/tang82mv-flpchatai-591k-dpo-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-05-11
win_ratio: 0.5047926883637985
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<', '>', '[INST]', '[\\INST]'], 'max_input_tokens': 1024, 'best_of': 8, '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}
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-tang82mv-flpc-99370-v1-mkmlizer
Waiting for job on bbchicago-tang82mv-flpc-99370-v1-mkmlizer to finish
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ /___/ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ Version: 0.12.8 ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ belonging to: ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: Downloaded to shared memory in 40.992s
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdvl8tyl9, device:0
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: quantized model in 38.243s
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: Processed model BBChicago/tang82mv-flpchatai-591k-dpo-ep2 in 79.235s
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-99370-v1
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-99370-v1/config.json
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-99370-v1/special_tokens_map.json
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-99370-v1/tokenizer_config.json
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-99370-v1/tokenizer.json
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-99370-v1/flywheel_model.0.safetensors
bbchicago-tang82mv-flpc-99370-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.50it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 42.51it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 40.09it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 39.49it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 40.60it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 32.08it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 38.98it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:08, 38.17it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:08, 37.68it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:08, 36.65it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:08, 35.82it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:13, 22.93it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 22.10it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:11, 24.53it/s] Loading 0: 20%|██ | 73/363 [00:02<00:11, 24.92it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:09, 29.91it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:09, 28.40it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:08, 33.14it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 31.10it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:07, 35.47it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:08, 32.74it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:06, 37.85it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 40.76it/s] Loading 0: 32%|███▏ | 117/363 [00:03<00:06, 37.35it/s] Loading 0: 33%|███▎ | 121/363 [00:03<00:06, 35.21it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 34.87it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 33.65it/s] Loading 0: 37%|███▋ | 134/363 [00:04<00:06, 35.47it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 34.25it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:09, 23.89it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 23.69it/s] Loading 0: 41%|████ | 149/363 [00:04<00:09, 23.48it/s] Loading 0: 42%|████▏ | 154/363 [00:04<00:07, 26.48it/s] Loading 0: 44%|████▎ | 158/363 [00:05<00:07, 26.77it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:05, 34.46it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:05, 35.13it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 37.00it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 36.28it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 38.96it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:04, 37.47it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 40.60it/s] Loading 0: 54%|█████▍ | 197/363 [00:05<00:04, 39.55it/s] Loading 0: 56%|█████▌ | 202/363 [00:06<00:04, 38.20it/s] Loading 0: 57%|█████▋ | 206/363 [00:06<00:04, 37.65it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 36.11it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 34.77it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 34.74it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 27.04it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.14it/s] Loading 0: 64%|██████▎ | 231/363 [00:07<00:05, 24.59it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 27.04it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 27.59it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 35.58it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.53it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 38.60it/s] Loading 0: 72%|███████▏ | 260/363 [00:07<00:02, 38.51it/s] Loading 0: 73%|███████▎ | 264/363 [00:08<00:02, 37.49it/s] Loading 0: 74%|███████▍ | 268/363 [00:08<00:02, 36.10it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 38.30it/s] Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 36.41it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 38.54it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 38.07it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 40.86it/s] Loading 0: 82%|████████▏ | 296/363 [00:08<00:01, 40.92it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 42.21it/s] Loading 0: 84%|████████▍ | 306/363 [00:15<00:25, 2.26it/s] Loading 0: 85%|████████▌ | 309/363 [00:15<00:19, 2.79it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:14, 3.49it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:07, 5.93it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:05, 7.57it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.36it/s] Loading 0: 92%|█████████▏| 333/363 [00:16<00:02, 13.53it/s] Loading 0: 93%|█████████▎| 338/363 [00:16<00:01, 17.16it/s] Loading 0: 94%|█████████▍| 343/363 [00:16<00:00, 21.40it/s] Loading 0: 96%|█████████▌| 348/363 [00:16<00:00, 22.32it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 29.76it/s] Loading 0: 99%|█████████▉| 360/363 [00:17<00:00, 32.38it/s]
Job bbchicago-tang82mv-flpc-99370-v1-mkmlizer completed after 104.64s with status: succeeded
Stopping job with name bbchicago-tang82mv-flpc-99370-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service bbchicago-tang82mv-flpc-99370-v1
Waiting for inference service bbchicago-tang82mv-flpc-99370-v1 to be ready
Inference service bbchicago-tang82mv-flpc-99370-v1 ready after 120.42842197418213s
Pipeline stage MKMLDeployer completed in 121.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5973269939422607s
Received healthy response to inference request in 1.6234524250030518s
Received healthy response to inference request in 1.6380257606506348s
Received healthy response to inference request in 1.836799144744873s
Received healthy response to inference request in 1.7647819519042969s
5 requests
0 failed requests
5th percentile: 1.6263670921325684
10th percentile: 1.629281759262085
20th percentile: 1.6351110935211182
30th percentile: 1.6633769989013671
40th percentile: 1.7140794754028321
50th percentile: 1.7647819519042969
60th percentile: 1.7935888290405273
70th percentile: 1.8223957061767577
80th percentile: 1.9889047145843508
90th percentile: 2.2931158542633057
95th percentile: 2.445221424102783
99th percentile: 2.566905879974365
mean time: 1.8920772552490235
Pipeline stage StressChecker completed in 11.12s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.80s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.80s
Shutdown handler de-registered
bbchicago-tang82mv-flpc_99370_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service bbchicago-tang82mv-flpc-99370-v1-profiler
Waiting for inference service bbchicago-tang82mv-flpc-99370-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2647.02s
Shutdown handler de-registered
bbchicago-tang82mv-flpc_99370_v1 status is now inactive due to auto deactivation removed underperforming models
bbchicago-tang82mv-flpc_99370_v1 status is now torndown due to DeploymentManager action