developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_8190_v1
model_name: sanchuanhehe-adjusted-co_8190_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:12:19+00:00
num_battles: 10921
num_wins: 4632
celo_rating: 1121.2
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_22_l
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 1.1114646909093986, 'latency_mean': 0.8996390330791474, 'latency_p50': 0.9044170379638672, 'latency_p90': 0.9995086908340454}, {'batch_size': 5, 'throughput': 3.6484453671444608, 'latency_mean': 1.368144838809967, 'latency_p50': 1.365557074546814, 'latency_p90': 1.5519341468811034}, {'batch_size': 10, 'throughput': 5.331923658285738, 'latency_mean': 1.8567875635623932, 'latency_p50': 1.85033118724823, 'latency_p90': 2.119524383544922}, {'batch_size': 15, 'throughput': 6.333991030003243, 'latency_mean': 2.336659816503525, 'latency_p50': 2.33495557308197, 'latency_p90': 2.6572251081466676}, {'batch_size': 20, 'throughput': 6.904480123950305, 'latency_mean': 2.867995718717575, 'latency_p50': 2.8637821674346924, 'latency_p90': 3.3209701776504517}, {'batch_size': 25, 'throughput': 7.204809399365144, 'latency_mean': 3.390127207040787, 'latency_p50': 3.3955596685409546, 'latency_p90': 3.959662938117981}, {'batch_size': 30, 'throughput': 7.305832357652717, 'latency_mean': 4.006131834983826, 'latency_p50': 3.9745302200317383, 'latency_p90': 4.754499506950378}, {'batch_size': 35, 'throughput': 7.532238504065062, 'latency_mean': 4.529138766527176, 'latency_p50': 4.449339151382446, 'latency_p90': 5.485521006584166}, {'batch_size': 40, 'throughput': 7.46700061714898, 'latency_mean': 5.171275988817215, 'latency_p50': 5.1312055587768555, 'latency_p90': 6.085227274894714}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_8190_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_22_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.44
us_pacific_date: 2024-09-17
win_ratio: 0.424136983792693
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'], 'max_input_tokens': 512, 'best_of': 1, '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 sanchuanhehe-adjusted-co-8190-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-8190-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ _____ __ __ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ /___/ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ Version: 0.10.1 ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ https://mk1.ai ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ belonging to: ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ Chai Research Corp. ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: quantized model in 18.302s
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_22_l in 50.847s
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1/config.json
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1/tokenizer.model
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1/tokenizer.json
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8190-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-8190-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 51.78it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 75.73it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 85.50it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 86.68it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 84.84it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 79.47it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 82.43it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 80.35it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:02, 81.38it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 81.88it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:08, 20.93it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:06, 26.53it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:05, 32.57it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:04, 39.19it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:03, 45.18it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 49.14it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 54.63it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 58.53it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 59.70it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 57.36it/s] Loading 0: 66%|██████▋ | 193/291 [00:03<00:01, 59.09it/s] Loading 0: 69%|██████▉ | 202/291 [00:03<00:01, 59.12it/s] Loading 0: 72%|███████▏ | 209/291 [00:04<00:04, 19.09it/s] Loading 0: 74%|███████▎ | 214/291 [00:05<00:03, 21.37it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:02, 27.90it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 34.35it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:01, 40.68it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 46.17it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 47.73it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 50.30it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 56.04it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 53.88it/s] Loading 0: 99%|█████████▉| 289/291 [00:06<00:00, 50.28it/s]
Job sanchuanhehe-adjusted-co-8190-v1-mkmlizer completed after 74.04s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-8190-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-8190-v1
Waiting for inference service sanchuanhehe-adjusted-co-8190-v1 to be ready
Inference service sanchuanhehe-adjusted-co-8190-v1 ready after 182.27979636192322s
Pipeline stage MKMLDeployer completed in 182.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5118956565856934s
Received healthy response to inference request in 1.8792104721069336s
Received healthy response to inference request in 0.7018215656280518s
Received healthy response to inference request in 0.9297304153442383s
Received healthy response to inference request in 1.3126580715179443s
5 requests
0 failed requests
5th percentile: 0.747403335571289
10th percentile: 0.7929851055145264
20th percentile: 0.884148645401001
30th percentile: 1.0063159465789795
40th percentile: 1.159487009048462
50th percentile: 1.3126580715179443
60th percentile: 1.392353105545044
70th percentile: 1.4720481395721434
80th percentile: 1.5853586196899414
90th percentile: 1.7322845458984375
95th percentile: 1.8057475090026855
99th percentile: 1.864517879486084
mean time: 1.2670632362365724
Pipeline stage StressChecker completed in 7.61s
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 5.32s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8190_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-8190-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-8190-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-8190-v1-profiler ready after 180.41684246063232s
Pipeline stage MKMLProfilerDeployer completed in 180.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste8911b27b46b8cfb7c3cd99dc838787bb-deplo9dzlf:/code/chaiverse_profiler_1726579228 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste8911b27b46b8cfb7c3cd99dc838787bb-deplo9dzlf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579228 && python profiles.py profile --best_of_n 1 --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_1726579228/summary.json'
kubectl exec -it sanchuanhehe-adjuste8911b27b46b8cfb7c3cd99dc838787bb-deplo9dzlf --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579228/summary.json'
Pipeline stage MKMLProfilerRunner completed in 446.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-8190-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-8190-v1-profiler
Service sanchuanhehe-adjusted-co-8190-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.91s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8190_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_8190_v1 status is now torndown due to DeploymentManager action