developer_uid: shiroe40
submission_id: cycy233-l3-bp-v6-c3_v1
model_name: auto
model_group: cycy233/L3-bp-v6-c3
status: torndown
timestamp: 2024-09-05T03:17:01+00:00
num_battles: 11783
num_wins: 6134
celo_rating: 1256.33
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bp-v6-c3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.9099866407414917, 'latency_mean': 1.0988244330883026, 'latency_p50': 1.105531930923462, 'latency_p90': 1.2158999919891358}, {'batch_size': 4, 'throughput': 1.8099473663898187, 'latency_mean': 2.1985631656646727, 'latency_p50': 2.2078893184661865, 'latency_p90': 2.4554316997528076}, {'batch_size': 5, 'throughput': 1.8991365909709341, 'latency_mean': 2.6179108905792234, 'latency_p50': 2.6170454025268555, 'latency_p90': 2.9081337213516236}, {'batch_size': 8, 'throughput': 2.0060680355486413, 'latency_mean': 3.9684039664268496, 'latency_p50': 3.9681512117385864, 'latency_p90': 4.437879800796509}, {'batch_size': 10, 'throughput': 2.0481950685781865, 'latency_mean': 4.830809158086777, 'latency_p50': 4.831403613090515, 'latency_p90': 5.570131969451904}, {'batch_size': 12, 'throughput': 2.024834264675908, 'latency_mean': 5.844160072803497, 'latency_p50': 5.945411443710327, 'latency_p90': 6.676182055473328}, {'batch_size': 15, 'throughput': 2.0390646900908416, 'latency_mean': 7.217609524726868, 'latency_p50': 7.356459140777588, 'latency_p90': 7.982364439964295}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-bp-v6-c3
model_size: 8B
ranking_group: single
throughput_3p7s: 2.0
us_pacific_date: 2024-09-04
win_ratio: 0.520580497326657
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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 cycy233-l3-bp-v6-c3-v1-mkmlizer
Waiting for job on cycy233-l3-bp-v6-c3-v1-mkmlizer to finish
cycy233-l3-bp-v6-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bp-v6-c3-v1-mkmlizer: Downloaded to shared memory in 34.911s
cycy233-l3-bp-v6-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjfxs79h6, device:0
cycy233-l3-bp-v6-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bp-v6-c3-v1-mkmlizer: quantized model in 25.295s
cycy233-l3-bp-v6-c3-v1-mkmlizer: Processed model cycy233/L3-bp-v6-c3 in 60.206s
cycy233-l3-bp-v6-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bp-v6-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bp-v6-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bp-v6-c3-v1
cycy233-l3-bp-v6-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c3-v1/config.json
cycy233-l3-bp-v6-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c3-v1/special_tokens_map.json
cycy233-l3-bp-v6-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c3-v1/tokenizer_config.json
cycy233-l3-bp-v6-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c3-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-bp-v6-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bp-v6-c3-v1/flywheel_model.0.safetensors
cycy233-l3-bp-v6-c3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 38.34it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 67.61it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 86.84it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 94.33it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 85.01it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 92.80it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 93.57it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:08, 25.44it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 29.50it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 36.63it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.99it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 53.24it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 65.88it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:01, 70.28it/s] Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 79.51it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 81.05it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 26.71it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 32.22it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 38.40it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 50.63it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 56.45it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 62.32it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 67.61it/s] Loading 0: 88%|████████▊ | 256/291 [00:04<00:00, 71.84it/s] Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 75.40it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 79.10it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 79.87it/s]
Job cycy233-l3-bp-v6-c3-v1-mkmlizer completed after 83.67s with status: succeeded
Stopping job with name cycy233-l3-bp-v6-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.81s
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 cycy233-l3-bp-v6-c3-v1
Waiting for inference service cycy233-l3-bp-v6-c3-v1 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
Inference service cycy233-l3-bp-v6-c3-v1 ready after 140.91792845726013s
Pipeline stage MKMLDeployer completed in 141.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1314473152160645s
Received healthy response to inference request in 2.015310764312744s
Received healthy response to inference request in 1.6587839126586914s
Received healthy response to inference request in 1.954892635345459s
Received healthy response to inference request in 1.8885290622711182s
5 requests
0 failed requests
5th percentile: 1.7047329425811768
10th percentile: 1.7506819725036622
20th percentile: 1.8425800323486328
30th percentile: 1.9018017768859863
40th percentile: 1.9283472061157227
50th percentile: 1.954892635345459
60th percentile: 1.979059886932373
70th percentile: 2.003227138519287
80th percentile: 2.0385380744934083
90th percentile: 2.084992694854736
95th percentile: 2.1082200050354003
99th percentile: 2.1268018531799315
mean time: 1.9297927379608155
Pipeline stage StressChecker completed in 10.31s
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 4.58s
Shutdown handler de-registered
cycy233-l3-bp-v6-c3_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 cycy233-l3-bp-v6-c3-v1-profiler
Waiting for inference service cycy233-l3-bp-v6-c3-v1-profiler to be ready
Inference service cycy233-l3-bp-v6-c3-v1-profiler ready after 150.34505128860474s
Pipeline stage MKMLProfilerDeployer completed in 150.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-bp-v6-c3-v1-profiler-predictor-00001-deploymentsqt66:/code/chaiverse_profiler_1725506651 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bp-v6-c3-v1-profiler-predictor-00001-deploymentsqt66 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725506651 && 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_1725506651/summary.json'
kubectl exec -it cycy233-l3-bp-v6-c3-v1-profiler-predictor-00001-deploymentsqt66 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725506651/summary.json'
Pipeline stage MKMLProfilerRunner completed in 835.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-bp-v6-c3-v1-profiler is running
Tearing down inference service cycy233-l3-bp-v6-c3-v1-profiler
Service cycy233-l3-bp-v6-c3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.67s
Shutdown handler de-registered
cycy233-l3-bp-v6-c3_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bp-v6-c3_v1 status is now torndown due to DeploymentManager action