developer_uid: shiroe40
submission_id: cycy233-l3-bp-v6-c4_v1
model_name: auto
model_group: cycy233/L3-bp-v6-c4
status: torndown
timestamp: 2024-09-05T03:17:16+00:00
num_battles: 11512
num_wins: 5964
celo_rating: 1254.23
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bp-v6-c4
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.910075303717869, 'latency_mean': 1.0987477123737335, 'latency_p50': 1.1003715991973877, 'latency_p90': 1.233406138420105}, {'batch_size': 4, 'throughput': 1.7993466095339878, 'latency_mean': 2.2074799716472624, 'latency_p50': 2.230735659599304, 'latency_p90': 2.464766597747803}, {'batch_size': 5, 'throughput': 1.9014867980067072, 'latency_mean': 2.6224301612377166, 'latency_p50': 2.6265194416046143, 'latency_p90': 2.9348464012145996}, {'batch_size': 8, 'throughput': 2.03030607586412, 'latency_mean': 3.9151843690872195, 'latency_p50': 3.9182769060134888, 'latency_p90': 4.415373349189758}, {'batch_size': 10, 'throughput': 2.065081587544961, 'latency_mean': 4.791423820257187, 'latency_p50': 4.775902032852173, 'latency_p90': 5.573750424385071}, {'batch_size': 12, 'throughput': 2.024231040278091, 'latency_mean': 5.851776167154312, 'latency_p50': 5.877109169960022, 'latency_p90': 6.616562342643737}, {'batch_size': 15, 'throughput': 2.038845315739247, 'latency_mean': 7.210738358497619, 'latency_p50': 7.33655321598053, 'latency_p90': 8.003422713279724}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-bp-v6-c4
model_size: 8B
ranking_group: single
throughput_3p7s: 2.03
us_pacific_date: 2024-09-04
win_ratio: 0.5180681028492008
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-c4-v1-mkmlizer
Waiting for job on cycy233-l3-bp-v6-c4-v1-mkmlizer to finish
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-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bp-v6-c4-v1-mkmlizer: Downloaded to shared memory in 38.418s
cycy233-l3-bp-v6-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa1xgc0do, device:0
cycy233-l3-bp-v6-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bp-v6-c4-v1-mkmlizer: quantized model in 25.743s
cycy233-l3-bp-v6-c4-v1-mkmlizer: Processed model cycy233/L3-bp-v6-c4 in 64.162s
cycy233-l3-bp-v6-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bp-v6-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bp-v6-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bp-v6-c4-v1
cycy233-l3-bp-v6-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c4-v1/config.json
cycy233-l3-bp-v6-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c4-v1/special_tokens_map.json
cycy233-l3-bp-v6-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c4-v1/tokenizer_config.json
cycy233-l3-bp-v6-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bp-v6-c4-v1/flywheel_model.0.safetensors
cycy233-l3-bp-v6-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.88it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 65.57it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 83.22it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 83.64it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 85.07it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 86.84it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 85.68it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.01it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 30.64it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 36.69it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 49.20it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 57.08it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 68.14it/s] Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 73.45it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 81.33it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 83.78it/s] Loading 0: 67%|██████▋ | 195/291 [00:04<00:03, 25.58it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 28.47it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 34.66it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 41.73it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 49.19it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 55.41it/s] Loading 0: 86%|████████▌ | 249/291 [00:04<00:00, 66.52it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 71.69it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 75.12it/s] Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 71.08it/s] Loading 0: 98%|█████████▊| 285/291 [00:05<00:00, 74.80it/s]
Job cycy233-l3-bp-v6-c4-v1-mkmlizer completed after 83.37s with status: succeeded
Stopping job with name cycy233-l3-bp-v6-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-bp-v6-c4-v1
Waiting for inference service cycy233-l3-bp-v6-c4-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-bp-v6-c4-v1 ready after 150.66979718208313s
Pipeline stage MKMLDeployer completed in 151.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.621821641921997s
Received healthy response to inference request in 3.7298378944396973s
Received healthy response to inference request in 3.53169584274292s
Received healthy response to inference request in 1.4046199321746826s
Received healthy response to inference request in 2.013681411743164s
5 requests
0 failed requests
5th percentile: 1.5264322280883789
10th percentile: 1.648244524002075
20th percentile: 1.8918691158294678
30th percentile: 2.1353094577789307
40th percentile: 2.378565549850464
50th percentile: 2.621821641921997
60th percentile: 2.985771322250366
70th percentile: 3.349721002578735
80th percentile: 3.5713242530822753
90th percentile: 3.6505810737609865
95th percentile: 3.690209484100342
99th percentile: 3.721912212371826
mean time: 2.6603313446044923
Pipeline stage StressChecker completed in 14.53s
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 5.17s
Shutdown handler de-registered
cycy233-l3-bp-v6-c4_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 0.11s
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-c4-v1-profiler
Waiting for inference service cycy233-l3-bp-v6-c4-v1-profiler to be ready
Inference service cycy233-l3-bp-v6-c4-v1-profiler ready after 140.31863641738892s
Pipeline stage MKMLProfilerDeployer completed in 140.68s
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-c4-v1-profiler-predictor-00001-deployment65chs:/code/chaiverse_profiler_1725506665 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bp-v6-c4-v1-profiler-predictor-00001-deployment65chs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725506665 && 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_1725506665/summary.json'
kubectl exec -it cycy233-l3-bp-v6-c4-v1-profiler-predictor-00001-deployment65chs --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725506665/summary.json'
Pipeline stage MKMLProfilerRunner completed in 834.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-bp-v6-c4-v1-profiler is running
Tearing down inference service cycy233-l3-bp-v6-c4-v1-profiler
Service cycy233-l3-bp-v6-c4-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
cycy233-l3-bp-v6-c4_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bp-v6-c4_v1 status is now torndown due to DeploymentManager action