submission_id: cycy233-l3-p-v1-c1_v1
developer_uid: shiroe40
alignment_samples: 11402
alignment_score: 0.0655909518754651
best_of: 16
celo_rating: 1251.24
display_name: auto
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/L3-p-v1-c1
latencies: [{'batch_size': 1, 'throughput': 0.9031958028298719, 'latency_mean': 1.1071206629276276, 'latency_p50': 1.1121330261230469, 'latency_p90': 1.2319985389709474}, {'batch_size': 4, 'throughput': 1.7912062864733915, 'latency_mean': 2.223607543706894, 'latency_p50': 2.241734027862549, 'latency_p90': 2.4927114248275757}, {'batch_size': 5, 'throughput': 1.8757764926539369, 'latency_mean': 2.656392433643341, 'latency_p50': 2.6511528491973877, 'latency_p90': 3.0005450010299684}, {'batch_size': 8, 'throughput': 1.9842953319732197, 'latency_mean': 3.9956230366230012, 'latency_p50': 4.002911567687988, 'latency_p90': 4.486087155342102}, {'batch_size': 10, 'throughput': 2.0251401820271107, 'latency_mean': 4.8986776578426365, 'latency_p50': 4.9319576025009155, 'latency_p90': 5.499258637428284}, {'batch_size': 12, 'throughput': 2.020769051654947, 'latency_mean': 5.866439038515091, 'latency_p50': 5.927496433258057, 'latency_p90': 6.532769799232483}, {'batch_size': 15, 'throughput': 2.042055753185837, 'latency_mean': 7.21549546122551, 'latency_p50': 7.318303227424622, 'latency_p90': 8.0898588180542}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v1-c1
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v1-c1
model_size: 8B
num_battles: 11402
num_wins: 5805
propriety_score: 0.7369477911646586
propriety_total_count: 996.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.98
timestamp: 2024-09-09T03:22:30+00:00
us_pacific_date: 2024-09-08
win_ratio: 0.5091212068058235
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 cycy233-l3-p-v1-c1-v1-mkmlizer
Waiting for job on cycy233-l3-p-v1-c1-v1-mkmlizer to finish
cycy233-l3-p-v1-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ /___/ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-p-v1-c1-v1-mkmlizer: Downloaded to shared memory in 36.785s
cycy233-l3-p-v1-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi3sl_e7d, device:0
cycy233-l3-p-v1-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v1-c1-v1-mkmlizer: quantized model in 25.998s
cycy233-l3-p-v1-c1-v1-mkmlizer: Processed model cycy233/L3-p-v1-c1 in 62.783s
cycy233-l3-p-v1-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v1-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v1-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v1-c1-v1
cycy233-l3-p-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c1-v1/config.json
cycy233-l3-p-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c1-v1/special_tokens_map.json
cycy233-l3-p-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c1-v1/tokenizer_config.json
cycy233-l3-p-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c1-v1/tokenizer.json
cycy233-l3-p-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v1-c1-v1/flywheel_model.0.safetensors
cycy233-l3-p-v1-c1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 38.92it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 64.51it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 70.84it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 80.78it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 77.93it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 79.85it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 81.35it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 82.88it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.45it/s] Loading 0: 34%|███▎ | 98/291 [00:02<00:06, 28.55it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 39.37it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 46.08it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 50.95it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 57.35it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 59.19it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 63.70it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 69.12it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 78.84it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:04, 23.82it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 29.70it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 38.00it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 50.04it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 54.82it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 60.04it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 65.42it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 67.44it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 77.96it/s]
Job cycy233-l3-p-v1-c1-v1-mkmlizer completed after 83.39s with status: succeeded
Stopping job with name cycy233-l3-p-v1-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v1-c1-v1
Waiting for inference service cycy233-l3-p-v1-c1-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-p-v1-c1-v1 ready after 151.184725522995s
Pipeline stage MKMLDeployer completed in 151.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9389903545379639s
Received healthy response to inference request in 2.5261547565460205s
Received healthy response to inference request in 1.7811613082885742s
Received healthy response to inference request in 1.7529065608978271s
Received healthy response to inference request in 1.8907029628753662s
5 requests
0 failed requests
5th percentile: 1.7585575103759765
10th percentile: 1.7642084598541259
20th percentile: 1.7755103588104248
30th percentile: 1.8030696392059327
40th percentile: 1.8468863010406493
50th percentile: 1.8907029628753662
60th percentile: 1.9100179195404052
70th percentile: 1.9293328762054442
80th percentile: 2.0564232349395755
90th percentile: 2.2912889957427978
95th percentile: 2.408721876144409
99th percentile: 2.5026681804656983
mean time: 1.9779831886291503
Pipeline stage StressChecker completed in 10.57s
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 5.05s
Shutdown handler de-registered
cycy233-l3-p-v1-c1_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 cycy233-l3-p-v1-c1-v1-profiler
Waiting for inference service cycy233-l3-p-v1-c1-v1-profiler to be ready
Inference service cycy233-l3-p-v1-c1-v1-profiler ready after 150.34468150138855s
Pipeline stage MKMLProfilerDeployer completed in 150.68s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v1-c1-v1-profiler-predictor-00001-deployment-7m8dd:/code/chaiverse_profiler_1725852582 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v1-c1-v1-profiler-predictor-00001-deployment-7m8dd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725852582 && 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_1725852582/summary.json'
kubectl exec -it cycy233-l3-p-v1-c1-v1-profiler-predictor-00001-deployment-7m8dd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725852582/summary.json'
Pipeline stage MKMLProfilerRunner completed in 840.99s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v1-c1-v1-profiler is running
Tearing down inference service cycy233-l3-p-v1-c1-v1-profiler
Service cycy233-l3-p-v1-c1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.13s
Shutdown handler de-registered
cycy233-l3-p-v1-c1_v1 status is now inactive due to auto deactivation removed underperforming models