submission_id: cycy233-l3-p-v4-c3_v1
developer_uid: shiroe40
alignment_samples: 13486
alignment_score: 0.42185596479757737
best_of: 16
celo_rating: 1244.91
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-v4-c3
latencies: [{'batch_size': 1, 'throughput': 0.9005197318385635, 'latency_mean': 1.1104150390625, 'latency_p50': 1.116875171661377, 'latency_p90': 1.2456694841384888}, {'batch_size': 4, 'throughput': 1.7846092657626327, 'latency_mean': 2.231219346523285, 'latency_p50': 2.22730553150177, 'latency_p90': 2.4860114574432375}, {'batch_size': 5, 'throughput': 1.8507405613722356, 'latency_mean': 2.687387422323227, 'latency_p50': 2.691369414329529, 'latency_p90': 3.0076743364334106}, {'batch_size': 8, 'throughput': 1.9778932082419598, 'latency_mean': 4.015090655088425, 'latency_p50': 3.9828851222991943, 'latency_p90': 4.5185185194015505}, {'batch_size': 10, 'throughput': 1.984309526065179, 'latency_mean': 4.979380596876144, 'latency_p50': 4.951327443122864, 'latency_p90': 5.718584752082824}, {'batch_size': 12, 'throughput': 2.0078352605076404, 'latency_mean': 5.902548240423203, 'latency_p50': 5.910148024559021, 'latency_p90': 6.75609655380249}, {'batch_size': 15, 'throughput': 1.9948978406788913, 'latency_mean': 7.369940856695175, 'latency_p50': 7.536653399467468, 'latency_p90': 8.131272339820862}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v4-c3
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v4-c3
model_size: 8B
num_battles: 13486
num_wins: 6742
propriety_score: 0.7268760907504364
propriety_total_count: 1146.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.97
timestamp: 2024-09-13T02:20:21+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.49992584902862225
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-v4-c3-v1-mkmlizer
Waiting for job on cycy233-l3-p-v4-c3-v1-mkmlizer to finish
cycy233-l3-p-v4-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v4-c3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
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
cycy233-l3-p-v4-c3-v1-mkmlizer: Downloaded to shared memory in 34.466s
cycy233-l3-p-v4-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpedswqlzb, device:0
cycy233-l3-p-v4-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v4-c3-v1-mkmlizer: quantized model in 25.802s
cycy233-l3-p-v4-c3-v1-mkmlizer: Processed model cycy233/L3-p-v4-c3 in 60.269s
cycy233-l3-p-v4-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v4-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v4-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v4-c3-v1
cycy233-l3-p-v4-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c3-v1/config.json
cycy233-l3-p-v4-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c3-v1/special_tokens_map.json
cycy233-l3-p-v4-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c3-v1/tokenizer_config.json
cycy233-l3-p-v4-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c3-v1/tokenizer.json
cycy233-l3-p-v4-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v4-c3-v1/flywheel_model.0.safetensors
cycy233-l3-p-v4-c3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 47.54it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 68.10it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 75.81it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 72.80it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 77.81it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 88.62it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 89.00it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 89.02it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.08it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.12it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 38.81it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 45.04it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 57.98it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 62.84it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 67.40it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 71.88it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 75.70it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 73.71it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:01, 82.76it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:04, 23.59it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 27.77it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 35.13it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 45.98it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 53.04it/s]
Loading 0:  82%|████████▏ | 240/291 [00:04<00:00, 59.46it/s]
Loading 0:  86%|████████▌ | 249/291 [00:04<00:00, 64.82it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 66.49it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 71.78it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 74.84it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 72.93it/s]
                                                            

Job cycy233-l3-p-v4-c3-v1-mkmlizer completed after 83.22s with status: succeeded
Stopping job with name cycy233-l3-p-v4-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.29s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v4-c3-v1
Waiting for inference service cycy233-l3-p-v4-c3-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-p-v4-c3-v1 ready after 171.07564568519592s
Pipeline stage MKMLDeployer completed in 171.82s
run pipeline stage %s
Running pipeline stage StressChecker
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
Received healthy response to inference request in 3.0458500385284424s
Received healthy response to inference request in 1.623500108718872s
Received healthy response to inference request in 1.9394478797912598s
Received healthy response to inference request in 1.7443482875823975s
Received healthy response to inference request in 2.225269317626953s
5 requests
0 failed requests
5th percentile: 1.647669744491577
10th percentile: 1.6718393802642821
20th percentile: 1.7201786518096924
30th percentile: 1.78336820602417
40th percentile: 1.8614080429077149
50th percentile: 1.9394478797912598
60th percentile: 2.0537764549255373
70th percentile: 2.1681050300598144
80th percentile: 2.389385461807251
90th percentile: 2.7176177501678467
95th percentile: 2.8817338943481445
99th percentile: 3.013026809692383
mean time: 2.115683126449585
Pipeline stage StressChecker completed in 11.22s
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 7.14s
Shutdown handler de-registered
cycy233-l3-p-v4-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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v4-c3-v1-profiler
Waiting for inference service cycy233-l3-p-v4-c3-v1-profiler to be ready
Inference service cycy233-l3-p-v4-c3-v1-profiler ready after 180.51176023483276s
Pipeline stage MKMLProfilerDeployer completed in 180.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v4-c3-v1-profiler-predictor-00001-deployment-tb96x:/code/chaiverse_profiler_1726194536 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v4-c3-v1-profiler-predictor-00001-deployment-tb96x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726194536 && 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_1726194536/summary.json'
kubectl exec -it cycy233-l3-p-v4-c3-v1-profiler-predictor-00001-deployment-tb96x --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726194536/summary.json'
Pipeline stage MKMLProfilerRunner completed in 850.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v4-c3-v1-profiler is running
Tearing down inference service cycy233-l3-p-v4-c3-v1-profiler
Service cycy233-l3-p-v4-c3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.19s
Shutdown handler de-registered
cycy233-l3-p-v4-c3_v1 status is now inactive due to auto deactivation removed underperforming models