submission_id: cycy233-l3-p-v2-c4_v2
developer_uid: shiroe40
alignment_samples: 10879
alignment_score: -0.2804003050058953
best_of: 16
celo_rating: 1248.11
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-v2-c4
latencies: [{'batch_size': 1, 'throughput': 0.9187640763172559, 'latency_mean': 1.088347749710083, 'latency_p50': 1.0809085369110107, 'latency_p90': 1.2280253887176513}, {'batch_size': 4, 'throughput': 1.7732814760364404, 'latency_mean': 2.2527752602100373, 'latency_p50': 2.2504197359085083, 'latency_p90': 2.528057646751404}, {'batch_size': 5, 'throughput': 1.870029881638341, 'latency_mean': 2.6561617934703827, 'latency_p50': 2.6550475358963013, 'latency_p90': 2.9750905752182004}, {'batch_size': 8, 'throughput': 1.9749583171090306, 'latency_mean': 4.016916311979294, 'latency_p50': 4.0245219469070435, 'latency_p90': 4.4464311599731445}, {'batch_size': 10, 'throughput': 2.0357841568883286, 'latency_mean': 4.864982694387436, 'latency_p50': 4.871996998786926, 'latency_p90': 5.6497605562210085}, {'batch_size': 12, 'throughput': 2.0018329236889207, 'latency_mean': 5.918327317237854, 'latency_p50': 5.935218572616577, 'latency_p90': 6.823033738136291}, {'batch_size': 15, 'throughput': 1.9957425816656462, 'latency_mean': 7.370493528842926, 'latency_p50': 7.470153093338013, 'latency_p90': 8.215447759628296}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v2-c4
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v2-c4
model_size: 8B
num_battles: 10879
num_wins: 5516
propriety_score: 0.7008830022075055
propriety_total_count: 906.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.97
timestamp: 2024-09-10T03:06:01+00:00
us_pacific_date: 2024-09-09
win_ratio: 0.5070318963139995
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-v2-c4-v2-mkmlizer
Waiting for job on cycy233-l3-p-v2-c4-v2-mkmlizer to finish
cycy233-l3-p-v2-c4-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ /___/ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ║ ║
cycy233-l3-p-v2-c4-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-p-v2-c4-v2-mkmlizer: Downloaded to shared memory in 28.565s
cycy233-l3-p-v2-c4-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9eittc7o, device:0
cycy233-l3-p-v2-c4-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v2-c4-v2-mkmlizer: quantized model in 25.858s
cycy233-l3-p-v2-c4-v2-mkmlizer: Processed model cycy233/L3-p-v2-c4 in 54.423s
cycy233-l3-p-v2-c4-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v2-c4-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v2-c4-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v2-c4-v2
cycy233-l3-p-v2-c4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c4-v2/tokenizer_config.json
cycy233-l3-p-v2-c4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c4-v2/tokenizer.json
cycy233-l3-p-v2-c4-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v2-c4-v2/flywheel_model.0.safetensors
cycy233-l3-p-v2-c4-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.58it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 73.46it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 93.44it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 93.23it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 81.51it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 78.89it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 87.48it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.26it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 28.46it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 36.94it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 49.70it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 56.68it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 59.18it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 60.80it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 65.71it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 76.11it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 76.98it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:04, 23.69it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 28.53it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 35.29it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 44.58it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 51.48it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 56.55it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 60.80it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 66.17it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 71.72it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 83.26it/s]
Job cycy233-l3-p-v2-c4-v2-mkmlizer completed after 73.44s with status: succeeded
Stopping job with name cycy233-l3-p-v2-c4-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v2-c4-v2
Waiting for inference service cycy233-l3-p-v2-c4-v2 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
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-v2-c4-v2 ready after 160.58695912361145s
Pipeline stage MKMLDeployer completed in 160.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8382322788238525s
Received healthy response to inference request in 2.4130547046661377s
Received healthy response to inference request in 1.7483727931976318s
Received healthy response to inference request in 2.6176698207855225s
Received healthy response to inference request in 2.219087600708008s
5 requests
0 failed requests
5th percentile: 1.842515754699707
10th percentile: 1.9366587162017823
20th percentile: 2.124944639205933
30th percentile: 2.257881021499634
40th percentile: 2.3354678630828856
50th percentile: 2.4130547046661377
60th percentile: 2.4949007511138914
70th percentile: 2.5767467975616456
80th percentile: 2.6617823123931883
90th percentile: 2.7500072956085204
95th percentile: 2.7941197872161867
99th percentile: 2.8294097805023193
mean time: 2.3672834396362306
Pipeline stage StressChecker completed in 13.30s
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 4.20s
Shutdown handler de-registered
cycy233-l3-p-v2-c4_v2 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v2-c4-v2-profiler
Waiting for inference service cycy233-l3-p-v2-c4-v2-profiler to be ready
Inference service cycy233-l3-p-v2-c4-v2-profiler ready after 160.36403918266296s
Pipeline stage MKMLProfilerDeployer completed in 160.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v2-c4-v2-profiler-predictor-00001-deployment-xd624:/code/chaiverse_profiler_1725938020 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v2-c4-v2-profiler-predictor-00001-deployment-xd624 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725938020 && 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_1725938020/summary.json'
kubectl exec -it cycy233-l3-p-v2-c4-v2-profiler-predictor-00001-deployment-xd624 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725938020/summary.json'
Pipeline stage MKMLProfilerRunner completed in 844.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v2-c4-v2-profiler is running
Tearing down inference service cycy233-l3-p-v2-c4-v2-profiler
Service cycy233-l3-p-v2-c4-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
Shutdown handler de-registered
cycy233-l3-p-v2-c4_v2 status is now inactive due to auto deactivation removed underperforming models