cycy233-l3-p-v5-c3

submission_id: cycy233-l3-p-v5-c3_v3

developer_uid: shiroe40

alignment_samples: 12633

alignment_score: -0.13736727499172552

best_of: 16

celo_rating: 1247.93

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-v5-c3

latencies: [{'batch_size': 1, 'throughput': 0.9129794856515353, 'latency_mean': 1.0952570140361786, 'latency_p50': 1.0992326736450195, 'latency_p90': 1.2311362504959107}, {'batch_size': 4, 'throughput': 1.8021214179468612, 'latency_mean': 2.209778550863266, 'latency_p50': 2.2078542709350586, 'latency_p90': 2.5028607130050657}, {'batch_size': 5, 'throughput': 1.9039369122619472, 'latency_mean': 2.6148872101306915, 'latency_p50': 2.6438101530075073, 'latency_p90': 2.9168606996536255}, {'batch_size': 8, 'throughput': 2.0178919583004804, 'latency_mean': 3.9314133846759796, 'latency_p50': 3.9438639879226685, 'latency_p90': 4.4095299243927}, {'batch_size': 10, 'throughput': 2.0519721692507575, 'latency_mean': 4.821046723127365, 'latency_p50': 4.873395919799805, 'latency_p90': 5.475319576263428}, {'batch_size': 12, 'throughput': 2.057281655220838, 'latency_mean': 5.758089973926544, 'latency_p50': 5.777101993560791, 'latency_p90': 6.7012334823608395}, {'batch_size': 15, 'throughput': 2.0544535421577916, 'latency_mean': 7.163832091093063, 'latency_p50': 7.237919926643372, 'latency_p90': 7.948050785064697}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-p-v5-c3

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-p-v5-c3

model_size: 8B

num_battles: 12632

num_wins: 6245

propriety_score: 0.7323704333050127

propriety_total_count: 1177.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 2.02

timestamp: 2024-09-14T10:28:10+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.4943793540215326

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-v5-c3-v3-mkmlizer
Waiting for job on cycy233-l3-p-v5-c3-v3-mkmlizer to finish
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
cycy233-l3-p-v5-c3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v5-c3-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v5-c3-v3-mkmlizer: Downloaded to shared memory in 31.715s
cycy233-l3-p-v5-c3-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7vcd34xk, device:0
cycy233-l3-p-v5-c3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v5-c3-v3-mkmlizer: quantized model in 25.303s
cycy233-l3-p-v5-c3-v3-mkmlizer: Processed model cycy233/L3-p-v5-c3 in 57.018s
cycy233-l3-p-v5-c3-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v5-c3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v5-c3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v5-c3-v3
cycy233-l3-p-v5-c3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c3-v3/config.json
cycy233-l3-p-v5-c3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c3-v3/special_tokens_map.json
cycy233-l3-p-v5-c3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c3-v3/tokenizer_config.json
cycy233-l3-p-v5-c3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c3-v3/tokenizer.json
cycy233-l3-p-v5-c3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v5-c3-v3/flywheel_model.0.safetensors
cycy233-l3-p-v5-c3-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.23it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 68.65it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 87.54it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 83.11it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 83.44it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 81.87it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 81.03it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 81.05it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 21.92it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 28.05it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 40.35it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 48.26it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 54.62it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 60.48it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 63.81it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 69.51it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 72.63it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 70.84it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 22.14it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 28.47it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 35.33it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 48.75it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 57.00it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:00, 62.95it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 66.81it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 67.29it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 71.04it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 75.24it/s]
Loading 0:  98%|█████████▊| 284/291 [00:05<00:00, 77.82it/s]
                                                            
Job cycy233-l3-p-v5-c3-v3-mkmlizer completed after 83.34s with status: succeeded
Stopping job with name cycy233-l3-p-v5-c3-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.19s
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-p-v5-c3-v3
Waiting for inference service cycy233-l3-p-v5-c3-v3 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
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-p-v5-c3-v3 ready after 170.77230048179626s
Pipeline stage MKMLDeployer completed in 171.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8151326179504395s
Received healthy response to inference request in 2.2663278579711914s
Received healthy response to inference request in 2.2457239627838135s
Received healthy response to inference request in 2.4386770725250244s
Received healthy response to inference request in 1.679473638534546s
5 requests
0 failed requests
5th percentile: 1.7066054344177246
10th percentile: 1.7337372303009033
20th percentile: 1.7880008220672607
30th percentile: 1.9012508869171143
40th percentile: 2.073487424850464
50th percentile: 2.2457239627838135
60th percentile: 2.2539655208587646
70th percentile: 2.2622070789337156
80th percentile: 2.300797700881958
90th percentile: 2.369737386703491
95th percentile: 2.404207229614258
99th percentile: 2.431783103942871
mean time: 2.0890670299530028
Pipeline stage StressChecker completed in 11.64s
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 6.12s
Shutdown handler de-registered
cycy233-l3-p-v5-c3_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v5-c3-v3-profiler
Waiting for inference service cycy233-l3-p-v5-c3-v3-profiler to be ready
Inference service cycy233-l3-p-v5-c3-v3-profiler ready after 170.40439891815186s
Pipeline stage MKMLProfilerDeployer completed in 172.33s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v5-c3-v3-profiler-predictor-00001-deployment-5p8qc:/code/chaiverse_profiler_1726310174 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v5-c3-v3-profiler-predictor-00001-deployment-5p8qc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726310174 && 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_1726310174/summary.json'
kubectl exec -it cycy233-l3-p-v5-c3-v3-profiler-predictor-00001-deployment-5p8qc --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726310174/summary.json'
Pipeline stage MKMLProfilerRunner completed in 834.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v5-c3-v3-profiler is running
Tearing down inference service cycy233-l3-p-v5-c3-v3-profiler
Service cycy233-l3-p-v5-c3-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.75s
Shutdown handler de-registered
cycy233-l3-p-v5-c3_v3 status is now inactive due to auto deactivation removed underperforming models