cycy233-l3-p-v2-c3

submission_id: cycy233-l3-p-v2-c3_v2

developer_uid: shiroe40

alignment_samples: 11023

alignment_score: -0.4832401107083182

best_of: 16

celo_rating: 1247.63

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-c3

latencies: [{'batch_size': 1, 'throughput': 0.8932413675035465, 'latency_mean': 1.1194210827350617, 'latency_p50': 1.1214078664779663, 'latency_p90': 1.2428869724273681}, {'batch_size': 4, 'throughput': 1.8008569285131668, 'latency_mean': 2.217465102672577, 'latency_p50': 2.2063342332839966, 'latency_p90': 2.5142111301422116}, {'batch_size': 5, 'throughput': 1.85398007122949, 'latency_mean': 2.6890361642837526, 'latency_p50': 2.6846340894699097, 'latency_p90': 2.972142791748047}, {'batch_size': 8, 'throughput': 2.0094675087695952, 'latency_mean': 3.9526594614982606, 'latency_p50': 3.9230223894119263, 'latency_p90': 4.487263798713684}, {'batch_size': 10, 'throughput': 2.0002783018126022, 'latency_mean': 4.942149972915649, 'latency_p50': 4.939579129219055, 'latency_p90': 5.651984190940857}, {'batch_size': 12, 'throughput': 2.0260023187447143, 'latency_mean': 5.838606376647949, 'latency_p50': 5.844248294830322, 'latency_p90': 6.885792875289917}, {'batch_size': 15, 'throughput': 2.0456418583799927, 'latency_mean': 7.180584781169891, 'latency_p50': 7.255676746368408, 'latency_p90': 8.096828699111938}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-p-v2-c3

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-p-v2-c3

model_size: 8B

num_battles: 11023

num_wins: 5586

propriety_score: 0.696329254727475

propriety_total_count: 899.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 2.0

timestamp: 2024-09-10T03:03:54+00:00

us_pacific_date: 2024-09-09

win_ratio: 0.5067585956636125

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-c3-v2-mkmlizer
Waiting for job on cycy233-l3-p-v2-c3-v2-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
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-v2-c3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v2-c3-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v2-c3-v2-mkmlizer: Downloaded to shared memory in 26.777s
cycy233-l3-p-v2-c3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv2npcoue, device:0
cycy233-l3-p-v2-c3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v2-c3-v2-mkmlizer: quantized model in 26.384s
cycy233-l3-p-v2-c3-v2-mkmlizer: Processed model cycy233/L3-p-v2-c3 in 53.162s
cycy233-l3-p-v2-c3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v2-c3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v2-c3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v2-c3-v2
cycy233-l3-p-v2-c3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c3-v2/config.json
cycy233-l3-p-v2-c3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c3-v2/special_tokens_map.json
cycy233-l3-p-v2-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c3-v2/tokenizer_config.json
cycy233-l3-p-v2-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c3-v2/tokenizer.json
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-v2-c3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v2-c3-v2/flywheel_model.0.safetensors
cycy233-l3-p-v2-c3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.04it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 54.76it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 67.42it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 76.70it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 74.78it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:02, 82.06it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 89.44it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 88.93it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 21.61it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 26.90it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 33.07it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 38.45it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.24it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 55.45it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 67.21it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 70.47it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 74.18it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 72.06it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 70.24it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 20.81it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 23.79it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 28.75it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 36.35it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 51.23it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 59.53it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 70.51it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 71.46it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 75.45it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 77.84it/s]
                                                            
Job cycy233-l3-p-v2-c3-v2-mkmlizer completed after 73.68s with status: succeeded
Stopping job with name cycy233-l3-p-v2-c3-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.88s
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-v2-c3-v2
Waiting for inference service cycy233-l3-p-v2-c3-v2 to be ready
Inference service cycy233-l3-p-v2-c3-v2 ready after 151.23134899139404s
Pipeline stage MKMLDeployer completed in 151.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.265409469604492s
Received healthy response to inference request in 1.8997511863708496s
Received healthy response to inference request in 2.2931227684020996s
Received healthy response to inference request in 1.6016292572021484s
Received healthy response to inference request in 1.9488964080810547s
5 requests
0 failed requests
5th percentile: 1.6612536430358886
10th percentile: 1.7208780288696288
20th percentile: 1.8401268005371094
30th percentile: 1.9095802307128906
40th percentile: 1.9292383193969727
50th percentile: 1.9488964080810547
60th percentile: 2.07550163269043
70th percentile: 2.2021068572998046
80th percentile: 2.2709521293640136
90th percentile: 2.282037448883057
95th percentile: 2.287580108642578
99th percentile: 2.2920142364501954
mean time: 2.001761817932129
Pipeline stage StressChecker completed in 10.66s
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 6.43s
Shutdown handler de-registered
cycy233-l3-p-v2-c3_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v2-c3-v2-profiler
Waiting for inference service cycy233-l3-p-v2-c3-v2-profiler to be ready
Inference service cycy233-l3-p-v2-c3-v2-profiler ready after 160.3866617679596s
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-c3-v2-profiler-predictor-00001-deployment-5v2gw:/code/chaiverse_profiler_1725937885 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v2-c3-v2-profiler-predictor-00001-deployment-5v2gw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725937885 && 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_1725937885/summary.json'
kubectl exec -it cycy233-l3-p-v2-c3-v2-profiler-predictor-00001-deployment-5v2gw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725937885/summary.json'
Pipeline stage MKMLProfilerRunner completed in 844.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v2-c3-v2-profiler is running
Tearing down inference service cycy233-l3-p-v2-c3-v2-profiler
Service cycy233-l3-p-v2-c3-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
cycy233-l3-p-v2-c3_v2 status is now inactive due to auto deactivation removed underperforming models