rica40325-spin-second

submission_id: rica40325-spin-second_v1

developer_uid: rica40325

best_of: 8

celo_rating: 1259.37

display_name: rica40325-spin-second_v1

family_friendly_score: 0.0

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: rica40325/spin_second

latencies: [{'batch_size': 1, 'throughput': 0.8553885342868017, 'latency_mean': 1.1689950835704803, 'latency_p50': 1.1716588735580444, 'latency_p90': 1.2773990154266357}, {'batch_size': 4, 'throughput': 1.8631096721085574, 'latency_mean': 2.1335839092731477, 'latency_p50': 2.1384197473526, 'latency_p90': 2.3730067729949953}, {'batch_size': 5, 'throughput': 2.003100339614562, 'latency_mean': 2.4852507948875426, 'latency_p50': 2.470765709877014, 'latency_p90': 2.7724714279174805}, {'batch_size': 8, 'throughput': 2.215750745537633, 'latency_mean': 3.584346171617508, 'latency_p50': 3.6030008792877197, 'latency_p90': 3.983885097503662}, {'batch_size': 10, 'throughput': 2.282789292746039, 'latency_mean': 4.346868485212326, 'latency_p50': 4.332485675811768, 'latency_p90': 4.941315221786499}, {'batch_size': 12, 'throughput': 2.3339584594408675, 'latency_mean': 5.088163899183273, 'latency_p50': 5.095232009887695, 'latency_p90': 5.8349100828170775}, {'batch_size': 15, 'throughput': 2.344606041563213, 'latency_mean': 6.307974835634232, 'latency_p50': 6.292023777961731, 'latency_p90': 6.968235039710999}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rica40325/spin_second

model_name: rica40325-spin-second_v1

model_num_parameters: 8030261248.0

model_repo: rica40325/spin_second

model_size: 8B

num_battles: 12339

num_wins: 6373

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 2.24

timestamp: 2024-09-19T14:40:21+00:00

us_pacific_date: 2024-09-19

win_ratio: 0.5164924224005187

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 rica40325-spin-second-v1-mkmlizer
Waiting for job on rica40325-spin-second-v1-mkmlizer to finish
rica40325-spin-second-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-spin-second-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-spin-second-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-spin-second-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-spin-second-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-spin-second-v1-mkmlizer: ║       /___/                                                         ║
rica40325-spin-second-v1-mkmlizer: ║                                                                     ║
rica40325-spin-second-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-spin-second-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-spin-second-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-spin-second-v1-mkmlizer: ║                                                                     ║
rica40325-spin-second-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-spin-second-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-spin-second-v1-mkmlizer: ║                                                                     ║
rica40325-spin-second-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-spin-second-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-spin-second-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-spin-second-v1-mkmlizer: ║                                                                     ║
rica40325-spin-second-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-spin-second-v1-mkmlizer: Downloaded to shared memory in 65.148s
rica40325-spin-second-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpixvzis2z, device:0
rica40325-spin-second-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-spin-second-v1-mkmlizer: quantized model in 28.329s
rica40325-spin-second-v1-mkmlizer: Processed model rica40325/spin_second in 93.477s
rica40325-spin-second-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-spin-second-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-spin-second-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-spin-second-v1
rica40325-spin-second-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-spin-second-v1/config.json
rica40325-spin-second-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-spin-second-v1/special_tokens_map.json
rica40325-spin-second-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-spin-second-v1/tokenizer_config.json
rica40325-spin-second-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-spin-second-v1/tokenizer.json
rica40325-spin-second-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-spin-second-v1/flywheel_model.0.safetensors
rica40325-spin-second-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 28.05it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 38.09it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 35.13it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.90it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.58it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.32it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.88it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.87it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.82it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.75it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.26it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 34.49it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 37.44it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 35.12it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.70it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 35.29it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:07, 26.20it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 28.38it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 30.04it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.80it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 34.45it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.77it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:04, 36.86it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.61it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.68it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.62it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.85it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.43it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.31it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.01it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.20it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.69it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.40it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 34.91it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 37.17it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.48it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.89it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.91it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 41.70it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 26.08it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 27.76it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 34.55it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 34.68it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.76it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 32.97it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 35.22it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.22it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 34.43it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 34.35it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.65it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.09it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.54it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.29it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.25it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.75it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 37.24it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.41it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.52it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 36.11it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 36.19it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.63it/s]
Loading 0:  99%|█████████▉| 289/291 [00:13<00:00,  3.27it/s]
                                                            
Job rica40325-spin-second-v1-mkmlizer completed after 115.18s with status: succeeded
Stopping job with name rica40325-spin-second-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-spin-second-v1
Waiting for inference service rica40325-spin-second-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
Inference service rica40325-spin-second-v1 ready after 192.24782299995422s
Pipeline stage MKMLDeployer completed in 192.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1976571083068848s
Received healthy response to inference request in 1.5910377502441406s
Received healthy response to inference request in 2.0834178924560547s
Received healthy response to inference request in 1.8371708393096924s
Received healthy response to inference request in 1.5134403705596924s
5 requests
0 failed requests
5th percentile: 1.5289598464965821
10th percentile: 1.5444793224334716
20th percentile: 1.5755182743072509
30th percentile: 1.640264368057251
40th percentile: 1.7387176036834717
50th percentile: 1.8371708393096924
60th percentile: 1.9356696605682373
70th percentile: 2.0341684818267822
80th percentile: 2.106265735626221
90th percentile: 2.151961421966553
95th percentile: 2.1748092651367186
99th percentile: 2.1930875396728515
mean time: 1.8445447921752929
Pipeline stage StressChecker completed in 10.12s
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 4.56s
Shutdown handler de-registered
rica40325-spin-second_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 rica40325-spin-second-v1-profiler
Waiting for inference service rica40325-spin-second-v1-profiler to be ready
Inference service rica40325-spin-second-v1-profiler ready after 200.45954060554504s
Pipeline stage MKMLProfilerDeployer completed in 200.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-spin-second-v1-profiler-predictor-00001-deploymeztnr9:/code/chaiverse_profiler_1726757391 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-spin-second-v1-profiler-predictor-00001-deploymeztnr9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726757391 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726757391/summary.json'
kubectl exec -it rica40325-spin-second-v1-profiler-predictor-00001-deploymeztnr9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726757391/summary.json'
Pipeline stage MKMLProfilerRunner completed in 797.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-spin-second-v1-profiler is running
Tearing down inference service rica40325-spin-second-v1-profiler
Service rica40325-spin-second-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.24s
Shutdown handler de-registered
rica40325-spin-second_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-spin-second_v1 status is now torndown due to DeploymentManager action