rica40325-spin-first

submission_id: rica40325-spin-first_v2

developer_uid: rica40325

best_of: 8

celo_rating: 1251.88

display_name: rica40325-spin-first_v2

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_first

latencies: [{'batch_size': 1, 'throughput': 0.865800099981104, 'latency_mean': 1.154909759759903, 'latency_p50': 1.1622397899627686, 'latency_p90': 1.2676811695098877}, {'batch_size': 4, 'throughput': 1.8793962976914027, 'latency_mean': 2.121829870939255, 'latency_p50': 2.1280887126922607, 'latency_p90': 2.3432441473007204}, {'batch_size': 5, 'throughput': 2.043067030616039, 'latency_mean': 2.436977651119232, 'latency_p50': 2.444364070892334, 'latency_p90': 2.730372405052185}, {'batch_size': 8, 'throughput': 2.2663672695855452, 'latency_mean': 3.501232532262802, 'latency_p50': 3.5363595485687256, 'latency_p90': 3.911249375343323}, {'batch_size': 10, 'throughput': 2.331152874992848, 'latency_mean': 4.253227590322495, 'latency_p50': 4.274131655693054, 'latency_p90': 4.8551878213882445}, {'batch_size': 12, 'throughput': 2.3828810168671857, 'latency_mean': 4.985044598579407, 'latency_p50': 4.994411587715149, 'latency_p90': 5.639243531227112}, {'batch_size': 15, 'throughput': 2.376622457062293, 'latency_mean': 6.229078224897385, 'latency_p50': 6.22661280632019, 'latency_p90': 7.060854268074036}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rica40325/spin_first

model_name: rica40325-spin-first_v2

model_num_parameters: 8030261248.0

model_repo: rica40325/spin_first

model_size: 8B

num_battles: 11401

num_wins: 5852

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 2.31

timestamp: 2024-09-19T02:55:43+00:00

us_pacific_date: 2024-09-18

win_ratio: 0.5132883080431541

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-first-v2-mkmlizer
Waiting for job on rica40325-spin-first-v2-mkmlizer to finish
rica40325-spin-first-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-spin-first-v2-mkmlizer: ║     _____            __           __                                ║
rica40325-spin-first-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-spin-first-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-spin-first-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-spin-first-v2-mkmlizer: ║       /___/                                                         ║
rica40325-spin-first-v2-mkmlizer: ║                                                                     ║
rica40325-spin-first-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-spin-first-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-spin-first-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-spin-first-v2-mkmlizer: ║                                                                     ║
rica40325-spin-first-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-spin-first-v2-mkmlizer: ║  belonging to:                                                      ║
rica40325-spin-first-v2-mkmlizer: ║                                                                     ║
rica40325-spin-first-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-spin-first-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-spin-first-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-spin-first-v2-mkmlizer: ║                                                                     ║
rica40325-spin-first-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-spin-first-v2-mkmlizer: Downloaded to shared memory in 62.413s
rica40325-spin-first-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp04qiqqsv, device:0
rica40325-spin-first-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
rica40325-spin-first-v2-mkmlizer: quantized model in 28.690s
rica40325-spin-first-v2-mkmlizer: Processed model rica40325/spin_first in 91.103s
rica40325-spin-first-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-spin-first-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-spin-first-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-spin-first-v2
rica40325-spin-first-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-spin-first-v2/config.json
rica40325-spin-first-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-spin-first-v2/special_tokens_map.json
rica40325-spin-first-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-spin-first-v2/tokenizer_config.json
rica40325-spin-first-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-spin-first-v2/tokenizer.json
rica40325-spin-first-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-spin-first-v2/flywheel_model.0.safetensors
rica40325-spin-first-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.89it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 37.72it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.96it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:06, 39.23it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:06, 38.86it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 40.27it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:09, 27.56it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.98it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 34.48it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 33.07it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.03it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.08it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 35.54it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.02it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.45it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.30it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.57it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 27.22it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:06, 30.13it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:06, 32.12it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 34.03it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.72it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 36.07it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 35.05it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 35.85it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.21it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.85it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.13it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.44it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.48it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.91it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.96it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:04, 33.67it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:04, 32.73it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 35.98it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.11it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.79it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.83it/s]
Loading 0:  64%|██████▎   | 185/291 [00:05<00:02, 40.07it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:03, 27.60it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 27.19it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.47it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.62it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.88it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.15it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.26it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.25it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.18it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 35.41it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.60it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.33it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.47it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.32it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.26it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 32.71it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.27it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 31.89it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 33.99it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 32.62it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 33.35it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.61it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.25it/s]
                                                            
Job rica40325-spin-first-v2-mkmlizer completed after 113.84s with status: succeeded
Stopping job with name rica40325-spin-first-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-spin-first-v2
Waiting for inference service rica40325-spin-first-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
Inference service rica40325-spin-first-v2 ready after 192.06193470954895s
Pipeline stage MKMLDeployer completed in 192.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0041515827178955s
Received healthy response to inference request in 1.9577128887176514s
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
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
Received healthy response to inference request in 1.3457534313201904s
Received healthy response to inference request in 1.4597582817077637s
Received healthy response to inference request in 1.35898756980896s
5 requests
0 failed requests
5th percentile: 1.3484002590179442
10th percentile: 1.3510470867156983
20th percentile: 1.3563407421112061
30th percentile: 1.3791417121887206
40th percentile: 1.4194499969482421
50th percentile: 1.4597582817077637
60th percentile: 1.6589401245117188
70th percentile: 1.8581219673156737
80th percentile: 1.9670006275177
90th percentile: 1.9855761051177978
95th percentile: 1.9948638439178468
99th percentile: 2.002294034957886
mean time: 1.6252727508544922
Pipeline stage StressChecker completed in 8.78s
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 5.78s
Shutdown handler de-registered
rica40325-spin-first_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-spin-first-v2-profiler
Waiting for inference service rica40325-spin-first-v2-profiler to be ready
Inference service rica40325-spin-first-v2-profiler ready after 190.44263243675232s
Pipeline stage MKMLProfilerDeployer completed in 190.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-spin-first-v2-profiler-predictor-00001-deploymen62v6t:/code/chaiverse_profiler_1726715101 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-spin-first-v2-profiler-predictor-00001-deploymen62v6t --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726715101 && 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_1726715101/summary.json'
kubectl exec -it rica40325-spin-first-v2-profiler-predictor-00001-deploymen62v6t --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726715101/summary.json'
Pipeline stage MKMLProfilerRunner completed in 782.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-spin-first-v2-profiler is running
Tearing down inference service rica40325-spin-first-v2-profiler
Service rica40325-spin-first-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
Shutdown handler de-registered
rica40325-spin-first_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-spin-first_v2 status is now torndown due to DeploymentManager action