submission_id: rica40325-spin-second_v3
developer_uid: rica40325
best_of: 8
celo_rating: 1256.86
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': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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': 0.8743672632105619, 'latency_mean': 1.1435431671142577, 'latency_p50': 1.1492629051208496, 'latency_p90': 1.2587862491607666}, {'batch_size': 4, 'throughput': 1.8662933549565615, 'latency_mean': 2.1370286631584166, 'latency_p50': 2.1540833711624146, 'latency_p90': 2.3981627941131594}, {'batch_size': 5, 'throughput': 2.0021828560214487, 'latency_mean': 2.4827039992809294, 'latency_p50': 2.4918856620788574, 'latency_p90': 2.746260929107666}, {'batch_size': 8, 'throughput': 2.2203097039786277, 'latency_mean': 3.5730340349674226, 'latency_p50': 3.6083110570907593, 'latency_p90': 3.964253234863281}, {'batch_size': 10, 'throughput': 2.2990800766859203, 'latency_mean': 4.322894871234894, 'latency_p50': 4.332465767860413, 'latency_p90': 4.851988577842713}, {'batch_size': 12, 'throughput': 2.3267290591110354, 'latency_mean': 5.104590694904328, 'latency_p50': 5.112960934638977, 'latency_p90': 5.735243964195251}, {'batch_size': 15, 'throughput': 2.3159252410128364, 'latency_mean': 6.3921448314189915, 'latency_p50': 6.427635669708252, 'latency_p90': 7.108602619171142}]
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: 11166
num_wins: 5666
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.25
timestamp: 2024-09-20T01:14:50+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.507433279598782
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-v3-mkmlizer
Waiting for job on rica40325-spin-second-v3-mkmlizer to finish
rica40325-spin-second-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-spin-second-v3-mkmlizer: ║ _____ __ __ ║
rica40325-spin-second-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-spin-second-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-spin-second-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-spin-second-v3-mkmlizer: ║ /___/ ║
rica40325-spin-second-v3-mkmlizer: ║ ║
rica40325-spin-second-v3-mkmlizer: ║ Version: 0.10.1 ║
rica40325-spin-second-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-spin-second-v3-mkmlizer: ║ https://mk1.ai ║
rica40325-spin-second-v3-mkmlizer: ║ ║
rica40325-spin-second-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-spin-second-v3-mkmlizer: ║ belonging to: ║
rica40325-spin-second-v3-mkmlizer: ║ ║
rica40325-spin-second-v3-mkmlizer: ║ Chai Research Corp. ║
rica40325-spin-second-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-spin-second-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-spin-second-v3-mkmlizer: ║ ║
rica40325-spin-second-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-spin-second-v3-mkmlizer: Downloaded to shared memory in 55.244s
rica40325-spin-second-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb9p2ouov, device:0
rica40325-spin-second-v3-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
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-second-v3-mkmlizer: quantized model in 28.578s
rica40325-spin-second-v3-mkmlizer: Processed model rica40325/spin_second in 83.822s
rica40325-spin-second-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-spin-second-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-spin-second-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-spin-second-v3
rica40325-spin-second-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-spin-second-v3/config.json
rica40325-spin-second-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-spin-second-v3/special_tokens_map.json
rica40325-spin-second-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-spin-second-v3/tokenizer_config.json
rica40325-spin-second-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-spin-second-v3/tokenizer.json
rica40325-spin-second-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-spin-second-v3/flywheel_model.0.safetensors
rica40325-spin-second-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.26it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.47it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.76it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.60it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.35it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.86it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.66it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.72it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.72it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:07, 33.88it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 35.04it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 34.16it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 36.43it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 34.94it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.44it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 34.49it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 23.53it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 26.37it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 28.77it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.31it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.47it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.73it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.23it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.13it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.84it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.82it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 35.19it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 29.69it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.49it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.21it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.33it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.66it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.55it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.48it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.88it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.95it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.45it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.18it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 40.56it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.66it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 26.27it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.90it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 32.39it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.04it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.37it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.96it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.97it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 34.59it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 35.23it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 26.44it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 26.13it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.16it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.61it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.58it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 34.58it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.60it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.09it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.66it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.89it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.33it/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-second-v3-mkmlizer completed after 103.82s with status: succeeded
Stopping job with name rica40325-spin-second-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-spin-second-v3
Waiting for inference service rica40325-spin-second-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
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
Inference service rica40325-spin-second-v3 ready after 302.0778479576111s
Pipeline stage MKMLDeployer completed in 303.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9065425395965576s
Received healthy response to inference request in 1.3183341026306152s
Received healthy response to inference request in 1.8088274002075195s
Received healthy response to inference request in 1.9615464210510254s
Received healthy response to inference request in 1.2994647026062012s
5 requests
0 failed requests
5th percentile: 1.303238582611084
10th percentile: 1.3070124626159667
20th percentile: 1.3145602226257325
30th percentile: 1.416432762145996
40th percentile: 1.6126300811767578
50th percentile: 1.8088274002075195
60th percentile: 1.8479134559631347
70th percentile: 1.88699951171875
80th percentile: 1.917543315887451
90th percentile: 1.9395448684692382
95th percentile: 1.950545644760132
99th percentile: 1.9593462657928467
mean time: 1.6589430332183839
Pipeline stage StressChecker completed in 9.09s
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 10.33s
Shutdown handler de-registered
rica40325-spin-second_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-spin-second-v3-profiler
Waiting for inference service rica40325-spin-second-v3-profiler to be ready
Inference service rica40325-spin-second-v3-profiler ready after 210.50629496574402s
Pipeline stage MKMLProfilerDeployer completed in 210.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-spin-second-v3-profiler-predictor-00001-deploymergkzz:/code/chaiverse_profiler_1726795577 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-spin-second-v3-profiler-predictor-00001-deploymergkzz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726795577 && 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_1726795577/summary.json'
kubectl exec -it rica40325-spin-second-v3-profiler-predictor-00001-deploymergkzz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726795577/summary.json'
Pipeline stage MKMLProfilerRunner completed in 790.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-spin-second-v3-profiler is running
Tearing down inference service rica40325-spin-second-v3-profiler
Service rica40325-spin-second-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.09s
Shutdown handler de-registered
rica40325-spin-second_v3 status is now inactive due to auto deactivation removed underperforming models
rica40325-spin-second_v3 status is now torndown due to DeploymentManager action