rica40325-iter0-00

submission_id: rica40325-iter0-00_v1

developer_uid: rica40325

best_of: 8

celo_rating: 1255.02

display_name: rica40325-iter0-00_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/iter0-00

latencies: [{'batch_size': 1, 'throughput': 0.8621361083621609, 'latency_mean': 1.159847538471222, 'latency_p50': 1.1688663959503174, 'latency_p90': 1.282182502746582}, {'batch_size': 4, 'throughput': 1.8533933744190787, 'latency_mean': 2.1483579194545745, 'latency_p50': 2.1562057733535767, 'latency_p90': 2.403863978385925}, {'batch_size': 5, 'throughput': 1.9957772955717923, 'latency_mean': 2.492143086194992, 'latency_p50': 2.467082977294922, 'latency_p90': 2.8007991313934326}, {'batch_size': 8, 'throughput': 2.2174669503673154, 'latency_mean': 3.5762291598320006, 'latency_p50': 3.5850510597229004, 'latency_p90': 3.9467114210128784}, {'batch_size': 10, 'throughput': 2.261321401035185, 'latency_mean': 4.383173420429229, 'latency_p50': 4.407534599304199, 'latency_p90': 4.951479935646057}, {'batch_size': 12, 'throughput': 2.3147904754854247, 'latency_mean': 5.143839471340179, 'latency_p50': 5.163961410522461, 'latency_p90': 5.914806604385376}, {'batch_size': 15, 'throughput': 2.3279765557671044, 'latency_mean': 6.362163634300232, 'latency_p50': 6.356178879737854, 'latency_p90': 7.162649154663086}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rica40325/iter0-00

model_name: rica40325-iter0-00_v1

model_num_parameters: 8030261248.0

model_repo: rica40325/iter0-00

model_size: 8B

num_battles: 70629

num_wins: 36239

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 2.25

timestamp: 2024-09-23T05:23:31+00:00

us_pacific_date: 2024-09-22

win_ratio: 0.5130895241331465

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-iter0-00-v1-mkmlizer
Waiting for job on rica40325-iter0-00-v1-mkmlizer to finish
rica40325-iter0-00-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-iter0-00-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-iter0-00-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-iter0-00-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-iter0-00-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-iter0-00-v1-mkmlizer: ║       /___/                                                         ║
rica40325-iter0-00-v1-mkmlizer: ║                                                                     ║
rica40325-iter0-00-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-iter0-00-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-iter0-00-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-iter0-00-v1-mkmlizer: ║                                                                     ║
rica40325-iter0-00-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-iter0-00-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-iter0-00-v1-mkmlizer: ║                                                                     ║
rica40325-iter0-00-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-iter0-00-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-iter0-00-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-iter0-00-v1-mkmlizer: ║                                                                     ║
rica40325-iter0-00-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
rica40325-iter0-00-v1-mkmlizer: Downloaded to shared memory in 60.890s
rica40325-iter0-00-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjsobjk8e, device:0
rica40325-iter0-00-v1-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-iter0-00-v1-mkmlizer: quantized model in 28.346s
rica40325-iter0-00-v1-mkmlizer: Processed model rica40325/iter0-00 in 89.237s
rica40325-iter0-00-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-iter0-00-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-iter0-00-v1
rica40325-iter0-00-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-iter0-00-v1/config.json
rica40325-iter0-00-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-iter0-00-v1/special_tokens_map.json
rica40325-iter0-00-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-iter0-00-v1/tokenizer_config.json
rica40325-iter0-00-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-iter0-00-v1/tokenizer.json
rica40325-iter0-00-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-iter0-00-v1/flywheel_model.0.safetensors
rica40325-iter0-00-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.49it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 42.16it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:07, 38.31it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:07, 36.85it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:06, 39.62it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 40.68it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:09, 25.75it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.76it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 34.21it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.56it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:06, 35.54it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:06, 36.20it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:06, 37.26it/s]
Loading 0:  24%|██▍       | 71/291 [00:02<00:05, 37.80it/s]
Loading 0:  26%|██▌       | 75/291 [00:02<00:06, 31.30it/s]
Loading 0:  27%|██▋       | 80/291 [00:02<00:07, 26.49it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:08, 24.26it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 33.33it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 32.59it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:05, 35.24it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.98it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:04, 37.84it/s]
Loading 0:  39%|███▉      | 113/291 [00:03<00:04, 38.32it/s]
Loading 0:  41%|████      | 118/291 [00:03<00:04, 41.11it/s]
Loading 0:  43%|████▎     | 125/291 [00:03<00:03, 45.18it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 43.03it/s]
Loading 0:  46%|████▋     | 135/291 [00:04<00:05, 26.76it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:05, 27.69it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.74it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.90it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:04, 33.70it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:04, 32.02it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 33.16it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 31.99it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.70it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.70it/s]
Loading 0:  64%|██████▎   | 185/291 [00:05<00:02, 38.45it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.88it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 25.86it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.99it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.51it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.67it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.02it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.60it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.10it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 34.61it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 34.71it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.62it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.19it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 34.52it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 34.03it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.46it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.57it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 35.68it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.09it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.49it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.78it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.66it/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-iter0-00-v1-mkmlizer completed after 113.86s with status: succeeded
Stopping job with name rica40325-iter0-00-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-iter0-00-v1
Waiting for inference service rica40325-iter0-00-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-iter0-00-v1 ready after 190.7487678527832s
Pipeline stage MKMLDeployer completed in 191.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3930280208587646s
Received healthy response to inference request in 1.8188869953155518s
Received healthy response to inference request in 2.085616111755371s
Received healthy response to inference request in 1.3531343936920166s
Received healthy response to inference request in 1.84228515625s
5 requests
0 failed requests
5th percentile: 1.4462849140167235
10th percentile: 1.5394354343414307
20th percentile: 1.7257364749908448
30th percentile: 1.8235666275024414
40th percentile: 1.8329258918762208
50th percentile: 1.84228515625
60th percentile: 1.9396175384521483
70th percentile: 2.0369499206542967
80th percentile: 2.14709849357605
90th percentile: 2.2700632572174073
95th percentile: 2.3315456390380858
99th percentile: 2.380731544494629
mean time: 1.8985901355743409
Pipeline stage StressChecker completed in 10.30s
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 9.35s
Shutdown handler de-registered
rica40325-iter0-00_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 0.11s
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 rica40325-iter0-00-v1-profiler
Waiting for inference service rica40325-iter0-00-v1-profiler to be ready
Inference service rica40325-iter0-00-v1-profiler ready after 180.46917033195496s
Pipeline stage MKMLProfilerDeployer completed in 180.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-iter0-00-v1-profiler-predictor-00001-deployment-gdm5x:/code/chaiverse_profiler_1727069562 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-iter0-00-v1-profiler-predictor-00001-deployment-gdm5x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727069562 && 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_1727069562/summary.json'
kubectl exec -it rica40325-iter0-00-v1-profiler-predictor-00001-deployment-gdm5x --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727069562/summary.json'
Pipeline stage MKMLProfilerRunner completed in 795.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-iter0-00-v1-profiler is running
Tearing down inference service rica40325-iter0-00-v1-profiler
Service rica40325-iter0-00-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.27s
Shutdown handler de-registered
rica40325-iter0-00_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-iter0-00_v1 status is now torndown due to DeploymentManager action