submission_id: rica40325-mistral-13b-2452_v1
developer_uid: rica40325
best_of: 8
celo_rating: 1259.5
display_name: rica40325-mistral-13b-2452_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}
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: rica40325/mistral-13B-2452
latencies: [{'batch_size': 1, 'throughput': 0.6180873478046552, 'latency_mean': 1.617793185710907, 'latency_p50': 1.6107242107391357, 'latency_p90': 1.7920722007751464}, {'batch_size': 3, 'throughput': 1.0794167221875741, 'latency_mean': 2.7714117753505705, 'latency_p50': 2.766854763031006, 'latency_p90': 3.039701223373413}, {'batch_size': 5, 'throughput': 1.2453082629877326, 'latency_mean': 3.997154933214188, 'latency_p50': 3.9783198833465576, 'latency_p90': 4.480979418754577}, {'batch_size': 6, 'throughput': 1.256401049530469, 'latency_mean': 4.7601352787017825, 'latency_p50': 4.803589344024658, 'latency_p90': 5.3915810823440555}, {'batch_size': 8, 'throughput': 1.2437330490734537, 'latency_mean': 6.406282942295075, 'latency_p50': 6.431764721870422, 'latency_p90': 7.139098119735718}, {'batch_size': 10, 'throughput': 1.2198501932149628, 'latency_mean': 8.140408164262771, 'latency_p50': 8.17073392868042, 'latency_p90': 9.325637269020081}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rica40325/mistral-13B-24
model_name: rica40325-mistral-13b-2452_v1
model_num_parameters: 12772070400.0
model_repo: rica40325/mistral-13B-2452
model_size: 13B
num_battles: 3652
num_wins: 1934
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.22
timestamp: 2024-09-24T12:10:20+00:00
us_pacific_date: 2024-09-24
win_ratio: 0.5295728368017525
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-mistral-13b-2452-v1-mkmlizer
Waiting for job on rica40325-mistral-13b-2452-v1-mkmlizer to finish
rica40325-mistral-13b-2452-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-mistral-13b-2452-v1-mkmlizer: ║ _____ __ __ ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ /___/ ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ Version: 0.10.1 ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ https://mk1.ai ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ belonging to: ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ Chai Research Corp. ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-mistral-13b-2452-v1-mkmlizer: ║ ║
rica40325-mistral-13b-2452-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
rica40325-mistral-13b-2452-v1-mkmlizer: Downloaded to shared memory in 46.384s
rica40325-mistral-13b-2452-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmcsyk5l5, device:0
rica40325-mistral-13b-2452-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-mistral-13b-2452-v1-mkmlizer: quantized model in 38.381s
rica40325-mistral-13b-2452-v1-mkmlizer: Processed model rica40325/mistral-13B-2452 in 84.765s
rica40325-mistral-13b-2452-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-mistral-13b-2452-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-mistral-13b-2452-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v1
rica40325-mistral-13b-2452-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v1/config.json
rica40325-mistral-13b-2452-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v1/special_tokens_map.json
rica40325-mistral-13b-2452-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v1/tokenizer_config.json
rica40325-mistral-13b-2452-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v1/tokenizer.json
rica40325-mistral-13b-2452-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v1/flywheel_model.0.safetensors
rica40325-mistral-13b-2452-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 38.82it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.79it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:06, 55.95it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:05, 58.12it/s] Loading 0: 11%|█ | 40/363 [00:00<00:05, 58.02it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 60.29it/s] Loading 0: 16%|█▌ | 58/363 [00:00<00:05, 60.87it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:17, 17.50it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:14, 19.98it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 26.69it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 34.40it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 42.14it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 48.11it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 51.70it/s] Loading 0: 34%|███▍ | 124/363 [00:03<00:04, 53.75it/s] Loading 0: 37%|███▋ | 133/363 [00:03<00:04, 54.97it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:12, 17.71it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:09, 22.16it/s] Loading 0: 44%|████▎ | 158/363 [00:04<00:07, 26.70it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:06, 30.56it/s] Loading 0: 48%|████▊ | 175/363 [00:05<00:05, 35.74it/s] Loading 0: 51%|█████ | 184/363 [00:05<00:04, 39.64it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:03, 44.77it/s] Loading 0: 56%|█████▌ | 202/363 [00:05<00:03, 50.17it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:02, 55.83it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:02, 57.26it/s] Loading 0: 63%|██████▎ | 227/363 [00:07<00:07, 17.97it/s] Loading 0: 64%|██████▍ | 232/363 [00:07<00:06, 19.72it/s] Loading 0: 66%|██████▋ | 241/363 [00:07<00:04, 25.56it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 32.13it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 39.62it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 46.98it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:01, 50.14it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:01, 53.11it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 57.08it/s] Loading 0: 83%|████████▎ | 303/363 [00:08<00:00, 61.75it/s] Loading 0: 85%|████████▌ | 310/363 [00:09<00:03, 17.31it/s] Loading 0: 88%|████████▊ | 319/363 [00:09<00:01, 22.32it/s] Loading 0: 90%|█████████ | 328/363 [00:09<00:01, 27.28it/s] Loading 0: 93%|█████████▎| 337/363 [00:09<00:00, 32.29it/s] Loading 0: 95%|█████████▌| 346/363 [00:10<00:00, 37.18it/s] Loading 0: 98%|█████████▊| 355/363 [00:10<00:00, 40.53it/s] Loading 0: 100%|██████████| 363/363 [00:16<00:00, 4.14it/s]
Job rica40325-mistral-13b-2452-v1-mkmlizer completed after 134.77s with status: succeeded
Stopping job with name rica40325-mistral-13b-2452-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.64s
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-mistral-13b-2452-v1
Waiting for inference service rica40325-mistral-13b-2452-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
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-mistral-13b-2452-v1 ready after 201.43227577209473s
Pipeline stage MKMLDeployer completed in 202.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.573528289794922s
Received healthy response to inference request in 3.7857725620269775s
Received healthy response to inference request in 2.308371067047119s
Received healthy response to inference request in 2.186394453048706s
Received healthy response to inference request in 1.8585097789764404s
5 requests
0 failed requests
5th percentile: 1.9240867137908935
10th percentile: 1.9896636486053467
20th percentile: 2.120817518234253
30th percentile: 2.2107897758483888
40th percentile: 2.2595804214477537
50th percentile: 2.308371067047119
60th percentile: 2.899331665039062
70th percentile: 3.4902922630310056
80th percentile: 3.9433237075805665
90th percentile: 4.258425998687744
95th percentile: 4.4159771442413325
99th percentile: 4.542018060684204
mean time: 2.942515230178833
Pipeline stage StressChecker completed in 16.28s
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 6.41s
Shutdown handler de-registered
rica40325-mistral-13b-2452_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 0.13s
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-mistral-13b-2452-v1-profiler
Waiting for inference service rica40325-mistral-13b-2452-v1-profiler to be ready
Inference service rica40325-mistral-13b-2452-v1-profiler ready after 200.46295976638794s
Pipeline stage MKMLProfilerDeployer completed in 200.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-mistral-1315960f5fd3341cfb85679dfef0604a32-deplojjsrf:/code/chaiverse_profiler_1727180437 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-mistral-1315960f5fd3341cfb85679dfef0604a32-deplojjsrf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727180437 && 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_1727180437/summary.json'
kubectl exec -it rica40325-mistral-1315960f5fd3341cfb85679dfef0604a32-deplojjsrf --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727180437/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.52s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-mistral-13b-2452-v1-profiler is running
Tearing down inference service rica40325-mistral-13b-2452-v1-profiler
Service rica40325-mistral-13b-2452-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
rica40325-mistral-13b-2452_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-mistral-13b-2452_v1 status is now torndown due to DeploymentManager action