submission_id: riverise-mistral-0920-7872_v1
developer_uid: Riverise
best_of: 8
celo_rating: 1254.42
display_name: riverise-mistral-0920-7872_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: Riverise/mistral_0920_7872
latencies: [{'batch_size': 1, 'throughput': 0.6143746031998439, 'latency_mean': 1.6276122760772704, 'latency_p50': 1.6350226402282715, 'latency_p90': 1.7838253021240233}, {'batch_size': 3, 'throughput': 1.088176573651834, 'latency_mean': 2.7455074799060823, 'latency_p50': 2.746282935142517, 'latency_p90': 2.9900617361068726}, {'batch_size': 5, 'throughput': 1.2428674977269973, 'latency_mean': 3.9968495774269104, 'latency_p50': 3.9980242252349854, 'latency_p90': 4.462361359596253}, {'batch_size': 6, 'throughput': 1.2635848858972984, 'latency_mean': 4.722403242588043, 'latency_p50': 4.749128937721252, 'latency_p90': 5.2368889331817625}, {'batch_size': 8, 'throughput': 1.2519797677958089, 'latency_mean': 6.354529765844345, 'latency_p50': 6.315898418426514, 'latency_p90': 7.13444972038269}, {'batch_size': 10, 'throughput': 1.2088969484888212, 'latency_mean': 8.216945519447327, 'latency_p50': 8.344471454620361, 'latency_p90': 9.184024429321289}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Riverise/mistral_0920_78
model_name: riverise-mistral-0920-7872_v1
model_num_parameters: 12772070400.0
model_repo: Riverise/mistral_0920_7872
model_size: 13B
num_battles: 202099
num_wins: 103295
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.22
timestamp: 2024-09-22T08:59:27+00:00
us_pacific_date: 2024-09-22
win_ratio: 0.5111108911968887
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 riverise-mistral-0920-7872-v1-mkmlizer
Waiting for job on riverise-mistral-0920-7872-v1-mkmlizer to finish
riverise-mistral-0920-7872-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-mistral-0920-7872-v1-mkmlizer: ║     _____            __           __                                ║
riverise-mistral-0920-7872-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-mistral-0920-7872-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-mistral-0920-7872-v1-mkmlizer: ║       /___/                                                         ║
riverise-mistral-0920-7872-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-mistral-0920-7872-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-mistral-0920-7872-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-mistral-0920-7872-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-mistral-0920-7872-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-7872-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
riverise-mistral-0920-7872-v1-mkmlizer: Downloaded to shared memory in 44.724s
riverise-mistral-0920-7872-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphrsvd1zh, device:0
riverise-mistral-0920-7872-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-mistral-0920-7872-v1-mkmlizer: quantized model in 35.221s
riverise-mistral-0920-7872-v1-mkmlizer: Processed model Riverise/mistral_0920_7872 in 79.945s
riverise-mistral-0920-7872-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-mistral-0920-7872-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-mistral-0920-7872-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-mistral-0920-7872-v1
riverise-mistral-0920-7872-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-mistral-0920-7872-v1/config.json
riverise-mistral-0920-7872-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-mistral-0920-7872-v1/special_tokens_map.json
riverise-mistral-0920-7872-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-mistral-0920-7872-v1/tokenizer.json
riverise-mistral-0920-7872-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-mistral-0920-7872-v1/flywheel_model.0.safetensors
riverise-mistral-0920-7872-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.45it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:03, 89.01it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:03, 95.77it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:03, 86.96it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:03, 85.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:14, 21.08it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 32.18it/s]
Loading 0:  23%|██▎       | 85/363 [00:01<00:07, 38.44it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:05, 45.38it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 51.78it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 59.95it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 64.09it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 68.55it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 21.05it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 27.01it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:05, 38.99it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 46.73it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:03, 52.45it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 58.48it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 71.00it/s]
Loading 0:  61%|██████    | 221/363 [00:04<00:01, 75.78it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:05, 24.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:05<00:04, 30.00it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 41.45it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:01, 48.71it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:01, 54.04it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:01, 58.92it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 65.09it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 23.29it/s]
Loading 0:  88%|████████▊ | 319/363 [00:07<00:01, 33.58it/s]
Loading 0:  90%|█████████ | 328/363 [00:07<00:00, 39.25it/s]
Loading 0:  93%|█████████▎| 337/363 [00:07<00:00, 45.95it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 54.69it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00,  5.66it/s]
                                                            

Job riverise-mistral-0920-7872-v1-mkmlizer completed after 103.68s with status: succeeded
Stopping job with name riverise-mistral-0920-7872-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-mistral-0920-7872-v1
Waiting for inference service riverise-mistral-0920-7872-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
Inference service riverise-mistral-0920-7872-v1 ready after 190.96464562416077s
Pipeline stage MKMLDeployer completed in 191.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.757932424545288s
Received healthy response to inference request in 2.2578327655792236s
Received healthy response to inference request in 1.8983352184295654s
Received healthy response to inference request in 2.2660253047943115s
Received healthy response to inference request in 2.8235976696014404s
5 requests
0 failed requests
5th percentile: 1.9702347278594972
10th percentile: 2.042134237289429
20th percentile: 2.185933256149292
30th percentile: 2.2594712734222413
40th percentile: 2.262748289108276
50th percentile: 2.2660253047943115
60th percentile: 2.462788152694702
70th percentile: 2.659551000595093
80th percentile: 2.7710654735565186
90th percentile: 2.7973315715789795
95th percentile: 2.81046462059021
99th percentile: 2.820971059799194
mean time: 2.400744676589966
Pipeline stage StressChecker completed in 12.95s
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 5.38s
Shutdown handler de-registered
riverise-mistral-0920-7872_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 0.10s
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 riverise-mistral-0920-7872-v1-profiler
Waiting for inference service riverise-mistral-0920-7872-v1-profiler to be ready
Inference service riverise-mistral-0920-7872-v1-profiler ready after 190.43330645561218s
Pipeline stage MKMLProfilerDeployer completed in 190.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/riverise-mistral-0925e22b1ed560322ef79983bb028274bb5-deplo46gdg:/code/chaiverse_profiler_1726996116 --namespace tenant-chaiml-guanaco
kubectl exec -it riverise-mistral-0925e22b1ed560322ef79983bb028274bb5-deplo46gdg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726996116 && 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_1726996116/summary.json'
kubectl exec -it riverise-mistral-0925e22b1ed560322ef79983bb028274bb5-deplo46gdg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726996116/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-mistral-0920-7872-v1-profiler is running
Tearing down inference service riverise-mistral-0920-7872-v1-profiler
Service riverise-mistral-0920-7872-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.83s
Shutdown handler de-registered
riverise-mistral-0920-7872_v1 status is now inactive due to auto deactivation removed underperforming models
Pipeline stage MKMLModelDeleter completed in 6.12s
riverise-mistral-0920-7872_v1 status is now torndown due to DeploymentManager action