sao10k-l3-8b-stheno-v3-2

developer_uid: azuruce

submission_id: sao10k-l3-8b-stheno-v3-2_v3

model_name: sao10k-l3-8b-stheno-v3-2_v3

model_group: Sao10K/L3-8B-Stheno-v3.2

status: torndown

timestamp: 2024-09-24T20:47:50+00:00

num_battles: 3923

num_wins: 1915

celo_rating: 1247.92

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/L3-8B-Stheno-v3.2

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8797468621062564, 'latency_mean': 1.136600912809372, 'latency_p50': 1.1317946910858154, 'latency_p90': 1.244735884666443}, {'batch_size': 4, 'throughput': 1.8809330807582645, 'latency_mean': 2.1206207048892973, 'latency_p50': 2.1177005767822266, 'latency_p90': 2.330601191520691}, {'batch_size': 5, 'throughput': 2.0314953353667917, 'latency_mean': 2.4478292047977446, 'latency_p50': 2.4690223932266235, 'latency_p90': 2.7146857261657713}, {'batch_size': 8, 'throughput': 2.233623949580867, 'latency_mean': 3.5549481189250947, 'latency_p50': 3.5376425981521606, 'latency_p90': 4.051112532615662}, {'batch_size': 10, 'throughput': 2.2922689658931903, 'latency_mean': 4.331050602197647, 'latency_p50': 4.348217844963074, 'latency_p90': 4.887986850738526}, {'batch_size': 12, 'throughput': 2.345085076108737, 'latency_mean': 5.083751233816147, 'latency_p50': 5.095942258834839, 'latency_p90': 5.7944748878479}, {'batch_size': 15, 'throughput': 2.3484413346232627, 'latency_mean': 6.29231703042984, 'latency_p50': 6.316669225692749, 'latency_p90': 7.121096801757813}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sao10k-l3-8b-stheno-v3-2_v3

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: Sao10K/L3-8B-Stheno-v3.2

model_size: 8B

ranking_group: single

throughput_3p7s: 2.26

us_pacific_date: 2024-09-24

win_ratio: 0.48814682640836093

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', '<|eot_id|>', '<|end_of_text|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}

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 sao10k-l3-8b-stheno-v3-2-v3-mkmlizer
Waiting for job on sao10k-l3-8b-stheno-v3-2-v3-mkmlizer to finish
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║       /___/                                                         ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: Downloaded to shared memory in 31.682s
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_nau_lj_, device:0
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: quantized model in 25.911s
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: Processed model Sao10K/L3-8B-Stheno-v3.2 in 57.594s
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v3
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v3/special_tokens_map.json
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v3/config.json
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v3/tokenizer_config.json
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v3/tokenizer.json
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-stheno-v3-2-v3/flywheel_model.0.safetensors
sao10k-l3-8b-stheno-v3-2-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:44,  2.44s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:07,  1.52it/s]
Loading 0:   5%|▍         | 14/291 [00:05<01:01,  4.53it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.36it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.27it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.48it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:11, 22.25it/s]
Loading 0:  16%|█▌        | 47/291 [00:05<00:09, 26.09it/s]
Loading 0:  18%|█▊        | 53/291 [00:05<00:07, 31.11it/s]
Loading 0:  21%|██        | 60/291 [00:06<00:09, 25.21it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:07, 31.52it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:05, 38.72it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:05, 40.49it/s]
Loading 0:  31%|███       | 89/291 [00:06<00:04, 44.10it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:04, 44.51it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:03, 51.57it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:03, 50.00it/s]
Loading 0:  40%|███▉      | 116/291 [00:07<00:03, 51.26it/s]
Loading 0:  42%|████▏     | 123/291 [00:07<00:03, 48.56it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:02, 55.45it/s]
Loading 0:  47%|████▋     | 137/291 [00:07<00:02, 52.67it/s]
Loading 0:  49%|████▉     | 143/291 [00:07<00:02, 53.92it/s]
Loading 0:  52%|█████▏    | 150/291 [00:07<00:02, 50.29it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 56.83it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 54.21it/s]
Loading 0:  58%|█████▊    | 170/291 [00:08<00:03, 36.29it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 40.61it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 41.02it/s]
Loading 0:  64%|██████▍   | 187/291 [00:08<00:02, 42.75it/s]
Loading 0:  67%|██████▋   | 195/291 [00:08<00:02, 45.23it/s]
Loading 0:  70%|██████▉   | 203/291 [00:09<00:01, 52.93it/s]
Loading 0:  72%|███████▏  | 209/291 [00:09<00:01, 51.65it/s]
Loading 0:  74%|███████▍  | 215/291 [00:09<00:01, 53.22it/s]
Loading 0:  76%|███████▋  | 222/291 [00:09<00:01, 49.78it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 56.85it/s]
Loading 0:  81%|████████  | 236/291 [00:09<00:01, 54.24it/s]
Loading 0:  83%|████████▎ | 242/291 [00:09<00:00, 55.17it/s]
Loading 0:  86%|████████▌ | 249/291 [00:09<00:00, 51.65it/s]
Loading 0:  88%|████████▊ | 257/291 [00:10<00:00, 58.34it/s]
Loading 0:  91%|█████████ | 264/291 [00:10<00:00, 57.77it/s]
Loading 0:  93%|█████████▎| 270/291 [00:10<00:00, 37.68it/s]
Loading 0:  95%|█████████▍| 276/291 [00:10<00:00, 36.98it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 45.15it/s]
Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 45.84it/s]
                                                            
Job sao10k-l3-8b-stheno-v3-2-v3-mkmlizer completed after 83.77s with status: succeeded
Stopping job with name sao10k-l3-8b-stheno-v3-2-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-l3-8b-stheno-v3-2-v3
Waiting for inference service sao10k-l3-8b-stheno-v3-2-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
Inference service sao10k-l3-8b-stheno-v3-2-v3 ready after 201.60001254081726s
Pipeline stage MKMLDeployer completed in 201.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1346418857574463s
Received healthy response to inference request in 2.37101149559021s
Received healthy response to inference request in 2.173023223876953s
Received healthy response to inference request in 1.5070688724517822s
Received healthy response to inference request in 1.5446927547454834s
5 requests
0 failed requests
5th percentile: 1.5145936489105225
10th percentile: 1.5221184253692628
20th percentile: 1.5371679782867431
30th percentile: 1.6703588485717773
40th percentile: 1.9216910362243653
50th percentile: 2.173023223876953
60th percentile: 2.2522185325622557
70th percentile: 2.3314138412475587
80th percentile: 2.5237375736236576
90th percentile: 2.829189729690552
95th percentile: 2.9819158077239987
99th percentile: 3.104096670150757
mean time: 2.146087646484375
Pipeline stage StressChecker completed in 11.74s
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 5.96s
Shutdown handler de-registered
sao10k-l3-8b-stheno-v3-2_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-l3-8b-stheno-v3-2-v3-profiler
Waiting for inference service sao10k-l3-8b-stheno-v3-2-v3-profiler to be ready
Inference service sao10k-l3-8b-stheno-v3-2-v3-profiler ready after 200.48978352546692s
Pipeline stage MKMLProfilerDeployer completed in 200.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-l3-8b-stheno-v3-2-v3-profiler-predictor-00001-deplo4nsbk:/code/chaiverse_profiler_1727211430 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-l3-8b-stheno-v3-2-v3-profiler-predictor-00001-deplo4nsbk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727211430 && 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_1727211430/summary.json'
kubectl exec -it sao10k-l3-8b-stheno-v3-2-v3-profiler-predictor-00001-deplo4nsbk --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727211430/summary.json'
Pipeline stage MKMLProfilerRunner completed in 785.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-l3-8b-stheno-v3-2-v3-profiler is running
Tearing down inference service sao10k-l3-8b-stheno-v3-2-v3-profiler
Service sao10k-l3-8b-stheno-v3-2-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.28s
Shutdown handler de-registered
sao10k-l3-8b-stheno-v3-2_v3 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-8b-stheno-v3-2_v3 status is now torndown due to DeploymentManager action