sanchuanhehe-adjusted-co_2026

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_2026_v1

model_name: sanchuanhehe-adjusted-co_2026_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:14:20+00:00

num_battles: 9226

num_wins: 3883

celo_rating: 1117.55

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_30_l

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 1.1083171848130884, 'latency_mean': 0.9021757853031158, 'latency_p50': 0.9016121625900269, 'latency_p90': 1.0033559322357177}, {'batch_size': 5, 'throughput': 3.653136186510423, 'latency_mean': 1.3630910336971283, 'latency_p50': 1.3660751581192017, 'latency_p90': 1.5403536319732665}, {'batch_size': 10, 'throughput': 5.369105007736282, 'latency_mean': 1.8402397632598877, 'latency_p50': 1.8320783376693726, 'latency_p90': 2.1400904178619387}, {'batch_size': 15, 'throughput': 6.324844077089557, 'latency_mean': 2.330325964689255, 'latency_p50': 2.3359856605529785, 'latency_p90': 2.664143109321594}, {'batch_size': 20, 'throughput': 6.800574002077154, 'latency_mean': 2.8844092798233034, 'latency_p50': 2.8981341123580933, 'latency_p90': 3.3297297954559326}, {'batch_size': 25, 'throughput': 7.241677053953292, 'latency_mean': 3.3868407928943634, 'latency_p50': 3.385860800743103, 'latency_p90': 3.943246293067932}, {'batch_size': 30, 'throughput': 7.42756988484276, 'latency_mean': 3.963140425682068, 'latency_p50': 3.929715633392334, 'latency_p90': 4.679876828193664}, {'batch_size': 35, 'throughput': 7.570341314260392, 'latency_mean': 4.511751962900162, 'latency_p50': 4.514561295509338, 'latency_p90': 5.22078320980072}, {'batch_size': 40, 'throughput': 7.545791937331793, 'latency_mean': 5.149587022066116, 'latency_p50': 5.123929858207703, 'latency_p90': 5.995238804817199}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_2026_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_30_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.49

us_pacific_date: 2024-09-17

win_ratio: 0.42087578582267504

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': 512, 'best_of': 1, 'max_output_tokens': 64}

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}

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 sanchuanhehe-adjusted-co-2026-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-2026-v1-mkmlizer to finish
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_sisun_2024-09-09: ('http://chaiml-elo-alignment-run-3-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48258->127.0.0.1:8080: read: connection reset by peer\n')
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: Downloaded to shared memory in 34.969s
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo7y0g6om, device:0
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: quantized model in 18.183s
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_30_l in 53.153s
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2026-v1
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2026-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-2026-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.21it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 61.45it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 70.65it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 70.56it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 70.45it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 74.02it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 77.14it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 79.59it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 81.12it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 82.60it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 83.12it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:09, 20.37it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 25.35it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:05, 31.18it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:04, 36.84it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 43.60it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 49.44it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 54.00it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 58.78it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 60.92it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 60.43it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 58.52it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:04, 20.40it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 23.86it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 30.48it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 36.90it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 43.06it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 48.27it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.39it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 59.23it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 63.00it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 61.81it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.14it/s]
                                                            
Job sanchuanhehe-adjusted-co-2026-v1-mkmlizer completed after 85.47s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-2026-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-2026-v1
Waiting for inference service sanchuanhehe-adjusted-co-2026-v1 to be ready
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service sanchuanhehe-adjusted-co-2026-v1 ready after 191.4733099937439s
Pipeline stage MKMLDeployer completed in 191.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8666086196899414s
Received healthy response to inference request in 0.803041934967041s
Received healthy response to inference request in 2.0024795532226562s
Received healthy response to inference request in 0.6168258190155029s
Received healthy response to inference request in 0.7697939872741699s
5 requests
0 failed requests
5th percentile: 0.6474194526672363
10th percentile: 0.6780130863189697
20th percentile: 0.7392003536224365
30th percentile: 0.7764435768127441
40th percentile: 0.7897427558898926
50th percentile: 0.803041934967041
60th percentile: 1.2284686088562011
70th percentile: 1.6538952827453612
80th percentile: 1.8937828063964843
90th percentile: 1.9481311798095704
95th percentile: 1.9753053665161133
99th percentile: 1.9970447158813476
mean time: 1.2117499828338623
Pipeline stage StressChecker completed in 6.68s
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 3.13s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2026_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 0.12s
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 sanchuanhehe-adjusted-co-2026-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-2026-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-2026-v1-profiler ready after 190.4755299091339s
Pipeline stage MKMLProfilerDeployer completed in 190.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste6f0f5eeb406a57365a36ff9d05f82450-deplongdh9:/code/chaiverse_profiler_1726579382 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste6f0f5eeb406a57365a36ff9d05f82450-deplongdh9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579382 && python profiles.py profile --best_of_n 1 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726579382/summary.json'
kubectl exec -it sanchuanhehe-adjuste6f0f5eeb406a57365a36ff9d05f82450-deplongdh9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579382/summary.json'
Pipeline stage MKMLProfilerRunner completed in 445.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-2026-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-2026-v1-profiler
Service sanchuanhehe-adjusted-co-2026-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2026_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_2026_v1 status is now torndown due to DeploymentManager action