developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_2077_v1
model_name: sanchuanhehe-adjusted-co_2077_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:12:53+00:00
num_battles: 10904
num_wins: 4670
celo_rating: 1123.45
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_24_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': 1.1270247982246513, 'latency_mean': 0.8871963346004486, 'latency_p50': 0.8896516561508179, 'latency_p90': 0.9915612697601318}, {'batch_size': 5, 'throughput': 3.6780662041902334, 'latency_mean': 1.3487776017189026, 'latency_p50': 1.3502020835876465, 'latency_p90': 1.5099562406539917}, {'batch_size': 10, 'throughput': 5.454865836998443, 'latency_mean': 1.814662709236145, 'latency_p50': 1.8081823587417603, 'latency_p90': 2.02999861240387}, {'batch_size': 15, 'throughput': 6.383153251871289, 'latency_mean': 2.322750309705734, 'latency_p50': 2.316746234893799, 'latency_p90': 2.662999653816223}, {'batch_size': 20, 'throughput': 6.914299618655548, 'latency_mean': 2.840730721950531, 'latency_p50': 2.8507537841796875, 'latency_p90': 3.2508844137191772}, {'batch_size': 25, 'throughput': 7.305111648727276, 'latency_mean': 3.355317142009735, 'latency_p50': 3.3754348754882812, 'latency_p90': 3.8346269369125365}, {'batch_size': 30, 'throughput': 7.569008510096152, 'latency_mean': 3.8677203834056852, 'latency_p50': 3.81711483001709, 'latency_p90': 4.609487891197204}, {'batch_size': 35, 'throughput': 7.830192058972269, 'latency_mean': 4.36164424419403, 'latency_p50': 4.290842533111572, 'latency_p90': 5.298902702331541}, {'batch_size': 40, 'throughput': 7.774509882244731, 'latency_mean': 4.9748014545440675, 'latency_p50': 4.942274212837219, 'latency_p90': 5.881302785873412}, {'batch_size': 45, 'throughput': 7.825891132783833, 'latency_mean': 5.524628564119339, 'latency_p50': 5.552753448486328, 'latency_p90': 6.420379900932311}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_2077_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_24_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.67
us_pacific_date: 2024-09-17
win_ratio: 0.42828319882611887
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-2077-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-2077-v1-mkmlizer to finish
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
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2077-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
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', '')
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: quantized model in 18.011s
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_24_l in 49.287s
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1/config.json
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1/tokenizer.model
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1/tokenizer.json
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2077-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-2077-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 47.98it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 65.98it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 67.31it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 83.75it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 79.00it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 76.99it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 79.55it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 77.74it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 85.86it/s]
Loading 0:  33%|███▎      | 96/291 [00:01<00:02, 85.45it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:08, 21.62it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 25.53it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 32.16it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:04, 37.59it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 44.38it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 51.21it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 56.82it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 63.63it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 68.94it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 71.84it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 69.48it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 70.39it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:03, 21.65it/s]
Loading 0:  74%|███████▍  | 216/291 [00:04<00:03, 24.55it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 28.45it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 35.26it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 41.29it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 47.11it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 53.03it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 58.48it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 62.68it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 62.16it/s]
                                                            

Job sanchuanhehe-adjusted-co-2077-v1-mkmlizer completed after 83.34s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-2077-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.04s
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 sanchuanhehe-adjusted-co-2077-v1
Waiting for inference service sanchuanhehe-adjusted-co-2077-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', '')
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', '')
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
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 sanchuanhehe-adjusted-co-2077-v1 ready after 180.6992757320404s
Pipeline stage MKMLDeployer completed in 181.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2374885082244873s
Received healthy response to inference request in 1.6293506622314453s
Received healthy response to inference request in 1.6175422668457031s
Received healthy response to inference request in 1.386991262435913s
Received healthy response to inference request in 0.6501073837280273s
5 requests
0 failed requests
5th percentile: 0.7974841594696045
10th percentile: 0.9448609352111816
20th percentile: 1.239614486694336
30th percentile: 1.4331014633178711
40th percentile: 1.525321865081787
50th percentile: 1.6175422668457031
60th percentile: 1.622265625
70th percentile: 1.626988983154297
80th percentile: 1.7509782314300537
90th percentile: 1.9942333698272705
95th percentile: 2.115860939025879
99th percentile: 2.2131629943847657
mean time: 1.5042960166931152
Pipeline stage StressChecker completed in 8.39s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.67s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2077_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-2077-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-2077-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-2077-v1-profiler ready after 200.56028389930725s
Pipeline stage MKMLProfilerDeployer completed in 200.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste51f4fafab5d62cc42bf4875ab823f288-deplofmn8n:/code/chaiverse_profiler_1726579296 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste51f4fafab5d62cc42bf4875ab823f288-deplofmn8n --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579296 && 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_1726579296/summary.json'
kubectl exec -it sanchuanhehe-adjuste51f4fafab5d62cc42bf4875ab823f288-deplofmn8n --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579296/summary.json'
Pipeline stage MKMLProfilerRunner completed in 463.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-2077-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-2077-v1-profiler
Service sanchuanhehe-adjusted-co-2077-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2077_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_2077_v1 status is now torndown due to DeploymentManager action