sanchuanhehe-adjusted-co_8535

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_8535_v1

model_name: sanchuanhehe-adjusted-co_8535_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:04:21+00:00

num_battles: 9463

num_wins: 3922

celo_rating: 1114.74

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_1_le

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 1.129438882706687, 'latency_mean': 0.8853344261646271, 'latency_p50': 0.8787847757339478, 'latency_p90': 0.9993305683135987}, {'batch_size': 5, 'throughput': 3.6530271497442883, 'latency_mean': 1.3594034600257874, 'latency_p50': 1.374876856803894, 'latency_p90': 1.5049481391906738}, {'batch_size': 10, 'throughput': 5.411415631197753, 'latency_mean': 1.8375368201732636, 'latency_p50': 1.8402743339538574, 'latency_p90': 2.0647687196731566}, {'batch_size': 15, 'throughput': 6.276138159092357, 'latency_mean': 2.3475990188121796, 'latency_p50': 2.3634371757507324, 'latency_p90': 2.715869736671448}, {'batch_size': 20, 'throughput': 6.936961417644108, 'latency_mean': 2.846467378139496, 'latency_p50': 2.817796230316162, 'latency_p90': 3.329827094078064}, {'batch_size': 25, 'throughput': 7.2323411475322645, 'latency_mean': 3.3983904790878294, 'latency_p50': 3.3741589784622192, 'latency_p90': 3.962620186805725}, {'batch_size': 30, 'throughput': 7.44919156865558, 'latency_mean': 3.922058559656143, 'latency_p50': 3.9166887998580933, 'latency_p90': 4.602846407890319}, {'batch_size': 35, 'throughput': 7.717353446161732, 'latency_mean': 4.424408334493637, 'latency_p50': 4.397673726081848, 'latency_p90': 5.159278225898743}, {'batch_size': 40, 'throughput': 7.583676157610637, 'latency_mean': 5.100558968782425, 'latency_p50': 5.03651762008667, 'latency_p90': 6.013205909729003}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_8535_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_1_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.54

us_pacific_date: 2024-09-17

win_ratio: 0.4144563034978337

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-8535-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-8535-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: Downloaded to shared memory in 32.701s
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjfxvgs_j, device:0
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: quantized model in 18.097s
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_1_le in 50.798s
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1/config.json
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1/tokenizer.model
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1/tokenizer.json
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8535-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-8535-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 45.02it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 57.65it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 65.07it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 65.14it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 65.49it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 69.81it/s]
Loading 0:  21%|██▏       | 62/291 [00:00<00:02, 77.41it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 78.10it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 80.81it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 81.44it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:08, 22.42it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:06, 27.52it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 33.70it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 41.38it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:03, 50.12it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 54.99it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 61.58it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 66.01it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 68.79it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 69.49it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 68.20it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 70.51it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:04, 21.50it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 25.30it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 32.56it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 39.41it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 44.97it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 49.09it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.64it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 55.98it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 56.45it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 57.99it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.23it/s]
                                                            
Job sanchuanhehe-adjusted-co-8535-v1-mkmlizer completed after 73.85s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-8535-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.67s
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-8535-v1
Waiting for inference service sanchuanhehe-adjusted-co-8535-v1 to be ready
Inference service sanchuanhehe-adjusted-co-8535-v1 ready after 171.50634670257568s
Pipeline stage MKMLDeployer completed in 171.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5171151161193848s
Received healthy response to inference request in 0.5906457901000977s
Received healthy response to inference request in 0.8162820339202881s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 0.4176359176635742s
Received healthy response to inference request in 0.6613435745239258s
5 requests
0 failed requests
5th percentile: 0.4522378921508789
10th percentile: 0.48683986663818357
20th percentile: 0.5560438156127929
30th percentile: 0.6047853469848633
40th percentile: 0.6330644607543945
50th percentile: 0.6613435745239258
60th percentile: 0.7233189582824707
70th percentile: 0.7852943420410156
80th percentile: 0.9564486503601075
90th percentile: 1.2367818832397461
95th percentile: 1.3769484996795653
99th percentile: 1.4890817928314208
mean time: 0.8006044864654541
Pipeline stage StressChecker completed in 4.61s
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 5.09s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8535_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 sanchuanhehe-adjusted-co-8535-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-8535-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-8535-v1-profiler ready after 200.48220014572144s
Pipeline stage MKMLProfilerDeployer completed in 200.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste39139cbdb20f010eddfa2495332bfd7b-deploch5rz:/code/chaiverse_profiler_1726578780 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste39139cbdb20f010eddfa2495332bfd7b-deploch5rz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578780 && 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_1726578780/summary.json'
kubectl exec -it sanchuanhehe-adjuste39139cbdb20f010eddfa2495332bfd7b-deploch5rz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578780/summary.json'
Pipeline stage MKMLProfilerRunner completed in 440.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-8535-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-8535-v1-profiler
Service sanchuanhehe-adjusted-co-8535-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8535_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_8535_v1 status is now torndown due to DeploymentManager action