fengfengzi14-mistral-testg3

developer_uid: fengfengzi14_07790

submission_id: fengfengzi14-mistral-testg3_v3

model_name: fengfengzi14-mistral-testG3_v2

model_group: fengfengzi14/mistral_tes

status: torndown

timestamp: 2024-09-07T04:29:56+00:00

num_battles: 12313

num_wins: 3804

celo_rating: 1089.68

family_friendly_score: 0.0

submission_type: basic

model_repo: fengfengzi14/mistral_testG3

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 1.1022482971452123, 'latency_mean': 0.9071610975265503, 'latency_p50': 0.9157490730285645, 'latency_p90': 1.0106991291046143}, {'batch_size': 5, 'throughput': 3.623621890211316, 'latency_mean': 1.3695307350158692, 'latency_p50': 1.3684900999069214, 'latency_p90': 1.5422230243682862}, {'batch_size': 10, 'throughput': 5.378333393750781, 'latency_mean': 1.842727621793747, 'latency_p50': 1.8434488773345947, 'latency_p90': 2.084741187095642}, {'batch_size': 15, 'throughput': 6.375507228589046, 'latency_mean': 2.3136263418197633, 'latency_p50': 2.3179584741592407, 'latency_p90': 2.7177186012268066}, {'batch_size': 20, 'throughput': 6.861881161748436, 'latency_mean': 2.8650103676319123, 'latency_p50': 2.822587728500366, 'latency_p90': 3.317965269088745}, {'batch_size': 25, 'throughput': 7.2792886654591165, 'latency_mean': 3.364137899875641, 'latency_p50': 3.31943142414093, 'latency_p90': 3.8476085186004636}, {'batch_size': 30, 'throughput': 7.541177526517706, 'latency_mean': 3.8956006252765656, 'latency_p50': 3.835968494415283, 'latency_p90': 4.522584939002991}, {'batch_size': 35, 'throughput': 7.642451674949929, 'latency_mean': 4.467921162843704, 'latency_p50': 4.47527539730072, 'latency_p90': 5.355112767219543}, {'batch_size': 40, 'throughput': 7.665049831182843, 'latency_mean': 5.044494791030884, 'latency_p50': 4.968356013298035, 'latency_p90': 6.042389416694641}, {'batch_size': 45, 'throughput': 7.688351415413826, 'latency_mean': 5.62470727443695, 'latency_p50': 5.649825572967529, 'latency_p90': 6.6128868579864495}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: fengfengzi14-mistral-testG3_v2

is_internal_developer: False

language_model: fengfengzi14/mistral_testG3

model_size: 7B

ranking_group: single

throughput_3p7s: 7.61

us_pacific_date: 2024-09-06

win_ratio: 0.30894176886217817

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.9, 'top_k': 40, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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 fengfengzi14-mistral-testg3-v3-mkmlizer
Waiting for job on fengfengzi14-mistral-testg3-v3-mkmlizer to finish
fengfengzi14-mistral-testg3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fengfengzi14-mistral-testg3-v3-mkmlizer: ║     _____            __           __                                ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║       /___/                                                         ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  https://mk1.ai                                                     ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  belonging to:                                                      ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  Chai Research Corp.                                                ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fengfengzi14-mistral-testg3-v3-mkmlizer: Downloaded to shared memory in 20.268s
fengfengzi14-mistral-testg3-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8vp_atcm, device:0
fengfengzi14-mistral-testg3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
fengfengzi14-mistral-testg3-v3-mkmlizer: quantized model in 17.992s
fengfengzi14-mistral-testg3-v3-mkmlizer: Processed model fengfengzi14/mistral_testG3 in 38.260s
fengfengzi14-mistral-testg3-v3-mkmlizer: creating bucket guanaco-mkml-models
fengfengzi14-mistral-testg3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fengfengzi14-mistral-testg3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3
fengfengzi14-mistral-testg3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3/tokenizer_config.json
fengfengzi14-mistral-testg3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3/config.json
fengfengzi14-mistral-testg3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3/special_tokens_map.json
fengfengzi14-mistral-testg3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3/tokenizer.model
fengfengzi14-mistral-testg3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3/tokenizer.json
fengfengzi14-mistral-testg3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v3/flywheel_model.0.safetensors
fengfengzi14-mistral-testg3-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.97it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 62.29it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 71.60it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 68.06it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 66.34it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 65.96it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 63.68it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 67.63it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 72.56it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 71.32it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 73.75it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:09, 20.40it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 26.47it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:05, 32.08it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:04, 38.08it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 43.85it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 51.40it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 55.47it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 58.87it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 65.08it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:01, 73.17it/s]
Loading 0:  68%|██████▊   | 197/291 [00:03<00:01, 75.68it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:03, 21.60it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 26.82it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 33.43it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 39.96it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 46.77it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 52.81it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 54.50it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 59.28it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 63.35it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 66.65it/s]
                                                            
Job fengfengzi14-mistral-testg3-v3-mkmlizer completed after 63.71s with status: succeeded
Stopping job with name fengfengzi14-mistral-testg3-v3-mkmlizer
Pipeline stage MKMLizer completed in 64.63s
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 fengfengzi14-mistral-testg3-v3
Waiting for inference service fengfengzi14-mistral-testg3-v3 to be ready
Inference service fengfengzi14-mistral-testg3-v3 ready after 150.50112628936768s
Pipeline stage MKMLDeployer completed in 150.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5567755699157715s
Received healthy response to inference request in 1.0036110877990723s
Received healthy response to inference request in 1.2463257312774658s
Received healthy response to inference request in 0.7560768127441406s
Received healthy response to inference request in 0.9915561676025391s
5 requests
0 failed requests
5th percentile: 0.8031726837158203
10th percentile: 0.8502685546875
20th percentile: 0.9444602966308594
30th percentile: 0.9939671516418457
40th percentile: 0.998789119720459
50th percentile: 1.0036110877990723
60th percentile: 1.1006969451904296
70th percentile: 1.1977828025817872
80th percentile: 1.308415699005127
90th percentile: 1.4325956344604491
95th percentile: 1.4946856021881103
99th percentile: 1.5443575763702393
mean time: 1.1108690738677978
Pipeline stage StressChecker completed in 6.31s
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 6.15s
Shutdown handler de-registered
fengfengzi14-mistral-testg3_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 0.10s
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 fengfengzi14-mistral-testg3-v3-profiler
Waiting for inference service fengfengzi14-mistral-testg3-v3-profiler to be ready
Inference service fengfengzi14-mistral-testg3-v3-profiler ready after 140.40540313720703s
Pipeline stage MKMLProfilerDeployer completed in 140.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/fengfengzi14-mistralc81d24f9799f8545c48b50814aade41b-deplojnbvq:/code/chaiverse_profiler_1725683804 --namespace tenant-chaiml-guanaco
kubectl exec -it fengfengzi14-mistralc81d24f9799f8545c48b50814aade41b-deplojnbvq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725683804 && 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_1725683804/summary.json'
kubectl exec -it fengfengzi14-mistralc81d24f9799f8545c48b50814aade41b-deplojnbvq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725683804/summary.json'
Pipeline stage MKMLProfilerRunner completed in 471.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service fengfengzi14-mistral-testg3-v3-profiler is running
Tearing down inference service fengfengzi14-mistral-testg3-v3-profiler
Service fengfengzi14-mistral-testg3-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.56s
Shutdown handler de-registered
fengfengzi14-mistral-testg3_v3 status is now inactive due to auto deactivation removed underperforming models
fengfengzi14-mistral-testg3_v2 status is now torndown due to DeploymentManager action
fengfengzi14-mistral-testg3_v3 status is now torndown due to DeploymentManager action