fengfengzi14-mistral-testg3

developer_uid: doyourbesthust_07790

submission_id: fengfengzi14-mistral-testg3_v1

model_name: fengfengzi14-mistral-testg3_v1

model_group: fengfengzi14/mistral_tes

status: torndown

timestamp: 2024-09-07T03:51:42+00:00

num_battles: 13886

num_wins: 4178

celo_rating: 1085.41

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': 1.1165821237355766, 'latency_mean': 0.895530812740326, 'latency_p50': 0.8856512308120728, 'latency_p90': 1.0094513654708863}, {'batch_size': 5, 'throughput': 3.6346388245435177, 'latency_mean': 1.3708802318573, 'latency_p50': 1.3603469133377075, 'latency_p90': 1.5165604829788208}, {'batch_size': 10, 'throughput': 5.300075935080797, 'latency_mean': 1.8633000934123993, 'latency_p50': 1.8747371435165405, 'latency_p90': 2.1170509815216065}, {'batch_size': 15, 'throughput': 6.310857310859342, 'latency_mean': 2.3372885632514953, 'latency_p50': 2.3379814624786377, 'latency_p90': 2.66397545337677}, {'batch_size': 20, 'throughput': 6.841896512266526, 'latency_mean': 2.880969910621643, 'latency_p50': 2.8723865747451782, 'latency_p90': 3.360393667221069}, {'batch_size': 25, 'throughput': 7.057378860055119, 'latency_mean': 3.4525426399707793, 'latency_p50': 3.426103711128235, 'latency_p90': 3.946131443977356}, {'batch_size': 30, 'throughput': 7.306987391708853, 'latency_mean': 4.009289400577545, 'latency_p50': 4.011451363563538, 'latency_p90': 4.716992020606995}, {'batch_size': 35, 'throughput': 7.605869350735863, 'latency_mean': 4.500929230451584, 'latency_p50': 4.436274170875549, 'latency_p90': 5.316530179977417}, {'batch_size': 40, 'throughput': 7.508583000536322, 'latency_mean': 5.155414263010025, 'latency_p50': 5.188506007194519, 'latency_p90': 6.029833436012268}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: fengfengzi14-mistral-testg3_v1

is_internal_developer: False

language_model: fengfengzi14/mistral_testG3

model_size: 7B

ranking_group: single

throughput_3p7s: 7.36

us_pacific_date: 2024-09-06

win_ratio: 0.300878582745211

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': '<|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-v1-mkmlizer
Waiting for job on fengfengzi14-mistral-testg3-v1-mkmlizer to finish
fengfengzi14-mistral-testg3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fengfengzi14-mistral-testg3-v1-mkmlizer: ║     _____            __           __                                ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║       /___/                                                         ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  belonging to:                                                      ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ║                                                                     ║
fengfengzi14-mistral-testg3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fengfengzi14-mistral-testg3-v1-mkmlizer: Downloaded to shared memory in 27.825s
fengfengzi14-mistral-testg3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl1p3f3fi, device:0
fengfengzi14-mistral-testg3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fengfengzi14-mistral-testg3-v1-mkmlizer: quantized model in 18.308s
fengfengzi14-mistral-testg3-v1-mkmlizer: Processed model fengfengzi14/mistral_testG3 in 46.134s
fengfengzi14-mistral-testg3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fengfengzi14-mistral-testg3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1
fengfengzi14-mistral-testg3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1/config.json
fengfengzi14-mistral-testg3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1/special_tokens_map.json
fengfengzi14-mistral-testg3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1/tokenizer_config.json
fengfengzi14-mistral-testg3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1/tokenizer.model
fengfengzi14-mistral-testg3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1/tokenizer.json
fengfengzi14-mistral-testg3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fengfengzi14-mistral-testg3-v1/flywheel_model.0.safetensors
fengfengzi14-mistral-testg3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 46.67it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:05, 54.89it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 60.95it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 75.88it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 76.95it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 77.16it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 76.67it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 76.38it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 70.63it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 68.45it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:09, 19.61it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 24.01it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 30.83it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:04, 38.05it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 45.02it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:02, 56.50it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 62.59it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:01, 63.54it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:01, 61.55it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 64.78it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 70.78it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 69.72it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:04, 19.41it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:03, 22.99it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:02, 29.31it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 35.35it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 40.78it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 47.57it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 53.78it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 54.07it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 61.18it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 67.88it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 16.98it/s]
                                                            
Job fengfengzi14-mistral-testg3-v1-mkmlizer completed after 64.24s with status: succeeded
Stopping job with name fengfengzi14-mistral-testg3-v1-mkmlizer
Pipeline stage MKMLizer completed in 65.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service fengfengzi14-mistral-testg3-v1
Waiting for inference service fengfengzi14-mistral-testg3-v1 to be ready
Failed to get response for submission blend_lobuf_2024-08-22: ('http://zonemercy-taurus-edit-v1-1e5-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41780->127.0.0.1:8080: read: connection reset by peer\n')
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service fengfengzi14-mistral-testg3-v1 ready after 150.6345283985138s
Pipeline stage MKMLDeployer completed in 152.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2933037281036377s
Received healthy response to inference request in 0.8481991291046143s
Received healthy response to inference request in 1.0183076858520508s
Received healthy response to inference request in 1.0508718490600586s
Received healthy response to inference request in 1.3687620162963867s
5 requests
0 failed requests
5th percentile: 0.8822208404541015
10th percentile: 0.9162425518035888
20th percentile: 0.9842859745025635
30th percentile: 1.0248205184936523
40th percentile: 1.0378461837768556
50th percentile: 1.0508718490600586
60th percentile: 1.1478446006774903
70th percentile: 1.2448173522949217
80th percentile: 1.3083953857421875
90th percentile: 1.338578701019287
95th percentile: 1.353670358657837
99th percentile: 1.3657436847686768
mean time: 1.1158888816833497
Pipeline stage StressChecker completed in 7.91s
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 5.35s
Shutdown handler de-registered
fengfengzi14-mistral-testg3_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service fengfengzi14-mistral-testg3-v1-profiler
Waiting for inference service fengfengzi14-mistral-testg3-v1-profiler to be ready
Inference service fengfengzi14-mistral-testg3-v1-profiler ready after 150.359797000885s
Pipeline stage MKMLProfilerDeployer completed in 150.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/fengfengzi14-mistral702cf41e436210568e206c317ac5e99d-deplo22ppg:/code/chaiverse_profiler_1725681518 --namespace tenant-chaiml-guanaco
kubectl exec -it fengfengzi14-mistral702cf41e436210568e206c317ac5e99d-deplo22ppg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725681518 && 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_1725681518/summary.json'
kubectl exec -it fengfengzi14-mistral702cf41e436210568e206c317ac5e99d-deplo22ppg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725681518/summary.json'
Pipeline stage MKMLProfilerRunner completed in 445.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service fengfengzi14-mistral-testg3-v1-profiler is running
Tearing down inference service fengfengzi14-mistral-testg3-v1-profiler
Service fengfengzi14-mistral-testg3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.63s
Shutdown handler de-registered
fengfengzi14-mistral-testg3_v1 status is now inactive due to auto deactivation removed underperforming models
fengfengzi14-mistral-testg3_v1 status is now torndown due to DeploymentManager action
Deleting key trace2333-mistral-align-8132-v6/special_tokens_map.json from bucket guanaco-mkml-models