sanchuanhehe-adjusted-co_5071

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_5071_v1

model_name: sanchuanhehe-adjusted-co_5071_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T09:08:56+00:00

num_battles: 11161

num_wins: 3504

celo_rating: 1116.66

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_0_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': 1.1073552221783447, 'latency_mean': 0.9029923832416534, 'latency_p50': 0.904621958732605, 'latency_p90': 1.0121314764022826}, {'batch_size': 5, 'throughput': 3.5963545776897226, 'latency_mean': 1.3790056169033051, 'latency_p50': 1.3796027898788452, 'latency_p90': 1.5327705144882202}, {'batch_size': 10, 'throughput': 5.301109674771235, 'latency_mean': 1.8687495946884156, 'latency_p50': 1.8519634008407593, 'latency_p90': 2.126851463317871}, {'batch_size': 15, 'throughput': 6.151827599856404, 'latency_mean': 2.396930910348892, 'latency_p50': 2.3950306177139282, 'latency_p90': 2.75509135723114}, {'batch_size': 20, 'throughput': 6.6957112400455605, 'latency_mean': 2.945816926956177, 'latency_p50': 2.9347742795944214, 'latency_p90': 3.4429563760757445}, {'batch_size': 25, 'throughput': 7.07143422240957, 'latency_mean': 3.4562839114665986, 'latency_p50': 3.4720970392227173, 'latency_p90': 4.035526585578919}, {'batch_size': 30, 'throughput': 7.267949809277365, 'latency_mean': 4.037582540512085, 'latency_p50': 4.0160157680511475, 'latency_p90': 4.73197660446167}, {'batch_size': 35, 'throughput': 7.485928001907721, 'latency_mean': 4.578929296731949, 'latency_p50': 4.487242817878723, 'latency_p90': 5.414169859886169}, {'batch_size': 40, 'throughput': 7.453479879972841, 'latency_mean': 5.2015116810798645, 'latency_p50': 5.164644241333008, 'latency_p90': 6.147909140586853}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_5071_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_0_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.32

us_pacific_date: 2024-09-17

win_ratio: 0.3139503628707105

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-5071-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-5071-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', '')
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_hokok_2024-09-09: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: Downloaded to shared memory in 30.034s
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfmcbeq5p, device:0
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: quantized model in 18.167s
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_0_le in 48.200s
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1/config.json
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1/tokenizer.model
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1/tokenizer.json
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-5071-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 53.08it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 81.64it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 75.54it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 76.79it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 73.28it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 74.33it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 72.63it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 71.56it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 75.16it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 75.25it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:08, 21.63it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 27.51it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:05, 32.71it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 40.23it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:03, 46.58it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 51.28it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 56.34it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 60.70it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 64.87it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 66.36it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 71.42it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:03, 23.13it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 27.43it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 33.58it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 40.85it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 48.71it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 53.04it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 58.55it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 61.90it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 62.63it/s]
Loading 0:  98%|█████████▊| 285/291 [00:05<00:00, 73.47it/s]
                                                            
Job sanchuanhehe-adjusted-co-5071-v1-mkmlizer completed after 73.93s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-5071-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.18s
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-5071-v1
Waiting for inference service sanchuanhehe-adjusted-co-5071-v1 to be ready
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', '')
Inference service sanchuanhehe-adjusted-co-5071-v1 ready after 171.32840299606323s
Pipeline stage MKMLDeployer completed in 171.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2393934726715088s
Received healthy response to inference request in 3.506434440612793s
Received healthy response to inference request in 1.4443457126617432s
Received healthy response to inference request in 0.7711195945739746s
Received healthy response to inference request in 0.449084997177124s
5 requests
0 failed requests
5th percentile: 0.5134919166564942
10th percentile: 0.5778988361358642
20th percentile: 0.7067126750946044
30th percentile: 0.8647743701934815
40th percentile: 1.052083921432495
50th percentile: 1.2393934726715088
60th percentile: 1.3213743686676025
70th percentile: 1.4033552646636962
80th percentile: 1.8567634582519534
90th percentile: 2.6815989494323733
95th percentile: 3.0940166950225825
99th percentile: 3.423950891494751
mean time: 1.4820756435394287
Pipeline stage StressChecker completed in 8.69s
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 6.20s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5071_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-5071-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-5071-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-5071-v1-profiler ready after 170.39596247673035s
Pipeline stage MKMLProfilerDeployer completed in 170.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste8d6eb3e0949d67e87bcba959eedcc000-deplorv6sp:/code/chaiverse_profiler_1726564611 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste8d6eb3e0949d67e87bcba959eedcc000-deplorv6sp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726564611 && 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_1726564611/summary.json'
kubectl exec -it sanchuanhehe-adjuste8d6eb3e0949d67e87bcba959eedcc000-deplorv6sp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726564611/summary.json'
Pipeline stage MKMLProfilerRunner completed in 450.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-5071-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-5071-v1-profiler
Service sanchuanhehe-adjusted-co-5071-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.89s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5071_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_5071_v1 status is now torndown due to DeploymentManager action