sanchuanhehe-adjusted-co_4239

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_4239_v1

model_name: sanchuanhehe-adjusted-co_4239_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:15:20+00:00

num_battles: 10588

num_wins: 4286

celo_rating: 1108.15

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_34_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': 1.1293582639491058, 'latency_mean': 0.8853969407081604, 'latency_p50': 0.8824883699417114, 'latency_p90': 0.98766610622406}, {'batch_size': 5, 'throughput': 3.6977415366206277, 'latency_mean': 1.3388858330249787, 'latency_p50': 1.3269085884094238, 'latency_p90': 1.5138675212860107}, {'batch_size': 10, 'throughput': 5.49156015320002, 'latency_mean': 1.8022906744480134, 'latency_p50': 1.7995282411575317, 'latency_p90': 2.0244487047195436}, {'batch_size': 15, 'throughput': 6.3589096603605935, 'latency_mean': 2.3116318368911744, 'latency_p50': 2.3169519901275635, 'latency_p90': 2.5857537269592283}, {'batch_size': 20, 'throughput': 6.910860382925526, 'latency_mean': 2.8405897092819212, 'latency_p50': 2.8380653858184814, 'latency_p90': 3.2595351696014405}, {'batch_size': 25, 'throughput': 7.415093826932763, 'latency_mean': 3.3063002705574034, 'latency_p50': 3.294394612312317, 'latency_p90': 3.832165241241455}, {'batch_size': 30, 'throughput': 7.503467799034522, 'latency_mean': 3.8990079307556154, 'latency_p50': 3.8630391359329224, 'latency_p90': 4.632411813735961}, {'batch_size': 35, 'throughput': 7.797608607363359, 'latency_mean': 4.382347178459168, 'latency_p50': 4.364139437675476, 'latency_p90': 5.174436163902283}, {'batch_size': 40, 'throughput': 7.737559741867225, 'latency_mean': 4.998589814901352, 'latency_p50': 4.9218926429748535, 'latency_p90': 5.843489432334898}, {'batch_size': 45, 'throughput': 7.674798267754871, 'latency_mean': 5.623025246858597, 'latency_p50': 5.6762412786483765, 'latency_p90': 6.5943379402160645}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_4239_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_34_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.65

us_pacific_date: 2024-09-17

win_ratio: 0.40479788439743103

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-4239-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-4239-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: Downloaded to shared memory in 39.633s
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_b4tf93j, device:0
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: quantized model in 18.645s
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_34_l in 58.278s
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1/config.json
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1/tokenizer.model
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1/tokenizer.json
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4239-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-4239-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 44.42it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 63.29it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 66.64it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 66.51it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 65.60it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 66.50it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 67.33it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 68.01it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 72.23it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 73.97it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 73.40it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:08, 21.15it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 25.07it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 31.18it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:04, 37.05it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 42.60it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 47.02it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 50.74it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 54.60it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 57.65it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 59.40it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 61.64it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 62.14it/s]
Loading 0:  72%|███████▏  | 209/291 [00:05<00:04, 18.97it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:03, 20.87it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 27.36it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 34.05it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 39.91it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 45.80it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 50.94it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 53.42it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 57.09it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 60.12it/s]
                                                            
Job sanchuanhehe-adjusted-co-4239-v1-mkmlizer completed after 84.71s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-4239-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-4239-v1
Waiting for inference service sanchuanhehe-adjusted-co-4239-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', '')
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-4239-v1 ready after 191.57243633270264s
Pipeline stage MKMLDeployer completed in 191.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2558221817016602s
Received healthy response to inference request in 2.0925111770629883s
Received healthy response to inference request in 1.4304077625274658s
Received healthy response to inference request in 2.0593228340148926s
Received healthy response to inference request in 1.1408393383026123s
5 requests
0 failed requests
5th percentile: 1.1638359069824218
10th percentile: 1.1868324756622315
20th percentile: 1.2328256130218507
30th percentile: 1.2907392978668213
40th percentile: 1.3605735301971436
50th percentile: 1.4304077625274658
60th percentile: 1.6819737911224364
70th percentile: 1.9335398197174072
80th percentile: 2.065960502624512
90th percentile: 2.07923583984375
95th percentile: 2.085873508453369
99th percentile: 2.0911836433410644
mean time: 1.5957806587219239
Pipeline stage StressChecker completed in 8.61s
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 3.76s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_4239_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 0.12s
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-4239-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-4239-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-4239-v1-profiler ready after 200.45153093338013s
Pipeline stage MKMLProfilerDeployer completed in 200.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustee8214a6ac8b5ba40530965a5307d4544-deploqz9kv:/code/chaiverse_profiler_1726579466 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustee8214a6ac8b5ba40530965a5307d4544-deploqz9kv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579466 && 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_1726579466/summary.json'
kubectl exec -it sanchuanhehe-adjustee8214a6ac8b5ba40530965a5307d4544-deploqz9kv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579466/summary.json'
Pipeline stage MKMLProfilerRunner completed in 464.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-4239-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-4239-v1-profiler
Service sanchuanhehe-adjusted-co-4239-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.93s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_4239_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_4239_v1 status is now torndown due to DeploymentManager action