sanchuanhehe-adjusted-co_2031

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_2031_v1

model_name: sanchuanhehe-adjusted-co_2031_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:04:38+00:00

num_battles: 10035

num_wins: 4201

celo_rating: 1118.83

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_2_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': 1.1070791741144448, 'latency_mean': 0.9032167494297028, 'latency_p50': 0.8971959352493286, 'latency_p90': 1.0035117387771606}, {'batch_size': 5, 'throughput': 3.6321643324218784, 'latency_mean': 1.3715442597866059, 'latency_p50': 1.3763291835784912, 'latency_p90': 1.5211615324020387}, {'batch_size': 10, 'throughput': 5.295659354445435, 'latency_mean': 1.8687536668777467, 'latency_p50': 1.8566985130310059, 'latency_p90': 2.114483284950256}, {'batch_size': 15, 'throughput': 6.2576904877145445, 'latency_mean': 2.3597645807266234, 'latency_p50': 2.3648332357406616, 'latency_p90': 2.680943512916565}, {'batch_size': 20, 'throughput': 6.796455514824249, 'latency_mean': 2.879243531227112, 'latency_p50': 2.8573213815689087, 'latency_p90': 3.356557011604309}, {'batch_size': 25, 'throughput': 7.153047023219591, 'latency_mean': 3.4305569529533386, 'latency_p50': 3.382780432701111, 'latency_p90': 4.011284184455872}, {'batch_size': 30, 'throughput': 7.279006258233465, 'latency_mean': 4.018647552728653, 'latency_p50': 4.010877013206482, 'latency_p90': 4.739235043525696}, {'batch_size': 35, 'throughput': 7.530168490837756, 'latency_mean': 4.542542785406113, 'latency_p50': 4.528897285461426, 'latency_p90': 5.255696892738342}, {'batch_size': 40, 'throughput': 7.466627360232962, 'latency_mean': 5.178724279403687, 'latency_p50': 5.105168700218201, 'latency_p90': 6.044846868515013}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_2031_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_2_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.38

us_pacific_date: 2024-09-17

win_ratio: 0.4186347782760339

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-2031-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-2031-v1-mkmlizer to finish
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
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: Downloaded to shared memory in 30.125s
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmkqvraz1, device:0
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: quantized model in 18.208s
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_2_le in 48.333s
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1/config.json
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1/tokenizer.model
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1/tokenizer.json
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2031-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-2031-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 43.08it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 55.90it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 61.81it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 68.44it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 71.59it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 73.06it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 71.76it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 71.25it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 75.72it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 79.35it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 80.35it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:09, 19.49it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:07, 24.94it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:04, 36.67it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:03, 44.74it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:02, 50.31it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:02, 54.01it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 60.80it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:01, 65.47it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 67.15it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 70.13it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 73.20it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:03, 21.80it/s]
Loading 0:  74%|███████▍  | 216/291 [00:04<00:03, 24.91it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 29.93it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 36.71it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 42.21it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 48.88it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 52.80it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 55.01it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 60.64it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 64.31it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 16.75it/s]
                                                            
Job sanchuanhehe-adjusted-co-2031-v1-mkmlizer completed after 73.66s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-2031-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.43s
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-2031-v1
Waiting for inference service sanchuanhehe-adjusted-co-2031-v1 to be ready
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
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
Inference service sanchuanhehe-adjusted-co-2031-v1 ready after 180.97294807434082s
Pipeline stage MKMLDeployer completed in 182.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3717191219329834s
Received healthy response to inference request in 1.484311580657959s
Received healthy response to inference request in 1.2795131206512451s
Received healthy response to inference request in 1.1449053287506104s
Received healthy response to inference request in 0.4386601448059082s
5 requests
0 failed requests
5th percentile: 0.5799091815948486
10th percentile: 0.721158218383789
20th percentile: 1.0036562919616698
30th percentile: 1.1718268871307373
40th percentile: 1.2256700038909911
50th percentile: 1.2795131206512451
60th percentile: 1.3163955211639404
70th percentile: 1.3532779216766357
80th percentile: 1.3942376136779786
90th percentile: 1.4392745971679688
95th percentile: 1.4617930889129638
99th percentile: 1.47980788230896
mean time: 1.1438218593597411
Pipeline stage StressChecker completed in 6.55s
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 4.88s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2031_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-2031-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-2031-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-2031-v1-profiler ready after 190.4798493385315s
Pipeline stage MKMLProfilerDeployer completed in 190.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste2fb36ffc9ca4e3a0262ea4e2b9443b63-deploznlxn:/code/chaiverse_profiler_1726578785 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste2fb36ffc9ca4e3a0262ea4e2b9443b63-deploznlxn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578785 && 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_1726578785/summary.json'
kubectl exec -it sanchuanhehe-adjuste2fb36ffc9ca4e3a0262ea4e2b9443b63-deploznlxn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578785/summary.json'
Pipeline stage MKMLProfilerRunner completed in 448.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-2031-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-2031-v1-profiler
Service sanchuanhehe-adjusted-co-2031-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.18s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2031_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_2031_v1 status is now torndown due to DeploymentManager action