sanchuanhehe-adjusted-co_5071

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_5071_v2

model_name: sanchuanhehe-adjusted-co_5071_v2

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:03:28+00:00

num_battles: 10251

num_wins: 4164

celo_rating: 1111.39

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': 1.1127874186208981, 'latency_mean': 0.8985426568984985, 'latency_p50': 0.900354266166687, 'latency_p90': 1.0075790643692017}, {'batch_size': 5, 'throughput': 3.6722938389465036, 'latency_mean': 1.3545769703388215, 'latency_p50': 1.3453233242034912, 'latency_p90': 1.523691749572754}, {'batch_size': 10, 'throughput': 5.347631648042611, 'latency_mean': 1.8482198345661163, 'latency_p50': 1.8487882614135742, 'latency_p90': 2.1070674896240233}, {'batch_size': 15, 'throughput': 6.294540041365967, 'latency_mean': 2.34950736284256, 'latency_p50': 2.3468313217163086, 'latency_p90': 2.6714754581451414}, {'batch_size': 20, 'throughput': 6.813283510409281, 'latency_mean': 2.883313740491867, 'latency_p50': 2.877410650253296, 'latency_p90': 3.2895159006118773}, {'batch_size': 25, 'throughput': 7.218319786612744, 'latency_mean': 3.401315085887909, 'latency_p50': 3.3509734869003296, 'latency_p90': 3.97930645942688}, {'batch_size': 30, 'throughput': 7.423285773796895, 'latency_mean': 3.957360512018204, 'latency_p50': 3.971357226371765, 'latency_p90': 4.591579341888427}, {'batch_size': 35, 'throughput': 7.595798643416973, 'latency_mean': 4.484364502429962, 'latency_p50': 4.458585739135742, 'latency_p90': 5.413942551612854}, {'batch_size': 40, 'throughput': 7.5327158875652485, 'latency_mean': 5.139929218292236, 'latency_p50': 5.078407049179077, 'latency_p90': 6.102287435531617}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_5071_v2

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_0_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.48

us_pacific_date: 2024-09-17

win_ratio: 0.40620427275387766

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-v2-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-5071-v2-mkmlizer to finish
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: Downloaded to shared memory in 18.060s
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1yroywch, device:0
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: quantized model in 17.618s
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: Processed model sanchuanhehe/adjusted_config_0_le in 35.679s
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2/config.json
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2/tokenizer_config.json
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2/special_tokens_map.json
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2/tokenizer.model
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2/tokenizer.json
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5071-v2/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-5071-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 54.83it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 86.53it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 86.47it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 79.54it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 80.47it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:02, 86.30it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:02, 81.79it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:02, 79.74it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 84.81it/s]
Loading 0:  33%|███▎      | 96/291 [00:01<00:02, 85.37it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:08, 20.90it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:06, 26.17it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 34.52it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:03, 40.35it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:02, 50.14it/s]
Loading 0:  52%|█████▏    | 150/291 [00:02<00:02, 53.29it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:02, 58.22it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 60.52it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 61.71it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:01, 72.74it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 71.85it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:03, 22.89it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 26.93it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 36.82it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 43.04it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 49.25it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 55.50it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 59.32it/s]
Loading 0:  92%|█████████▏| 269/291 [00:05<00:00, 67.71it/s]
Loading 0:  96%|█████████▌| 278/291 [00:05<00:00, 65.43it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 64.76it/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', '')
Job sanchuanhehe-adjusted-co-5071-v2-mkmlizer completed after 65.87s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-5071-v2-mkmlizer
Pipeline stage MKMLizer completed in 69.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.37s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-5071-v2
Waiting for inference service sanchuanhehe-adjusted-co-5071-v2 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
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-5071-v2 ready after 180.6838457584381s
Pipeline stage MKMLDeployer completed in 181.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.0512700080871582s
Received healthy response to inference request in 2.99853253364563s
Received healthy response to inference request in 0.5876493453979492s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 0.3945894241333008s
Received healthy response to inference request in 0.573911190032959s
5 requests
0 failed requests
5th percentile: 0.4304537773132324
10th percentile: 0.46631813049316406
20th percentile: 0.5380468368530273
30th percentile: 0.576658821105957
40th percentile: 0.5821540832519532
50th percentile: 0.5876493453979492
60th percentile: 0.7730976104736328
70th percentile: 0.9585458755493164
80th percentile: 1.4407225131988528
90th percentile: 2.2196275234222416
95th percentile: 2.6090800285339353
99th percentile: 2.920642032623291
mean time: 1.1211905002593994
Pipeline stage StressChecker completed in 8.07s
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 7.66s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5071_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-5071-v2-profiler
Waiting for inference service sanchuanhehe-adjusted-co-5071-v2-profiler to be ready
Inference service sanchuanhehe-adjusted-co-5071-v2-profiler ready after 180.44820141792297s
Pipeline stage MKMLProfilerDeployer completed in 180.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustee01dd0478544c6e4099423afcb2432f3-deplojgbbw:/code/chaiverse_profiler_1726578700 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustee01dd0478544c6e4099423afcb2432f3-deplojgbbw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578700 && 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_1726578700/summary.json'
kubectl exec -it sanchuanhehe-adjustee01dd0478544c6e4099423afcb2432f3-deplojgbbw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578700/summary.json'
Pipeline stage MKMLProfilerRunner completed in 445.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-5071-v2-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-5071-v2-profiler
Service sanchuanhehe-adjusted-co-5071-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.93s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5071_v2 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_5071_v2 status is now torndown due to DeploymentManager action