sanchuanhehe-adjusted-co_1639

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_1639_v1

model_name: sanchuanhehe-adjusted-co_1639_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:14:06+00:00

num_battles: 10891

num_wins: 4538

celo_rating: 1116.96

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_29_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': 1.1225131683912652, 'latency_mean': 0.8907983803749084, 'latency_p50': 0.8969478607177734, 'latency_p90': 0.9834323644638061}, {'batch_size': 5, 'throughput': 3.6901569852237124, 'latency_mean': 1.3480167496204376, 'latency_p50': 1.3352750539779663, 'latency_p90': 1.51624436378479}, {'batch_size': 10, 'throughput': 5.422279751735761, 'latency_mean': 1.8173409509658813, 'latency_p50': 1.8255342245101929, 'latency_p90': 2.06790668964386}, {'batch_size': 15, 'throughput': 6.288591672265117, 'latency_mean': 2.343374487161636, 'latency_p50': 2.34314501285553, 'latency_p90': 2.645467185974121}, {'batch_size': 20, 'throughput': 6.926381190646483, 'latency_mean': 2.844381457567215, 'latency_p50': 2.8308935165405273, 'latency_p90': 3.273938012123108}, {'batch_size': 25, 'throughput': 7.195864774143855, 'latency_mean': 3.398461216688156, 'latency_p50': 3.3883113861083984, 'latency_p90': 3.9838090896606446}, {'batch_size': 30, 'throughput': 7.490387207181621, 'latency_mean': 3.903898124694824, 'latency_p50': 3.863693356513977, 'latency_p90': 4.585810685157776}, {'batch_size': 35, 'throughput': 7.566667812829721, 'latency_mean': 4.5160939145088195, 'latency_p50': 4.484765529632568, 'latency_p90': 5.3743021965026845}, {'batch_size': 40, 'throughput': 7.62743228509901, 'latency_mean': 5.075303742885589, 'latency_p50': 4.995924353599548, 'latency_p90': 5.980029439926147}, {'batch_size': 45, 'throughput': 7.66920953359199, 'latency_mean': 5.623154537677765, 'latency_p50': 5.636238098144531, 'latency_p90': 6.57182207107544}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_1639_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_29_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.56

us_pacific_date: 2024-09-17

win_ratio: 0.416674318244422

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-1639-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-1639-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: Downloaded to shared memory in 31.065s
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvqjfo71z, device:0
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: quantized model in 17.424s
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_29_l in 48.489s
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1/config.json
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1/tokenizer.model
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1/tokenizer.json
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1639-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-1639-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 54.84it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 70.54it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 76.04it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 80.44it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 83.58it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 80.84it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 80.22it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:02, 85.58it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:02, 86.84it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:02, 84.94it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:08, 21.62it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:06, 26.85it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 33.63it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 41.07it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 48.25it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 55.12it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 58.88it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 63.26it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 66.72it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 69.90it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 69.92it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 70.04it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:03, 22.37it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 25.83it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 32.30it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 39.22it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 45.87it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 51.37it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 58.02it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 64.48it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 69.18it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 71.27it/s]
Loading 0: 100%|██████████| 291/291 [00:06<00:00, 17.61it/s]
                                                            
Job sanchuanhehe-adjusted-co-1639-v1-mkmlizer completed after 74.34s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-1639-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.13s
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-1639-v1
Waiting for inference service sanchuanhehe-adjusted-co-1639-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
Inference service sanchuanhehe-adjusted-co-1639-v1 ready after 191.24062514305115s
Pipeline stage MKMLDeployer completed in 191.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2285947799682617s
Received healthy response to inference request in 1.2989552021026611s
Received healthy response to inference request in 1.2617807388305664s
Received healthy response to inference request in 0.7632889747619629s
Received healthy response to inference request in 0.9544985294342041s
5 requests
0 failed requests
5th percentile: 0.8015308856964112
10th percentile: 0.8397727966308594
20th percentile: 0.9162566184997558
30th percentile: 1.0093177795410155
40th percentile: 1.1189562797546386
50th percentile: 1.2285947799682617
60th percentile: 1.2418691635131835
70th percentile: 1.2551435470581054
80th percentile: 1.2692156314849854
90th percentile: 1.2840854167938232
95th percentile: 1.2915203094482421
99th percentile: 1.2974682235717774
mean time: 1.1014236450195312
Pipeline stage StressChecker completed in 6.85s
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 5.89s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1639_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-1639-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-1639-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-1639-v1-profiler ready after 180.4691174030304s
Pipeline stage MKMLProfilerDeployer completed in 180.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste0c1ab0d35354e4ea4d062388d7a3c824-deplovnbqj:/code/chaiverse_profiler_1726579355 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste0c1ab0d35354e4ea4d062388d7a3c824-deplovnbqj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579355 && 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_1726579355/summary.json'
kubectl exec -it sanchuanhehe-adjuste0c1ab0d35354e4ea4d062388d7a3c824-deplovnbqj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579355/summary.json'
Pipeline stage MKMLProfilerRunner completed in 468.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-1639-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-1639-v1-profiler
Service sanchuanhehe-adjusted-co-1639-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.22s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1639_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_1639_v1 status is now torndown due to DeploymentManager action