sanchuanhehe-adjusted-co_4823

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_4823_v1

model_name: sanchuanhehe-adjusted-co_4823_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:05:47+00:00

num_battles: 11546

num_wins: 4645

celo_rating: 1106.89

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_4_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': 1.1329481391667349, 'latency_mean': 0.8825933134555817, 'latency_p50': 0.8816156387329102, 'latency_p90': 0.9885868549346923}, {'batch_size': 5, 'throughput': 3.643884655518439, 'latency_mean': 1.3631253039836884, 'latency_p50': 1.368309497833252, 'latency_p90': 1.5194429159164429}, {'batch_size': 10, 'throughput': 5.351392937175998, 'latency_mean': 1.8483013343811034, 'latency_p50': 1.8536573648452759, 'latency_p90': 2.0748010158538817}, {'batch_size': 15, 'throughput': 6.354247450109346, 'latency_mean': 2.3171352350711825, 'latency_p50': 2.3026063442230225, 'latency_p90': 2.6742649555206297}, {'batch_size': 20, 'throughput': 6.840180978331514, 'latency_mean': 2.863482121229172, 'latency_p50': 2.8537672758102417, 'latency_p90': 3.2567506790161134}, {'batch_size': 25, 'throughput': 7.193791278493009, 'latency_mean': 3.397074135541916, 'latency_p50': 3.399193525314331, 'latency_p90': 4.002023673057556}, {'batch_size': 30, 'throughput': 7.520227951459174, 'latency_mean': 3.8947024965286254, 'latency_p50': 3.870347261428833, 'latency_p90': 4.660330796241761}, {'batch_size': 35, 'throughput': 7.571476056703285, 'latency_mean': 4.514836866855621, 'latency_p50': 4.475244045257568, 'latency_p90': 5.372410464286804}, {'batch_size': 40, 'throughput': 7.603169356452411, 'latency_mean': 5.129647097587585, 'latency_p50': 5.080675363540649, 'latency_p90': 5.913354682922363}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_4823_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_4_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.58

us_pacific_date: 2024-09-17

win_ratio: 0.40230382816559845

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-4823-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-4823-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-4823-v1-mkmlizer: Downloaded to shared memory in 31.132s
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy_1izqes, device:0
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: quantized model in 17.984s
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_4_le in 49.116s
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1/config.json
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1/tokenizer.model
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1/tokenizer.json
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-4823-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-4823-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.79it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 57.84it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 64.77it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 65.32it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 70.88it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 73.57it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 73.02it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 73.36it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 73.04it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 70.00it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 72.74it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:09, 20.60it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:07, 23.56it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 27.62it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 33.62it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 39.48it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 44.22it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 51.02it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:02, 60.57it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 63.07it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 69.34it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 73.43it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 76.10it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:04, 18.32it/s]
Loading 0:  74%|███████▍  | 215/291 [00:05<00:03, 24.89it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 30.42it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 38.01it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 44.97it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 52.52it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 57.56it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 62.67it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 66.58it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 70.72it/s]
                                                            
Job sanchuanhehe-adjusted-co-4823-v1-mkmlizer completed after 74.14s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-4823-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-4823-v1
Waiting for inference service sanchuanhehe-adjusted-co-4823-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
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-4823-v1 ready after 171.98213458061218s
Pipeline stage MKMLDeployer completed in 172.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3887383937835693s
Received healthy response to inference request in 1.7788281440734863s
Received healthy response to inference request in 0.7599806785583496s
Received healthy response to inference request in 0.5963191986083984s
Received healthy response to inference request in 1.9100770950317383s
5 requests
0 failed requests
5th percentile: 0.6290514945983887
10th percentile: 0.6617837905883789
20th percentile: 0.7272483825683593
30th percentile: 0.8857322216033935
40th percentile: 1.1372353076934816
50th percentile: 1.3887383937835693
60th percentile: 1.5447742938995361
70th percentile: 1.700810194015503
80th percentile: 1.8050779342651366
90th percentile: 1.8575775146484375
95th percentile: 1.883827304840088
99th percentile: 1.9048271369934082
mean time: 1.2867887020111084
Pipeline stage StressChecker completed in 7.40s
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 6.79s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_4823_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-4823-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-4823-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-4823-v1-profiler ready after 200.47921776771545s
Pipeline stage MKMLProfilerDeployer completed in 201.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustea969fa479c635cb0d74ca8fba73e25e1-deplonkp6b:/code/chaiverse_profiler_1726578856 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustea969fa479c635cb0d74ca8fba73e25e1-deplonkp6b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578856 && 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_1726578856/summary.json'
kubectl exec -it sanchuanhehe-adjustea969fa479c635cb0d74ca8fba73e25e1-deplonkp6b --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578856/summary.json'
Pipeline stage MKMLProfilerRunner completed in 441.20s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-4823-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-4823-v1-profiler
Service sanchuanhehe-adjusted-co-4823-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.00s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_4823_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_4823_v1 status is now torndown due to DeploymentManager action