developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_1766_v1
model_name: sanchuanhehe-adjusted-co_1766_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:13:40+00:00
num_battles: 10477
num_wins: 4334
celo_rating: 1114.42
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_27_l
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 1.1059227403447902, 'latency_mean': 0.9041565954685211, 'latency_p50': 0.9132115840911865, 'latency_p90': 1.006696105003357}, {'batch_size': 5, 'throughput': 3.6280615183637925, 'latency_mean': 1.3706315636634827, 'latency_p50': 1.3807810544967651, 'latency_p90': 1.5508760690689087}, {'batch_size': 10, 'throughput': 5.228031671199439, 'latency_mean': 1.890338579416275, 'latency_p50': 1.9049348831176758, 'latency_p90': 2.1368538856506345}, {'batch_size': 15, 'throughput': 6.163997053840596, 'latency_mean': 2.4003244721889496, 'latency_p50': 2.4039093255996704, 'latency_p90': 2.7302347660064696}, {'batch_size': 20, 'throughput': 6.705646393327569, 'latency_mean': 2.933160506486893, 'latency_p50': 2.9120854139328003, 'latency_p90': 3.4170151710510255}, {'batch_size': 25, 'throughput': 7.07512510395054, 'latency_mean': 3.4703839194774626, 'latency_p50': 3.455472230911255, 'latency_p90': 3.990977644920349}, {'batch_size': 30, 'throughput': 7.2999573965055635, 'latency_mean': 4.013751472234726, 'latency_p50': 3.9891527891159058, 'latency_p90': 4.705126619338989}, {'batch_size': 35, 'throughput': 7.405694264194355, 'latency_mean': 4.602103327512741, 'latency_p50': 4.591697096824646, 'latency_p90': 5.482331347465514}, {'batch_size': 40, 'throughput': 7.412537316809145, 'latency_mean': 5.234101783037186, 'latency_p50': 5.247318625450134, 'latency_p90': 6.040986084938049}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_1766_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_27_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.33
us_pacific_date: 2024-09-17
win_ratio: 0.41366803474276986
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-1766-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-1766-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: Downloaded to shared memory in 31.681s
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp57xlb8e1, device:0
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: quantized model in 17.745s
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_27_l in 49.426s
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1/config.json
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1/tokenizer.model
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1/tokenizer.json
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1766-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-1766-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 49.75it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 67.54it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 67.46it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 68.34it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 74.31it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:02, 81.88it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 88.08it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:02, 91.07it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 87.50it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 78.80it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:08, 21.78it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 26.79it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:05, 32.60it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:04, 38.57it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:03, 44.10it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 48.35it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 52.16it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 54.60it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:02, 56.37it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 58.63it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 64.01it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:03, 22.36it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 25.42it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 31.43it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 37.85it/s]
Loading 0:  81%|████████  | 236/291 [00:05<00:01, 42.94it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 46.38it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 50.21it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 57.71it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 71.91it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 75.53it/s]
                                                            

Job sanchuanhehe-adjusted-co-1766-v1-mkmlizer completed after 73.13s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-1766-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-1766-v1
Waiting for inference service sanchuanhehe-adjusted-co-1766-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
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
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', '')
Inference service sanchuanhehe-adjusted-co-1766-v1 ready after 190.9330859184265s
Pipeline stage MKMLDeployer completed in 191.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9315009117126465s
Received healthy response to inference request in 1.3609061241149902s
Received healthy response to inference request in 0.5506784915924072s
Received healthy response to inference request in 1.1263372898101807s
Received healthy response to inference request in 0.8145613670349121s
5 requests
0 failed requests
5th percentile: 0.6034550666809082
10th percentile: 0.6562316417694092
20th percentile: 0.7617847919464111
30th percentile: 0.8769165515899658
40th percentile: 1.0016269207000732
50th percentile: 1.1263372898101807
60th percentile: 1.2201648235321045
70th percentile: 1.3139923572540282
80th percentile: 1.4750250816345216
90th percentile: 1.703262996673584
95th percentile: 1.817381954193115
99th percentile: 1.9086771202087403
mean time: 1.1567968368530273
Pipeline stage StressChecker completed in 6.58s
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 5.90s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1766_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-1766-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-1766-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-1766-v1-profiler ready after 190.4305555820465s
Pipeline stage MKMLProfilerDeployer completed in 190.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustea5679f4a6e9791948e536ad65a9258b5-deplodpqk2:/code/chaiverse_profiler_1726579323 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustea5679f4a6e9791948e536ad65a9258b5-deplodpqk2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579323 && 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_1726579323/summary.json'
kubectl exec -it sanchuanhehe-adjustea5679f4a6e9791948e536ad65a9258b5-deplodpqk2 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579323/summary.json'
Pipeline stage MKMLProfilerRunner completed in 452.27s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-1766-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-1766-v1-profiler
Service sanchuanhehe-adjusted-co-1766-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1766_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_1766_v1 status is now torndown due to DeploymentManager action