sanchuanhehe-adjusted-co_183

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_183_v1

model_name: sanchuanhehe-adjusted-co_183_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:07:23+00:00

num_battles: 10005

num_wins: 4108

celo_rating: 1111.99

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_9_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': 1.1124477139066122, 'latency_mean': 0.8988421201705933, 'latency_p50': 0.8963544368743896, 'latency_p90': 1.005391001701355}, {'batch_size': 5, 'throughput': 3.600752470098987, 'latency_mean': 1.377300077676773, 'latency_p50': 1.373733401298523, 'latency_p90': 1.5470599889755248}, {'batch_size': 10, 'throughput': 5.330115739001041, 'latency_mean': 1.8578532087802886, 'latency_p50': 1.866133451461792, 'latency_p90': 2.0595995426177978}, {'batch_size': 15, 'throughput': 6.2321874918602225, 'latency_mean': 2.3702123165130615, 'latency_p50': 2.3625375032424927, 'latency_p90': 2.71474871635437}, {'batch_size': 20, 'throughput': 6.703853574922449, 'latency_mean': 2.927456970214844, 'latency_p50': 2.8910467624664307, 'latency_p90': 3.30747447013855}, {'batch_size': 25, 'throughput': 7.018124096188149, 'latency_mean': 3.4862313759326935, 'latency_p50': 3.494002342224121, 'latency_p90': 3.9959943294525146}, {'batch_size': 30, 'throughput': 7.425316756473618, 'latency_mean': 3.9560701656341553, 'latency_p50': 4.0208916664123535, 'latency_p90': 4.788630652427673}, {'batch_size': 35, 'throughput': 7.548409214273133, 'latency_mean': 4.52518838763237, 'latency_p50': 4.454623222351074, 'latency_p90': 5.516009473800659}, {'batch_size': 40, 'throughput': 7.401418625941698, 'latency_mean': 5.21425375699997, 'latency_p50': 5.199791789054871, 'latency_p90': 6.122376132011413}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_183_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_9_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.37

us_pacific_date: 2024-09-17

win_ratio: 0.41059470264867565

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-183-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-183-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-183-v1-mkmlizer: Downloaded to shared memory in 30.708s
sanchuanhehe-adjusted-co-183-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_qm4tlsh, device:0
sanchuanhehe-adjusted-co-183-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-183-v1-mkmlizer: quantized model in 17.770s
sanchuanhehe-adjusted-co-183-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_9_le in 48.478s
sanchuanhehe-adjusted-co-183-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-183-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-183-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1
sanchuanhehe-adjusted-co-183-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1/config.json
sanchuanhehe-adjusted-co-183-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-183-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-183-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1/tokenizer.model
sanchuanhehe-adjusted-co-183-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1/tokenizer.json
sanchuanhehe-adjusted-co-183-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-183-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 43.12it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:05, 54.73it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 59.74it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 68.92it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:03, 78.25it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 87.48it/s]
Loading 0:  24%|██▎       | 69/291 [00:00<00:02, 92.59it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 84.79it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 91.43it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:07, 24.78it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:06, 28.98it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 37.78it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:03, 40.77it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 44.71it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:02, 54.19it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 60.05it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:01, 67.56it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:01, 71.47it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 80.36it/s]
Loading 0:  70%|██████▉   | 203/291 [00:03<00:01, 84.97it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:03, 24.96it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 28.84it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 34.80it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 41.47it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 48.58it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.75it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 61.44it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 69.77it/s]
Loading 0:  98%|█████████▊| 284/291 [00:05<00:00, 72.54it/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
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
Job sanchuanhehe-adjusted-co-183-v1-mkmlizer completed after 75.54s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-183-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.65s
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-183-v1
Waiting for inference service sanchuanhehe-adjusted-co-183-v1 to be ready
Inference service sanchuanhehe-adjusted-co-183-v1 ready after 181.21297645568848s
Pipeline stage MKMLDeployer completed in 181.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.1029648780822754s
Received healthy response to inference request in 1.1904783248901367s
Received healthy response to inference request in 1.2624874114990234s
Received healthy response to inference request in 1.1952886581420898s
Received healthy response to inference request in 1.6896436214447021s
5 requests
0 failed requests
5th percentile: 1.1204675674438476
10th percentile: 1.13797025680542
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
20th percentile: 1.1729756355285645
30th percentile: 1.1914403915405274
40th percentile: 1.1933645248413085
50th percentile: 1.1952886581420898
60th percentile: 1.2221681594848632
70th percentile: 1.2490476608276366
80th percentile: 1.3479186534881593
90th percentile: 1.5187811374664306
95th percentile: 1.6042123794555663
99th percentile: 1.672557373046875
mean time: 1.2881725788116456
Pipeline stage StressChecker completed in 7.46s
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 6.69s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_183_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 0.11s
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-183-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-183-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-183-v1-profiler ready after 190.51923823356628s
Pipeline stage MKMLProfilerDeployer completed in 190.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste011b9911adc615023738c2a9eb8466ff-deploqhhfs:/code/chaiverse_profiler_1726578943 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste011b9911adc615023738c2a9eb8466ff-deploqhhfs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578943 && 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_1726578943/summary.json'
kubectl exec -it sanchuanhehe-adjuste011b9911adc615023738c2a9eb8466ff-deploqhhfs --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578943/summary.json'
Pipeline stage MKMLProfilerRunner completed in 448.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-183-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-183-v1-profiler
Service sanchuanhehe-adjusted-co-183-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_183_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_183_v1 status is now torndown due to DeploymentManager action