sanchuanhehe-large-dataset

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-large-dataset_v1

model_name: sanchuanhehe-large-dataset_v1

model_group: sanchuanhehe/large_datas

status: torndown

timestamp: 2024-09-24T13:10:26+00:00

num_battles: 3750

num_wins: 1645

celo_rating: 1210.1

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/large_dataset

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8652569051398076, 'latency_mean': 1.155630089044571, 'latency_p50': 1.1567516326904297, 'latency_p90': 1.2752554893493653}, {'batch_size': 4, 'throughput': 1.8425662921490866, 'latency_mean': 2.1582520103454588, 'latency_p50': 2.1622793674468994, 'latency_p90': 2.3874128580093386}, {'batch_size': 5, 'throughput': 1.9643235617215922, 'latency_mean': 2.5352153527736663, 'latency_p50': 2.531400442123413, 'latency_p90': 2.853459048271179}, {'batch_size': 8, 'throughput': 2.124577490966084, 'latency_mean': 3.7384770572185517, 'latency_p50': 3.7314828634262085, 'latency_p90': 4.211713576316834}, {'batch_size': 10, 'throughput': 2.160333730578786, 'latency_mean': 4.592992310523987, 'latency_p50': 4.59746253490448, 'latency_p90': 5.168446135520935}, {'batch_size': 12, 'throughput': 2.19018973788342, 'latency_mean': 5.437557703256607, 'latency_p50': 5.404683709144592, 'latency_p90': 6.171350955963135}, {'batch_size': 15, 'throughput': 2.163259601802687, 'latency_mean': 6.8493396139144895, 'latency_p50': 6.887260794639587, 'latency_p90': 7.62942214012146}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-large-dataset_v1

ineligible_reason: num_battles<5000

is_internal_developer: False

language_model: sanchuanhehe/large_dataset

model_size: 8B

ranking_group: single

throughput_3p7s: 2.14

us_pacific_date: 2024-09-24

win_ratio: 0.43866666666666665

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': 1024, 'best_of': 8, '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-large-dataset-v1-mkmlizer
Waiting for job on sanchuanhehe-large-dataset-v1-mkmlizer to finish
sanchuanhehe-large-dataset-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-large-dataset-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-large-dataset-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-large-dataset-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-large-dataset-v1-mkmlizer: Downloaded to shared memory in 35.920s
sanchuanhehe-large-dataset-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2usc_kve, device:0
sanchuanhehe-large-dataset-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-large-dataset-v1-mkmlizer: quantized model in 25.391s
sanchuanhehe-large-dataset-v1-mkmlizer: Processed model sanchuanhehe/large_dataset in 61.312s
sanchuanhehe-large-dataset-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-large-dataset-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-large-dataset-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-large-dataset-v1
sanchuanhehe-large-dataset-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-large-dataset-v1/special_tokens_map.json
sanchuanhehe-large-dataset-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-large-dataset-v1/config.json
sanchuanhehe-large-dataset-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-large-dataset-v1/tokenizer_config.json
sanchuanhehe-large-dataset-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-large-dataset-v1/tokenizer.json
sanchuanhehe-large-dataset-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-large-dataset-v1/flywheel_model.0.safetensors
sanchuanhehe-large-dataset-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.98it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 68.07it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 86.94it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 87.71it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 87.76it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 85.07it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 85.35it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 85.75it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 20.76it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:06, 28.03it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 36.01it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 49.42it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 57.55it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 65.94it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 69.40it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 73.58it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 77.17it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 24.27it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 34.60it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 42.63it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 54.43it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 60.99it/s]
Loading 0:  88%|████████▊ | 256/291 [00:04<00:00, 72.72it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 75.45it/s]
Loading 0:  96%|█████████▌| 278/291 [00:05<00:00, 78.72it/s]
Loading 0:  99%|█████████▉| 288/291 [00:05<00:00, 47.95it/s]
                                                            
Job sanchuanhehe-large-dataset-v1-mkmlizer completed after 85.51s with status: succeeded
Stopping job with name sanchuanhehe-large-dataset-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-large-dataset-v1
Waiting for inference service sanchuanhehe-large-dataset-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
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-large-dataset-v1 ready after 202.6522295475006s
Pipeline stage MKMLDeployer completed in 203.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.381859064102173s
Received healthy response to inference request in 1.5982191562652588s
Received healthy response to inference request in 1.3955864906311035s
Received healthy response to inference request in 3.6712615489959717s
Received healthy response to inference request in 1.8615121841430664s
5 requests
0 failed requests
5th percentile: 1.4361130237579345
10th percentile: 1.4766395568847657
20th percentile: 1.5576926231384278
30th percentile: 1.6508777618408204
40th percentile: 1.7561949729919433
50th percentile: 1.8615121841430664
60th percentile: 2.4696509361267087
70th percentile: 3.0777896881103515
80th percentile: 3.4397395610809327
90th percentile: 3.555500555038452
95th percentile: 3.613381052017212
99th percentile: 3.65968544960022
mean time: 2.3816876888275145
Pipeline stage StressChecker completed in 13.08s
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 5.54s
Shutdown handler de-registered
sanchuanhehe-large-dataset_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-large-dataset-v1-profiler
Waiting for inference service sanchuanhehe-large-dataset-v1-profiler to be ready
Inference service sanchuanhehe-large-dataset-v1-profiler ready after 200.4535870552063s
Pipeline stage MKMLProfilerDeployer completed in 200.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-large-d8f177edbda2ce1d1572c1253c184ece7-deplo9rzdb:/code/chaiverse_profiler_1727183996 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-large-d8f177edbda2ce1d1572c1253c184ece7-deplo9rzdb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727183996 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727183996/summary.json'
kubectl exec -it sanchuanhehe-large-d8f177edbda2ce1d1572c1253c184ece7-deplo9rzdb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727183996/summary.json'
Pipeline stage MKMLProfilerRunner completed in 817.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-large-dataset-v1-profiler is running
Tearing down inference service sanchuanhehe-large-dataset-v1-profiler
Service sanchuanhehe-large-dataset-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.13s
Shutdown handler de-registered
sanchuanhehe-large-dataset_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-large-dataset_v1 status is now torndown due to DeploymentManager action