sao10k-hanami-1-t1

submission_id: sao10k-hanami-1-t1_v2

developer_uid: sao10k

best_of: 8

celo_rating: 1247.51

display_name: Hanami1t1

family_friendly_score: 0.0

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '<|eot_id|>', '\n\n{user_name}', '\nYou:', '<|end_header_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: Sao10K/Hanami-1-t1

latencies: [{'batch_size': 1, 'throughput': 0.8710435011965415, 'latency_mean': 1.1479878389835358, 'latency_p50': 1.1449629068374634, 'latency_p90': 1.2625255346298219}, {'batch_size': 4, 'throughput': 1.8415708266726853, 'latency_mean': 2.1671055030822752, 'latency_p50': 2.1805527210235596, 'latency_p90': 2.374584603309631}, {'batch_size': 5, 'throughput': 1.9912001740260672, 'latency_mean': 2.4966468703746796, 'latency_p50': 2.4990333318710327, 'latency_p90': 2.7966816186904904}, {'batch_size': 8, 'throughput': 2.1771073223088435, 'latency_mean': 3.6534867107868196, 'latency_p50': 3.6359715461730957, 'latency_p90': 4.040697073936462}, {'batch_size': 10, 'throughput': 2.214035009659796, 'latency_mean': 4.485659358501434, 'latency_p50': 4.532679915428162, 'latency_p90': 5.0095432043075565}, {'batch_size': 12, 'throughput': 2.2112150752057556, 'latency_mean': 5.3817428517341614, 'latency_p50': 5.4373674392700195, 'latency_p90': 6.107398056983948}, {'batch_size': 15, 'throughput': 2.1911276518288054, 'latency_mean': 6.753681497573853, 'latency_p50': 6.7663198709487915, 'latency_p90': 7.4796154499053955}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Sao10K/Hanami-1-t1

model_name: Hanami1t1

model_num_parameters: 8030261248.0

model_repo: Sao10K/Hanami-1-t1

model_size: 8B

num_battles: 10246

num_wins: 5052

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 2.19

timestamp: 2024-09-14T10:08:12+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.4930704665235214

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 sao10k-hanami-1-t1-v2-mkmlizer
Waiting for job on sao10k-hanami-1-t1-v2-mkmlizer to finish
sao10k-hanami-1-t1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hanami-1-t1-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-hanami-1-t1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-hanami-1-t1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-hanami-1-t1-v2-mkmlizer: ║       /___/                                                         ║
sao10k-hanami-1-t1-v2-mkmlizer: ║                                                                     ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-hanami-1-t1-v2-mkmlizer: ║                                                                     ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-hanami-1-t1-v2-mkmlizer: ║                                                                     ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-hanami-1-t1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-hanami-1-t1-v2-mkmlizer: ║                                                                     ║
sao10k-hanami-1-t1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-hanami-1-t1-v2-mkmlizer: Downloaded to shared memory in 18.249s
sao10k-hanami-1-t1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5uy4_09b, device:0
sao10k-hanami-1-t1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-hanami-1-t1-v2-mkmlizer: quantized model in 25.463s
sao10k-hanami-1-t1-v2-mkmlizer: Processed model Sao10K/Hanami-1-t1 in 43.713s
sao10k-hanami-1-t1-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hanami-1-t1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hanami-1-t1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hanami-1-t1-v2
sao10k-hanami-1-t1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hanami-1-t1-v2/special_tokens_map.json
sao10k-hanami-1-t1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hanami-1-t1-v2/config.json
sao10k-hanami-1-t1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hanami-1-t1-v2/tokenizer_config.json
sao10k-hanami-1-t1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hanami-1-t1-v2/tokenizer.json
sao10k-hanami-1-t1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hanami-1-t1-v2/flywheel_model.0.safetensors
sao10k-hanami-1-t1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:26,  2.38s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:02,  1.56it/s]
Loading 0:   5%|▍         | 14/291 [00:04<00:59,  4.65it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.51it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.40it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.85it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 22.45it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 29.56it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 31.89it/s]
Loading 0:  21%|██▏       | 62/291 [00:05<00:06, 36.15it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:05, 38.62it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:04, 46.31it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:04, 45.84it/s]
Loading 0:  31%|███       | 89/291 [00:06<00:04, 48.40it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:04, 46.91it/s]
Loading 0:  35%|███▌      | 103/291 [00:06<00:05, 35.43it/s]
Loading 0:  37%|███▋      | 108/291 [00:06<00:04, 37.84it/s]
Loading 0:  39%|███▉      | 114/291 [00:07<00:04, 38.65it/s]
Loading 0:  42%|████▏     | 123/291 [00:07<00:03, 44.06it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:03, 51.50it/s]
Loading 0:  47%|████▋     | 137/291 [00:07<00:03, 47.14it/s]
Loading 0:  49%|████▉     | 143/291 [00:07<00:03, 46.73it/s]
Loading 0:  51%|█████     | 149/291 [00:07<00:02, 48.40it/s]
Loading 0:  53%|█████▎    | 155/291 [00:07<00:03, 44.24it/s]
Loading 0:  55%|█████▍    | 160/291 [00:08<00:03, 43.41it/s]
Loading 0:  57%|█████▋    | 167/291 [00:08<00:02, 48.63it/s]
Loading 0:  59%|█████▉    | 173/291 [00:08<00:02, 47.77it/s]
Loading 0:  62%|██████▏   | 179/291 [00:08<00:02, 50.37it/s]
Loading 0:  64%|██████▍   | 186/291 [00:08<00:02, 48.47it/s]
Loading 0:  67%|██████▋   | 195/291 [00:08<00:01, 50.61it/s]
Loading 0:  70%|███████   | 204/291 [00:08<00:01, 50.73it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 56.06it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 53.68it/s]
Loading 0:  77%|███████▋  | 224/291 [00:09<00:01, 51.72it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 52.52it/s]
Loading 0:  81%|████████  | 236/291 [00:09<00:01, 51.27it/s]
Loading 0:  83%|████████▎ | 242/291 [00:09<00:00, 51.12it/s]
Loading 0:  85%|████████▌ | 248/291 [00:09<00:01, 35.25it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 37.13it/s]
Loading 0:  89%|████████▉ | 260/291 [00:10<00:00, 41.72it/s]
Loading 0:  92%|█████████▏| 267/291 [00:10<00:00, 42.98it/s]
Loading 0:  95%|█████████▍| 276/291 [00:10<00:00, 47.00it/s]
Loading 0:  98%|█████████▊| 285/291 [00:10<00:00, 49.95it/s]
                                                            
Job sao10k-hanami-1-t1-v2-mkmlizer completed after 65.75s with status: succeeded
Stopping job with name sao10k-hanami-1-t1-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.28s
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 sao10k-hanami-1-t1-v2
Waiting for inference service sao10k-hanami-1-t1-v2 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
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 sao10k-hanami-1-t1-v2 ready after 171.17385983467102s
Pipeline stage MKMLDeployer completed in 172.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8839919567108154s
Received healthy response to inference request in 1.6076064109802246s
Received healthy response to inference request in 1.6910369396209717s
Received healthy response to inference request in 1.720243215560913s
Received healthy response to inference request in 1.7394490242004395s
5 requests
0 failed requests
5th percentile: 1.624292516708374
10th percentile: 1.6409786224365235
20th percentile: 1.6743508338928224
30th percentile: 1.69687819480896
40th percentile: 1.7085607051849365
50th percentile: 1.720243215560913
60th percentile: 1.7279255390167236
70th percentile: 1.7356078624725342
80th percentile: 1.7683576107025147
90th percentile: 1.826174783706665
95th percentile: 1.8550833702087401
99th percentile: 1.8782102394104003
mean time: 1.7284655094146728
Pipeline stage StressChecker completed in 11.10s
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 6.16s
Shutdown handler de-registered
sao10k-hanami-1-t1_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-hanami-1-t1-v2-profiler
Waiting for inference service sao10k-hanami-1-t1-v2-profiler to be ready
Inference service sao10k-hanami-1-t1-v2-profiler ready after 170.3780174255371s
Pipeline stage MKMLProfilerDeployer completed in 170.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-hanami-1-t1-v2-profiler-predictor-00001-deployment-2wbmh:/code/chaiverse_profiler_1726308979 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-hanami-1-t1-v2-profiler-predictor-00001-deployment-2wbmh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726308979 && 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_1726308979/summary.json'
kubectl exec -it sao10k-hanami-1-t1-v2-profiler-predictor-00001-deployment-2wbmh --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726308979/summary.json'
Pipeline stage MKMLProfilerRunner completed in 807.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-hanami-1-t1-v2-profiler is running
Tearing down inference service sao10k-hanami-1-t1-v2-profiler
Service sao10k-hanami-1-t1-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.86s
Shutdown handler de-registered
sao10k-hanami-1-t1_v2 status is now inactive due to auto deactivation removed underperforming models
sao10k-hanami-1-t1_v2 status is now torndown due to DeploymentManager action