cycy233-model-8

developer_uid: Luna1040

submission_id: cycy233-model-8_v2

model_name: cycy233-model-8_v2

model_group: cycy233/model-8

status: torndown

timestamp: 2025-02-20T03:33:03+00:00

num_battles: 5609

num_wins: 2655

celo_rating: 1247.16

family_friendly_score: 0.5449999999999999

family_friendly_standard_error: 0.0070423717595707765

submission_type: basic

model_repo: cycy233/model-8

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8470253732869804, 'latency_mean': 1.1805192804336548, 'latency_p50': 1.177919626235962, 'latency_p90': 1.304565668106079}, {'batch_size': 4, 'throughput': 1.7876487746130691, 'latency_mean': 2.2287602365016936, 'latency_p50': 2.2349324226379395, 'latency_p90': 2.4956441640853884}, {'batch_size': 5, 'throughput': 1.907691988192279, 'latency_mean': 2.6033155727386474, 'latency_p50': 2.609919786453247, 'latency_p90': 2.856624889373779}, {'batch_size': 8, 'throughput': 2.1185546239389312, 'latency_mean': 3.7528553903102875, 'latency_p50': 3.761918306350708, 'latency_p90': 4.2752806663513185}, {'batch_size': 10, 'throughput': 2.1596946124805334, 'latency_mean': 4.588086344003678, 'latency_p50': 4.627642631530762, 'latency_p90': 5.1886886835098265}, {'batch_size': 12, 'throughput': 2.2085775535110113, 'latency_mean': 5.386340112686157, 'latency_p50': 5.455837726593018, 'latency_p90': 6.092911195755005}, {'batch_size': 15, 'throughput': 2.209365252438795, 'latency_mean': 6.693526057004928, 'latency_p50': 6.756766080856323, 'latency_p90': 7.513702178001404}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cycy233-model-8_v2

is_internal_developer: False

language_model: cycy233/model-8

model_size: 8B

ranking_group: single

throughput_3p7s: 2.12

us_pacific_date: 2025-02-19

win_ratio: 0.4733464075592797

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, '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 cycy233-model-8-v2-mkmlizer
Waiting for job on cycy233-model-8-v2-mkmlizer to finish
cycy233-model-8-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model-8-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-model-8-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model-8-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model-8-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model-8-v2-mkmlizer: ║       /___/                                                         ║
cycy233-model-8-v2-mkmlizer: ║                                                                     ║
cycy233-model-8-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model-8-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model-8-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model-8-v2-mkmlizer: ║                                                                     ║
cycy233-model-8-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model-8-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-model-8-v2-mkmlizer: ║                                                                     ║
cycy233-model-8-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model-8-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model-8-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model-8-v2-mkmlizer: ║                                                                     ║
cycy233-model-8-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model-8-v2-mkmlizer: Downloaded to shared memory in 37.530s
cycy233-model-8-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxn5_45wr, device:0
cycy233-model-8-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model-8-v2-mkmlizer: quantized model in 28.147s
cycy233-model-8-v2-mkmlizer: Processed model cycy233/model-8 in 65.678s
cycy233-model-8-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model-8-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model-8-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model-8-v2
cycy233-model-8-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model-8-v2/config.json
cycy233-model-8-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model-8-v2/special_tokens_map.json
cycy233-model-8-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model-8-v2/tokenizer_config.json
cycy233-model-8-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model-8-v2/tokenizer.json
cycy233-model-8-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model-8-v2/flywheel_model.0.safetensors
cycy233-model-8-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 30.97it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 47.09it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:05, 47.25it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:07, 35.04it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:06, 43.25it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:05, 43.07it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:05, 42.81it/s]
Loading 0:  15%|█▌        | 45/291 [00:01<00:05, 44.25it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:06, 35.89it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:05, 43.14it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:05, 42.02it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:05, 41.95it/s]
Loading 0:  25%|██▍       | 72/291 [00:01<00:05, 42.74it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:06, 34.10it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:07, 27.64it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:07, 28.21it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 33.94it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:05, 33.54it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:05, 36.34it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 35.56it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:04, 38.22it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 38.64it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 37.61it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:04, 34.78it/s]
Loading 0:  44%|████▍     | 129/291 [00:03<00:04, 37.07it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 36.07it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 38.60it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:04, 36.91it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 39.44it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:03, 37.39it/s]
Loading 0:  53%|█████▎    | 155/291 [00:04<00:03, 37.39it/s]
Loading 0:  55%|█████▍    | 159/291 [00:04<00:03, 35.86it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 40.79it/s]
Loading 0:  58%|█████▊    | 170/291 [00:04<00:02, 41.12it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 41.49it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 40.80it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 41.78it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:03, 25.31it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 26.44it/s]
Loading 0:  68%|██████▊   | 199/291 [00:05<00:02, 31.01it/s]
Loading 0:  70%|██████▉   | 203/291 [00:05<00:02, 30.43it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:02, 37.89it/s]
Loading 0:  74%|███████▍  | 215/291 [00:05<00:01, 38.52it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 38.62it/s]
Loading 0:  77%|███████▋  | 225/291 [00:06<00:01, 39.98it/s]
Loading 0:  79%|███████▉  | 230/291 [00:06<00:01, 33.00it/s]
Loading 0:  81%|████████▏ | 237/291 [00:06<00:01, 39.55it/s]
Loading 0:  83%|████████▎ | 242/291 [00:06<00:01, 39.29it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:01, 39.08it/s]
Loading 0:  87%|████████▋ | 252/291 [00:06<00:00, 40.73it/s]
Loading 0:  88%|████████▊ | 257/291 [00:06<00:00, 34.47it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 41.47it/s]
Loading 0:  92%|█████████▏| 269/291 [00:07<00:00, 41.07it/s]
Loading 0:  94%|█████████▍| 274/291 [00:07<00:00, 40.99it/s]
Loading 0:  96%|█████████▌| 279/291 [00:07<00:00, 41.18it/s]
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 33.73it/s]
Loading 0:  99%|█████████▉| 288/291 [00:13<00:01,  2.76it/s]
                                                            
Job cycy233-model-8-v2-mkmlizer completed after 94.03s with status: succeeded
Stopping job with name cycy233-model-8-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model-8-v2
Waiting for inference service cycy233-model-8-v2 to be ready
Inference service cycy233-model-8-v2 ready after 180.69928336143494s
Pipeline stage MKMLDeployer completed in 181.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0549800395965576s
Received healthy response to inference request in 1.412602424621582s
Received healthy response to inference request in 1.2429120540618896s
Received healthy response to inference request in 1.3442659378051758s
Received healthy response to inference request in 1.1705763339996338s
5 requests
0 failed requests
5th percentile: 1.1850434780120849
10th percentile: 1.1995106220245362
20th percentile: 1.2284449100494386
30th percentile: 1.2631828308105468
40th percentile: 1.3037243843078614
50th percentile: 1.3442659378051758
60th percentile: 1.3716005325317382
70th percentile: 1.3989351272583008
80th percentile: 1.5410779476165772
90th percentile: 1.7980289936065674
95th percentile: 1.9265045166015624
99th percentile: 2.0292849349975586
mean time: 1.4450673580169677
Pipeline stage StressChecker completed in 8.45s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.59s
Shutdown handler de-registered
cycy233-model-8_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-model-8-v2-profiler
Waiting for inference service cycy233-model-8-v2-profiler to be ready
Inference service cycy233-model-8-v2-profiler ready after 181.42121982574463s
Pipeline stage MKMLProfilerDeployer completed in 181.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-model-8-v2-profiler-predictor-00001-deployment-65659g5m:/code/chaiverse_profiler_1740022889 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-model-8-v2-profiler-predictor-00001-deployment-65659g5m --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1740022889 && 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_1740022889/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2520.61s
Shutdown handler de-registered
cycy233-model-8_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-model-8_v2 status is now torndown due to DeploymentManager action
cycy233-model-8_v2 status is now torndown due to DeploymentManager action
cycy233-model-8_v2 status is now torndown due to DeploymentManager action