cycy233-model0

developer_uid: cycy233

submission_id: cycy233-model0_v2

model_name: 486

model_group: cycy233/model0

status: torndown

timestamp: 2025-03-07T09:42:25+00:00

num_battles: 10051

num_wins: 4474

celo_rating: 1239.04

family_friendly_score: 0.5082

family_friendly_standard_error: 0.007070116830717863

submission_type: basic

model_repo: cycy233/model0

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.8507624105761056, 'latency_mean': 1.1753493535518647, 'latency_p50': 1.1697827577590942, 'latency_p90': 1.3046946048736572}, {'batch_size': 4, 'throughput': 1.776236993281138, 'latency_mean': 2.2435961413383483, 'latency_p50': 2.2459702491760254, 'latency_p90': 2.4953359842300413}, {'batch_size': 5, 'throughput': 1.918803757493886, 'latency_mean': 2.592016499042511, 'latency_p50': 2.604995846748352, 'latency_p90': 2.877245783805847}, {'batch_size': 8, 'throughput': 2.102565238180153, 'latency_mean': 3.7748381316661836, 'latency_p50': 3.7875359058380127, 'latency_p90': 4.2429646968841555}, {'batch_size': 10, 'throughput': 2.1753245951715607, 'latency_mean': 4.5537951374053955, 'latency_p50': 4.548722743988037, 'latency_p90': 5.229451704025268}, {'batch_size': 12, 'throughput': 2.1888176531871024, 'latency_mean': 5.424012604951859, 'latency_p50': 5.399828672409058, 'latency_p90': 6.080938196182251}, {'batch_size': 15, 'throughput': 2.214442072371993, 'latency_mean': 6.677752333879471, 'latency_p50': 6.742388963699341, 'latency_p90': 7.412891006469726}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model0

model_size: 8B

ranking_group: single

throughput_3p7s: 2.11

us_pacific_date: 2025-03-07

win_ratio: 0.4451298378270819

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

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}

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-model0-v2-mkmlizer
Waiting for job on cycy233-model0-v2-mkmlizer to finish
cycy233-model0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model0-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-model0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model0-v2-mkmlizer: ║       /___/                                                         ║
cycy233-model0-v2-mkmlizer: ║                                                                     ║
cycy233-model0-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model0-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model0-v2-mkmlizer: ║                                                                     ║
cycy233-model0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model0-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-model0-v2-mkmlizer: ║                                                                     ║
cycy233-model0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model0-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model0-v2-mkmlizer: ║                                                                     ║
cycy233-model0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model0-v2-mkmlizer: Downloaded to shared memory in 22.867s
cycy233-model0-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwaez89xp, device:0
cycy233-model0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model0-v2-mkmlizer: quantized model in 26.043s
cycy233-model0-v2-mkmlizer: Processed model cycy233/model0 in 48.911s
cycy233-model0-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model0-v2
cycy233-model0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model0-v2/config.json
cycy233-model0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model0-v2/special_tokens_map.json
cycy233-model0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model0-v2/tokenizer_config.json
cycy233-model0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model0-v2/tokenizer.json
cycy233-model0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model0-v2/flywheel_model.0.safetensors
cycy233-model0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:38,  2.42s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:06,  1.53it/s]
Loading 0:   5%|▍         | 14/291 [00:05<01:00,  4.55it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.34it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.26it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.58it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:11, 21.40it/s]
Loading 0:  16%|█▌        | 46/291 [00:05<00:09, 26.30it/s]
Loading 0:  18%|█▊        | 52/291 [00:05<00:08, 29.19it/s]
Loading 0:  21%|██        | 60/291 [00:06<00:08, 26.14it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:06, 33.18it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:06, 34.57it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:05, 36.92it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 42.77it/s]
Loading 0:  32%|███▏      | 92/291 [00:06<00:04, 43.13it/s]
Loading 0:  33%|███▎      | 97/291 [00:06<00:04, 44.34it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:03, 50.23it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:03, 48.47it/s]
Loading 0:  40%|███▉      | 116/291 [00:07<00:03, 50.13it/s]
Loading 0:  42%|████▏     | 123/291 [00:07<00:03, 46.32it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:03, 52.42it/s]
Loading 0:  47%|████▋     | 137/291 [00:07<00:03, 48.46it/s]
Loading 0:  49%|████▉     | 143/291 [00:07<00:03, 49.22it/s]
Loading 0:  52%|█████▏    | 150/291 [00:08<00:02, 47.49it/s]
Loading 0:  55%|█████▍    | 159/291 [00:08<00:02, 49.78it/s]
Loading 0:  57%|█████▋    | 166/291 [00:08<00:03, 39.64it/s]
Loading 0:  59%|█████▉    | 171/291 [00:08<00:03, 39.91it/s]
Loading 0:  61%|██████    | 177/291 [00:08<00:03, 37.72it/s]
Loading 0:  64%|██████▎   | 185/291 [00:08<00:02, 44.65it/s]
Loading 0:  65%|██████▌   | 190/291 [00:08<00:02, 45.74it/s]
Loading 0:  67%|██████▋   | 195/291 [00:09<00:02, 41.89it/s]
Loading 0:  70%|███████   | 204/291 [00:09<00:01, 45.79it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 52.78it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 51.05it/s]
Loading 0:  77%|███████▋  | 224/291 [00:09<00:01, 51.16it/s]
Loading 0:  79%|███████▉  | 231/291 [00:09<00:01, 48.37it/s]
Loading 0:  82%|████████▏ | 239/291 [00:09<00:00, 55.06it/s]
Loading 0:  84%|████████▍ | 245/291 [00:10<00:00, 51.44it/s]
Loading 0:  86%|████████▋ | 251/291 [00:10<00:00, 51.22it/s]
Loading 0:  88%|████████▊ | 257/291 [00:10<00:00, 52.90it/s]
Loading 0:  90%|█████████ | 263/291 [00:10<00:00, 50.52it/s]
Loading 0:  92%|█████████▏| 269/291 [00:10<00:00, 36.36it/s]
Loading 0:  95%|█████████▍| 276/291 [00:10<00:00, 38.07it/s]
Loading 0:  98%|█████████▊| 285/291 [00:10<00:00, 43.09it/s]
                                                            
Job cycy233-model0-v2-mkmlizer completed after 73.07s with status: succeeded
Stopping job with name cycy233-model0-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model0-v2
Waiting for inference service cycy233-model0-v2 to be ready
Inference service cycy233-model0-v2 ready after 100.37933087348938s
Pipeline stage MKMLDeployer completed in 100.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8683748245239258s
Received healthy response to inference request in 1.4407007694244385s
Received healthy response to inference request in 1.4706802368164062s
Received healthy response to inference request in 1.282573938369751s
Received healthy response to inference request in 1.1565377712249756s
5 requests
0 failed requests
5th percentile: 1.1817450046539306
10th percentile: 1.2069522380828857
20th percentile: 1.257366704940796
30th percentile: 1.3141993045806886
40th percentile: 1.3774500370025635
50th percentile: 1.4407007694244385
60th percentile: 1.4526925563812256
70th percentile: 1.4646843433380128
80th percentile: 1.5502191543579102
90th percentile: 1.709296989440918
95th percentile: 1.7888359069824218
99th percentile: 1.852467041015625
mean time: 1.4437735080718994
Pipeline stage StressChecker completed in 8.55s
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 0.66s
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 0.65s
Shutdown handler de-registered
cycy233-model0_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 0.11s
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-model0-v2-profiler
Waiting for inference service cycy233-model0-v2-profiler to be ready
Inference service cycy233-model0-v2-profiler ready after 100.42638826370239s
Pipeline stage MKMLProfilerDeployer completed in 100.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-model0-v2-profiler-predictor-00001-deployment-5d88l8bk8:/code/chaiverse_profiler_1741340872 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-model0-v2-profiler-predictor-00001-deployment-5d88l8bk8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741340872 && 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_1741340872/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 2381.79s
Shutdown handler de-registered
cycy233-model0_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-model0_v2 status is now torndown due to DeploymentManager action