cycy233-model-8

developer_uid: Luna1040

submission_id: cycy233-model-8_v3

model_name: cycy233-model-8_v3

model_group: cycy233/model-8

status: torndown

timestamp: 2025-02-20T03:33:29+00:00

num_battles: 5532

num_wins: 2650

celo_rating: 1249.29

family_friendly_score: 0.5422

family_friendly_standard_error: 0.007045837920361212

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': 0.8509814763879896, 'latency_mean': 1.1750360250473022, 'latency_p50': 1.1675783395767212, 'latency_p90': 1.3007766723632812}, {'batch_size': 4, 'throughput': 1.802989739124811, 'latency_mean': 2.206165192127228, 'latency_p50': 2.200690507888794, 'latency_p90': 2.4419349670410155}, {'batch_size': 5, 'throughput': 1.9221919062040171, 'latency_mean': 2.5861957800388335, 'latency_p50': 2.609280586242676, 'latency_p90': 2.8744058132171633}, {'batch_size': 8, 'throughput': 2.1188789476488092, 'latency_mean': 3.7488307893276214, 'latency_p50': 3.7384033203125, 'latency_p90': 4.229377174377442}, {'batch_size': 10, 'throughput': 2.187590513863859, 'latency_mean': 4.538464614152908, 'latency_p50': 4.554939150810242, 'latency_p90': 5.104752707481384}, {'batch_size': 12, 'throughput': 2.2335430078286054, 'latency_mean': 5.319079896211624, 'latency_p50': 5.327848196029663, 'latency_p90': 6.032529187202454}, {'batch_size': 15, 'throughput': 2.247992474905561, 'latency_mean': 6.573259768486023, 'latency_p50': 6.5263484716415405, 'latency_p90': 7.309458303451538}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cycy233-model-8_v3

is_internal_developer: False

language_model: cycy233/model-8

model_size: 8B

ranking_group: single

throughput_3p7s: 2.13

us_pacific_date: 2025-02-19

win_ratio: 0.4790310918293565

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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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-model-8-v3-mkmlizer
Waiting for job on cycy233-model-8-v3-mkmlizer to finish
cycy233-model-8-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model-8-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-model-8-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model-8-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model-8-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model-8-v3-mkmlizer: ║       /___/                                                         ║
cycy233-model-8-v3-mkmlizer: ║                                                                     ║
cycy233-model-8-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model-8-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model-8-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model-8-v3-mkmlizer: ║                                                                     ║
cycy233-model-8-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model-8-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-model-8-v3-mkmlizer: ║                                                                     ║
cycy233-model-8-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model-8-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model-8-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model-8-v3-mkmlizer: ║                                                                     ║
cycy233-model-8-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model-8-v3-mkmlizer: Downloaded to shared memory in 25.168s
cycy233-model-8-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpprnwu598, device:0
cycy233-model-8-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model-8-v3-mkmlizer: quantized model in 29.440s
cycy233-model-8-v3-mkmlizer: Processed model cycy233/model-8 in 54.609s
cycy233-model-8-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model-8-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model-8-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model-8-v3
cycy233-model-8-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model-8-v3/config.json
cycy233-model-8-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model-8-v3/special_tokens_map.json
cycy233-model-8-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model-8-v3/tokenizer_config.json
cycy233-model-8-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model-8-v3/tokenizer.json
cycy233-model-8-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model-8-v3/flywheel_model.0.safetensors
cycy233-model-8-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 28.62it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 43.70it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 41.31it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 40.67it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:06, 41.46it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:08, 32.32it/s]
Loading 0:  13%|█▎        | 39/291 [00:01<00:06, 39.60it/s]
Loading 0:  15%|█▌        | 44/291 [00:01<00:06, 39.94it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:05, 40.44it/s]
Loading 0:  19%|█▊        | 54/291 [00:01<00:05, 41.45it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:07, 32.52it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:06, 35.81it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:06, 33.70it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:05, 40.20it/s]
Loading 0:  27%|██▋       | 80/291 [00:02<00:05, 39.98it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:07, 26.86it/s]
Loading 0:  31%|███       | 89/291 [00:02<00:07, 28.43it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 31.66it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 32.97it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:05, 33.97it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 33.50it/s]
Loading 0:  38%|███▊      | 111/291 [00:03<00:04, 36.21it/s]
Loading 0:  40%|███▉      | 115/291 [00:03<00:05, 33.31it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 35.99it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:04, 34.98it/s]
Loading 0:  44%|████▍     | 128/291 [00:03<00:04, 35.31it/s]
Loading 0:  45%|████▌     | 132/291 [00:03<00:04, 32.34it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:04, 34.17it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:04, 32.27it/s]
Loading 0:  50%|████▉     | 145/291 [00:04<00:04, 36.29it/s]
Loading 0:  51%|█████     | 149/291 [00:04<00:04, 33.07it/s]
Loading 0:  53%|█████▎    | 154/291 [00:04<00:03, 36.89it/s]
Loading 0:  54%|█████▍    | 158/291 [00:04<00:03, 33.61it/s]
Loading 0:  56%|█████▌    | 163/291 [00:04<00:03, 36.89it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 32.92it/s]
Loading 0:  59%|█████▉    | 172/291 [00:04<00:03, 36.32it/s]
Loading 0:  61%|██████    | 177/291 [00:05<00:03, 37.29it/s]
Loading 0:  62%|██████▏   | 181/291 [00:05<00:03, 33.79it/s]
Loading 0:  64%|██████▍   | 186/291 [00:05<00:02, 37.19it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:04, 23.64it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 24.65it/s]
Loading 0:  68%|██████▊   | 199/291 [00:05<00:03, 29.45it/s]
Loading 0:  70%|██████▉   | 203/291 [00:05<00:03, 28.98it/s]
Loading 0:  71%|███████▏  | 208/291 [00:06<00:02, 33.24it/s]
Loading 0:  73%|███████▎  | 212/291 [00:06<00:02, 30.43it/s]
Loading 0:  75%|███████▍  | 217/291 [00:06<00:02, 34.18it/s]
Loading 0:  76%|███████▌  | 221/291 [00:06<00:02, 32.03it/s]
Loading 0:  78%|███████▊  | 226/291 [00:06<00:01, 35.91it/s]
Loading 0:  79%|███████▉  | 230/291 [00:06<00:01, 33.46it/s]
Loading 0:  81%|████████  | 235/291 [00:06<00:01, 37.39it/s]
Loading 0:  82%|████████▏ | 239/291 [00:06<00:01, 34.17it/s]
Loading 0:  84%|████████▍ | 244/291 [00:07<00:01, 37.97it/s]
Loading 0:  85%|████████▌ | 248/291 [00:07<00:01, 34.12it/s]
Loading 0:  87%|████████▋ | 253/291 [00:07<00:01, 37.90it/s]
Loading 0:  88%|████████▊ | 257/291 [00:07<00:00, 34.48it/s]
Loading 0:  90%|█████████ | 262/291 [00:07<00:00, 37.94it/s]
Loading 0:  91%|█████████▏| 266/291 [00:07<00:00, 34.85it/s]
Loading 0:  94%|█████████▍| 273/291 [00:07<00:00, 41.56it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 40.54it/s]
Loading 0:  97%|█████████▋| 283/291 [00:08<00:00, 33.83it/s]
Loading 0:  99%|█████████▊| 287/291 [00:13<00:01,  2.67it/s]
                                                            
Job cycy233-model-8-v3-mkmlizer completed after 84.26s with status: succeeded
Stopping job with name cycy233-model-8-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model-8-v3
Waiting for inference service cycy233-model-8-v3 to be ready
Inference service cycy233-model-8-v3 ready after 170.84102296829224s
Pipeline stage MKMLDeployer completed in 171.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9589824676513672s
Received healthy response to inference request in 1.3529672622680664s
Received healthy response to inference request in 1.314070701599121s
Received healthy response to inference request in 1.2884531021118164s
Received healthy response to inference request in 1.38633394241333s
5 requests
0 failed requests
5th percentile: 1.2935766220092773
10th percentile: 1.2987001419067383
20th percentile: 1.3089471817016602
30th percentile: 1.3218500137329101
40th percentile: 1.3374086380004884
50th percentile: 1.3529672622680664
60th percentile: 1.3663139343261719
70th percentile: 1.3796606063842773
80th percentile: 1.5008636474609376
90th percentile: 1.7299230575561524
95th percentile: 1.8444527626037597
99th percentile: 1.9360765266418456
mean time: 1.4601614952087403
Pipeline stage StressChecker completed in 8.62s
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 0.65s
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 0.63s
Shutdown handler de-registered
cycy233-model-8_v3 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 0.10s
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-v3-profiler
Waiting for inference service cycy233-model-8-v3-profiler to be ready
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 2620.93s
Shutdown handler de-registered
cycy233-model-8_v3 status is now inactive due to auto deactivation removed underperforming models
cycy233-model-8_v3 status is now torndown due to DeploymentManager action
cycy233-model-8_v3 status is now torndown due to DeploymentManager action
cycy233-model-8_v3 status is now torndown due to DeploymentManager action