cycy233-model4-2

developer_uid: cycy233

submission_id: cycy233-model4-2_v1

model_name: 486

model_group: cycy233/model4-2

status: torndown

timestamp: 2025-03-03T04:24:34+00:00

num_battles: 8015

num_wins: 3705

celo_rating: 1250.29

family_friendly_score: 0.5156000000000001

family_friendly_standard_error: 0.007067625343777075

submission_type: basic

model_repo: cycy233/model4-2

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': 0.8519040386454485, 'latency_mean': 1.173770248889923, 'latency_p50': 1.1781589984893799, 'latency_p90': 1.3060476303100585}, {'batch_size': 4, 'throughput': 1.8034299090419368, 'latency_mean': 2.2095739221572877, 'latency_p50': 2.2011632919311523, 'latency_p90': 2.452517533302307}, {'batch_size': 5, 'throughput': 1.954981849071462, 'latency_mean': 2.547732256650925, 'latency_p50': 2.5471850633621216, 'latency_p90': 2.8791826248168944}, {'batch_size': 8, 'throughput': 2.1279243340598963, 'latency_mean': 3.7297904801368715, 'latency_p50': 3.730094075202942, 'latency_p90': 4.191602993011474}, {'batch_size': 10, 'throughput': 2.2026855502295697, 'latency_mean': 4.493193793296814, 'latency_p50': 4.487754464149475, 'latency_p90': 5.131363558769226}, {'batch_size': 12, 'throughput': 2.246920123814861, 'latency_mean': 5.296178338527679, 'latency_p50': 5.312483549118042, 'latency_p90': 6.038792657852173}, {'batch_size': 15, 'throughput': 2.25621184399115, 'latency_mean': 6.563283517360687, 'latency_p50': 6.560070157051086, 'latency_p90': 7.316184329986572}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model4-2

model_size: 8B

ranking_group: single

throughput_3p7s: 2.14

us_pacific_date: 2025-03-02

win_ratio: 0.4622582657517155

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-model4-2-v1-mkmlizer
Waiting for job on cycy233-model4-2-v1-mkmlizer to finish
cycy233-model4-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model4-2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model4-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model4-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model4-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model4-2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model4-2-v1-mkmlizer: ║                                                                     ║
cycy233-model4-2-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model4-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model4-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model4-2-v1-mkmlizer: ║                                                                     ║
cycy233-model4-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model4-2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model4-2-v1-mkmlizer: ║                                                                     ║
cycy233-model4-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model4-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model4-2-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model4-2-v1-mkmlizer: ║                                                                     ║
cycy233-model4-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model4-2-v1-mkmlizer: Downloaded to shared memory in 28.791s
cycy233-model4-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp96r5pnyy, device:0
cycy233-model4-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model4-2-v1-mkmlizer: quantized model in 27.288s
cycy233-model4-2-v1-mkmlizer: Processed model cycy233/model4-2 in 56.079s
cycy233-model4-2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model4-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model4-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model4-2-v1
cycy233-model4-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model4-2-v1/config.json
cycy233-model4-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model4-2-v1/special_tokens_map.json
cycy233-model4-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model4-2-v1/tokenizer_config.json
cycy233-model4-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model4-2-v1/tokenizer.json
cycy233-model4-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model4-2-v1/flywheel_model.0.safetensors
cycy233-model4-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 29.58it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 49.38it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 43.06it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 42.14it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 48.62it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 44.90it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 43.46it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:05, 48.23it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 44.88it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.68it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 49.10it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 45.37it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 44.36it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:06, 31.55it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 31.68it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 37.14it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:04, 39.10it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 40.68it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 42.72it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:04, 37.42it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.18it/s]
Loading 0:  43%|████▎     | 126/291 [00:02<00:03, 46.78it/s]
Loading 0:  45%|████▌     | 131/291 [00:03<00:04, 39.20it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 46.26it/s]
Loading 0:  49%|████▉     | 144/291 [00:03<00:03, 45.93it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 37.73it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 45.80it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:03, 42.58it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 41.32it/s]
Loading 0:  59%|█████▉    | 173/291 [00:04<00:02, 42.42it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 44.70it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 44.59it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 27.49it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 30.28it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 39.37it/s]
Loading 0:  71%|███████▏  | 208/291 [00:05<00:02, 39.55it/s]
Loading 0:  73%|███████▎  | 213/291 [00:05<00:01, 39.33it/s]
Loading 0:  75%|███████▌  | 219/291 [00:05<00:01, 43.28it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 43.93it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 45.31it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 42.32it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 41.74it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 46.97it/s]
Loading 0:  87%|████████▋ | 253/291 [00:06<00:00, 44.37it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 43.79it/s]
Loading 0:  91%|█████████ | 264/291 [00:06<00:00, 46.79it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 46.52it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 46.75it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 43.86it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 43.07it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  3.09it/s]
                                                            
Job cycy233-model4-2-v1-mkmlizer completed after 83.97s with status: succeeded
Stopping job with name cycy233-model4-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model4-2-v1
Waiting for inference service cycy233-model4-2-v1 to be ready
Inference service cycy233-model4-2-v1 ready after 240.7973849773407s
Pipeline stage MKMLDeployer completed in 241.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1033661365509033s
Received healthy response to inference request in 1.3184654712677002s
Received healthy response to inference request in 1.1135365962982178s
Received healthy response to inference request in 1.1714239120483398s
Received healthy response to inference request in 1.1247105598449707s
5 requests
0 failed requests
5th percentile: 1.1157713890075684
10th percentile: 1.118006181716919
20th percentile: 1.12247576713562
30th percentile: 1.1340532302856445
40th percentile: 1.1527385711669922
50th percentile: 1.1714239120483398
60th percentile: 1.230240535736084
70th percentile: 1.289057159423828
80th percentile: 1.475445604324341
90th percentile: 1.7894058704376221
95th percentile: 1.9463860034942626
99th percentile: 2.071970109939575
mean time: 1.3663005352020263
Pipeline stage StressChecker completed in 8.04s
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 0.69s
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 0.64s
Shutdown handler de-registered
cycy233-model4-2_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 0.10s
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-model4-2-v1-profiler
Waiting for inference service cycy233-model4-2-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3381.50s
Shutdown handler de-registered
cycy233-model4-2_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model4-2_v1 status is now torndown due to DeploymentManager action