developer_uid: huohuo12
submission_id: sao10k-14b-qwen2-5-kunou-v1_v5
model_name: sao10k-14b-qwen2-5-kunou-v1_v3
model_group: Sao10K/14B-Qwen2.5-Kunou
status: torndown
timestamp: 2025-02-19T03:27:14+00:00
num_battles: 5932
num_wins: 2739
celo_rating: 1233.34
family_friendly_score: 0.6066
family_friendly_standard_error: 0.006908493902436334
submission_type: basic
model_repo: Sao10K/14B-Qwen2.5-Kunou-v1
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4674434988156318, 'latency_mean': 2.1392047035694124, 'latency_p50': 2.145196557044983, 'latency_p90': 2.3507392406463623}, {'batch_size': 3, 'throughput': 0.8541105153420644, 'latency_mean': 3.496039400100708, 'latency_p50': 3.507659077644348, 'latency_p90': 3.8628023624420167}, {'batch_size': 5, 'throughput': 1.041798624626184, 'latency_mean': 4.783380219936371, 'latency_p50': 4.827294111251831, 'latency_p90': 5.267979407310485}, {'batch_size': 6, 'throughput': 1.0997408376124589, 'latency_mean': 5.42619738817215, 'latency_p50': 5.4710530042648315, 'latency_p90': 6.166540813446045}, {'batch_size': 10, 'throughput': 1.1753103990738933, 'latency_mean': 8.437399940490723, 'latency_p50': 8.43162226676941, 'latency_p90': 9.449342751502991}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sao10k-14b-qwen2-5-kunou-v1_v3
is_internal_developer: False
language_model: Sao10K/14B-Qwen2.5-Kunou-v1
model_size: 15B
ranking_group: single
throughput_3p7s: 0.9
us_pacific_date: 2025-02-18
win_ratio: 0.4617329737019555
generation_params: {'temperature': 1.07, 'top_p': 0.88, 'min_p': 0.025, 'top_k': 48, 'presence_penalty': 0.47, 'frequency_penalty': 0.35, '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 sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer
Waiting for job on sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer to finish
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ _____ __ __ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ /___/ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ Version: 0.12.8 ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ https://mk1.ai ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ belonging to: ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ Chai Research Corp. ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: quantized model in 38.326s
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: Processed model Sao10K/14B-Qwen2.5-Kunou-v1 in 70.755s
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: creating bucket guanaco-mkml-models
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5/config.json
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5/added_tokens.json
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5/special_tokens_map.json
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5/tokenizer_config.json
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5/flywheel_model.1.safetensors
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v5/flywheel_model.0.safetensors
sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 0%| | 2/579 [00:07<35:25, 3.68s/it] Loading 0: 3%|▎ | 16/579 [00:07<03:12, 2.93it/s] Loading 0: 5%|▌ | 29/579 [00:07<01:27, 6.28it/s] Loading 0: 8%|▊ | 45/579 [00:07<00:45, 11.86it/s] Loading 0: 11%|█ | 64/579 [00:07<00:25, 20.47it/s] Loading 0: 13%|█▎ | 78/579 [00:07<00:18, 27.77it/s] Loading 0: 17%|█▋ | 96/579 [00:08<00:11, 40.45it/s] Loading 0: 19%|█▉ | 112/579 [00:08<00:08, 52.73it/s] Loading 0: 22%|██▏ | 127/579 [00:08<00:07, 63.07it/s] Loading 0: 25%|██▍ | 144/579 [00:08<00:05, 78.73it/s] Loading 0: 27%|██▋ | 159/579 [00:08<00:07, 59.10it/s] Loading 0: 30%|██▉ | 172/579 [00:08<00:05, 68.59it/s] Loading 0: 32%|███▏ | 185/579 [00:08<00:05, 78.48it/s] Loading 0: 34%|███▍ | 198/579 [00:09<00:04, 88.35it/s] Loading 0: 38%|███▊ | 220/579 [00:09<00:03, 113.09it/s] Loading 0: 41%|████ | 235/579 [00:09<00:02, 116.94it/s] Loading 0: 44%|████▍ | 254/579 [00:09<00:02, 134.19it/s] Loading 0: 47%|████▋ | 270/579 [00:09<00:02, 127.47it/s] Loading 0: 50%|█████ | 290/579 [00:09<00:01, 144.92it/s] Loading 0: 53%|█████▎ | 306/579 [00:09<00:02, 133.10it/s] Loading 0: 56%|█████▌ | 324/579 [00:09<00:01, 142.59it/s] Loading 0: 59%|█████▊ | 340/579 [00:10<00:01, 144.12it/s] Loading 0: 61%|██████▏ | 356/579 [00:10<00:01, 137.98it/s] Loading 0: 64%|██████▍ | 371/579 [00:10<00:02, 82.32it/s] Loading 0: 67%|██████▋ | 386/579 [00:10<00:02, 94.27it/s] Loading 0: 69%|██████▉ | 400/579 [00:10<00:01, 101.27it/s] Loading 0: 71%|███████▏ | 413/579 [00:10<00:01, 107.09it/s] Loading 0: 74%|███████▎ | 427/579 [00:10<00:01, 114.91it/s] Loading 0: 77%|███████▋ | 444/579 [00:11<00:01, 127.39it/s] Loading 0: 79%|███████▉ | 460/579 [00:11<00:00, 133.39it/s] Loading 0: 82%|████████▏ | 475/579 [00:11<00:00, 128.58it/s] Loading 0: 84%|████████▍ | 489/579 [00:27<00:29, 3.06it/s] Loading 0: 87%|████████▋ | 504/579 [00:27<00:17, 4.34it/s] Loading 0: 90%|████████▉ | 520/579 [00:27<00:09, 6.25it/s] Loading 0: 92%|█████████▏| 535/579 [00:27<00:05, 8.66it/s] Loading 0: 95%|█████████▍| 548/579 [00:27<00:02, 11.55it/s] Loading 0: 97%|█████████▋| 561/579 [00:27<00:01, 15.43it/s] Loading 0: 99%|█████████▉| 574/579 [00:27<00:00, 20.49it/s]
Job sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer completed after 94.05s with status: succeeded
Stopping job with name sao10k-14b-qwen2-5-kunou-v1-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.52s
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 sao10k-14b-qwen2-5-kunou-v1-v5
Waiting for inference service sao10k-14b-qwen2-5-kunou-v1-v5 to be ready
Failed to get response for submission chaiml-20250218-c-4epoc_55567_v1: HTTPConnectionPool(host='chaiml-20250218-c-4epoc-55567-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-20250218-c-4epoc_55567_v2: HTTPConnectionPool(host='chaiml-20250218-c-4epoc-55567-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-20250218-c-4epoc_55567_v1: HTTPConnectionPool(host='chaiml-20250218-c-4epoc-55567-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service sao10k-14b-qwen2-5-kunou-v1-v5 ready after 231.1791672706604s
Pipeline stage MKMLDeployer completed in 231.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.674022912979126s
Received healthy response to inference request in 1.5179972648620605s
Received healthy response to inference request in 1.8788788318634033s
Received healthy response to inference request in 1.8827173709869385s
Received healthy response to inference request in 1.204695224761963s
5 requests
0 failed requests
5th percentile: 1.2673556327819824
10th percentile: 1.3300160408020019
20th percentile: 1.455336856842041
30th percentile: 1.5901735782623292
40th percentile: 1.7345262050628663
50th percentile: 1.8788788318634033
60th percentile: 1.8804142475128174
70th percentile: 1.8819496631622314
80th percentile: 2.0409784793853762
90th percentile: 2.357500696182251
95th percentile: 2.515761804580688
99th percentile: 2.6423706912994382
mean time: 1.8316623210906982
Pipeline stage StressChecker completed in 10.27s
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 0.86s
Shutdown handler de-registered
sao10k-14b-qwen2-5-kunou-v1_v5 status is now deployed due to DeploymentManager action
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 2897.50s
Shutdown handler de-registered
sao10k-14b-qwen2-5-kunou-v1_v5 status is now inactive due to auto deactivation removed underperforming models
sao10k-14b-qwen2-5-kunou-v1_v5 status is now torndown due to DeploymentManager action
sao10k-14b-qwen2-5-kunou-v1_v5 status is now torndown due to DeploymentManager action
sao10k-14b-qwen2-5-kunou-v1_v5 status is now torndown due to DeploymentManager action