developer_uid: huangjiayin
submission_id: alexxi19-f1-v1-nemo-ba_19525_v50
model_name: alexxi19-f1-v1-nemo-ba_19525_v50
model_group: alexxi19/f1-v1-nemo-base
status: torndown
timestamp: 2025-02-25T09:00:41+00:00
num_battles: 7163
num_wins: 3583
celo_rating: 1264.76
family_friendly_score: 0.5566
family_friendly_standard_error: 0.007025616556573523
submission_type: basic
model_repo: alexxi19/f1-v1-nemo-base-merge
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6037601874538068, 'latency_mean': 1.65621910572052, 'latency_p50': 1.6505322456359863, 'latency_p90': 1.8409154415130615}, {'batch_size': 3, 'throughput': 1.091614147203313, 'latency_mean': 2.737753177881241, 'latency_p50': 2.7256394624710083, 'latency_p90': 3.0387792587280273}, {'batch_size': 5, 'throughput': 1.3128589385013958, 'latency_mean': 3.7885446417331696, 'latency_p50': 3.782232642173767, 'latency_p90': 4.279836750030517}, {'batch_size': 6, 'throughput': 1.3726376130442763, 'latency_mean': 4.350987125635147, 'latency_p50': 4.3610919713974, 'latency_p90': 4.8719449758529665}, {'batch_size': 8, 'throughput': 1.4521122139164797, 'latency_mean': 5.476637120246887, 'latency_p50': 5.471766352653503, 'latency_p90': 6.154258370399475}, {'batch_size': 10, 'throughput': 1.465614370785441, 'latency_mean': 6.769881303310394, 'latency_p50': 6.806074023246765, 'latency_p90': 7.576054835319519}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexxi19-f1-v1-nemo-ba_19525_v50
is_internal_developer: False
language_model: alexxi19/f1-v1-nemo-base-merge
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-02-25
win_ratio: 0.5002094094653078
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', 'Bot', 'User', 'You:', 'Me:', '####'], '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 alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer
Waiting for job on alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer to finish
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ _____ __ __ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ /___/ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ Version: 0.12.8 ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ https://mk1.ai ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ belonging to: ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ Chai Research Corp. ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ║ ║
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: Downloaded to shared memory in 117.419s
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvzb8slj4, device:0
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: quantized model in 40.295s
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: Processed model alexxi19/f1-v1-nemo-base-merge in 157.715s
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v50
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v50/config.json
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v50/special_tokens_map.json
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v50/tokenizer_config.json
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v50/tokenizer.json
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-f1-v1-nemo-ba-19525-v50/flywheel_model.0.safetensors
alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<19:08, 3.18s/it] Loading 0: 1%| | 3/363 [00:06<11:29, 1.92s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:17, 1.38it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:24, 4.14it/s] Loading 0: 5%|▍ | 18/363 [00:06<00:54, 6.36it/s] Loading 0: 6%|▋ | 23/363 [00:07<00:36, 9.36it/s] Loading 0: 8%|▊ | 29/363 [00:07<00:24, 13.37it/s] Loading 0: 9%|▉ | 33/363 [00:07<00:22, 14.41it/s] Loading 0: 11%|█ | 40/363 [00:07<00:15, 20.61it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:13, 22.96it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.23it/s] Loading 0: 15%|█▌ | 55/363 [00:07<00:10, 29.38it/s] Loading 0: 17%|█▋ | 60/363 [00:08<00:10, 29.36it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:09, 32.72it/s] Loading 0: 20%|█▉ | 71/363 [00:08<00:08, 33.40it/s] Loading 0: 21%|██ | 76/363 [00:08<00:07, 36.20it/s] Loading 0: 22%|██▏ | 80/363 [00:08<00:08, 34.62it/s] Loading 0: 23%|██▎ | 84/363 [00:08<00:09, 29.94it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:09, 29.29it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:07, 35.08it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:09, 28.40it/s] Loading 0: 28%|██▊ | 103/363 [00:09<00:08, 31.91it/s] Loading 0: 29%|██▉ | 107/363 [00:09<00:07, 32.10it/s] Loading 0: 31%|███ | 112/363 [00:09<00:07, 35.37it/s] Loading 0: 32%|███▏ | 116/363 [00:09<00:09, 27.32it/s] Loading 0: 33%|███▎ | 120/363 [00:10<00:08, 28.96it/s] Loading 0: 34%|███▍ | 124/363 [00:10<00:08, 28.79it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:08, 29.01it/s] Loading 0: 37%|███▋ | 134/363 [00:10<00:07, 29.83it/s] Loading 0: 38%|███▊ | 139/363 [00:10<00:06, 33.80it/s] Loading 0: 39%|███▉ | 143/363 [00:10<00:06, 33.00it/s] Loading 0: 40%|████ | 147/363 [00:10<00:07, 27.66it/s] Loading 0: 41%|████▏ | 150/363 [00:11<00:08, 25.40it/s] Loading 0: 43%|████▎ | 157/363 [00:11<00:06, 33.79it/s] Loading 0: 44%|████▍ | 161/363 [00:11<00:07, 27.09it/s] Loading 0: 46%|████▌ | 166/363 [00:11<00:06, 30.06it/s] Loading 0: 47%|████▋ | 170/363 [00:11<00:06, 29.91it/s] Loading 0: 48%|████▊ | 174/363 [00:11<00:05, 31.85it/s] Loading 0: 49%|████▉ | 178/363 [00:12<00:07, 24.02it/s] Loading 0: 50%|█████ | 182/363 [00:12<00:06, 26.80it/s] Loading 0: 51%|█████ | 186/363 [00:12<00:07, 24.79it/s] Loading 0: 53%|█████▎ | 191/363 [00:12<00:05, 29.44it/s] Loading 0: 54%|█████▎ | 195/363 [00:12<00:07, 23.08it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:05, 27.43it/s] Loading 0: 56%|█████▌ | 204/363 [00:13<00:05, 26.57it/s] Loading 0: 57%|█████▋ | 208/363 [00:13<00:05, 26.63it/s] Loading 0: 58%|█████▊ | 211/363 [00:13<00:05, 26.00it/s] Loading 0: 59%|█████▉ | 214/363 [00:13<00:05, 25.03it/s] Loading 0: 60%|██████ | 218/363 [00:13<00:05, 27.88it/s] Loading 0: 61%|██████ | 222/363 [00:13<00:06, 21.22it/s] Loading 0: 63%|██████▎ | 227/363 [00:13<00:05, 26.24it/s] Loading 0: 64%|██████▎ | 231/363 [00:14<00:05, 25.71it/s] Loading 0: 65%|██████▌ | 236/363 [00:14<00:04, 30.54it/s] Loading 0: 66%|██████▌ | 240/363 [00:14<00:04, 25.05it/s] Loading 0: 68%|██████▊ | 247/363 [00:14<00:03, 33.21it/s] Loading 0: 69%|██████▉ | 251/363 [00:14<00:03, 32.88it/s] Loading 0: 71%|███████ | 256/363 [00:14<00:03, 27.75it/s] Loading 0: 72%|███████▏ | 260/363 [00:15<00:03, 28.85it/s] Loading 0: 73%|███████▎ | 266/363 [00:15<00:02, 34.67it/s] Loading 0: 74%|███████▍ | 270/363 [00:15<00:02, 31.59it/s] Loading 0: 76%|███████▌ | 275/363 [00:15<00:02, 34.47it/s] Loading 0: 77%|███████▋ | 281/363 [00:15<00:02, 37.09it/s] Loading 0: 79%|███████▊ | 285/363 [00:15<00:02, 30.50it/s] Loading 0: 80%|████████ | 292/363 [00:15<00:01, 38.58it/s] Loading 0: 82%|████████▏ | 297/363 [00:15<00:01, 40.24it/s] Loading 0: 83%|████████▎ | 302/363 [00:16<00:01, 34.85it/s] Loading 0: 85%|████████▍ | 307/363 [00:16<00:01, 37.60it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:01, 30.75it/s] Loading 0: 87%|████████▋ | 317/363 [00:16<00:01, 33.52it/s] Loading 0: 88%|████████▊ | 321/363 [00:16<00:01, 26.25it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:01, 33.56it/s] Loading 0: 91%|█████████▏| 332/363 [00:17<00:00, 32.99it/s] Loading 0: 93%|█████████▎| 336/363 [00:17<00:00, 27.37it/s] Loading 0: 94%|█████████▎| 340/363 [00:17<00:00, 25.73it/s] Loading 0: 95%|█████████▌| 346/363 [00:17<00:00, 30.90it/s] Loading 0: 96%|█████████▋| 350/363 [00:17<00:00, 25.70it/s] Loading 0: 98%|█████████▊| 355/363 [00:18<00:00, 28.88it/s] Loading 0: 99%|█████████▉| 359/363 [00:18<00:00, 29.47it/s]
Job alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer completed after 215.83s with status: succeeded
Stopping job with name alexxi19-f1-v1-nemo-ba-19525-v50-mkmlizer
Pipeline stage MKMLizer completed in 216.29s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-f1-v1-nemo-ba-19525-v50
Waiting for inference service alexxi19-f1-v1-nemo-ba-19525-v50 to be ready
Inference service alexxi19-f1-v1-nemo-ba-19525-v50 ready after 250.94188499450684s
Pipeline stage MKMLDeployer completed in 251.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.329423427581787s
Received healthy response to inference request in 1.5732932090759277s
Received healthy response to inference request in 1.6086535453796387s
Received healthy response to inference request in 1.4637115001678467s
Received healthy response to inference request in 1.592674970626831s
5 requests
0 failed requests
5th percentile: 1.4856278419494628
10th percentile: 1.507544183731079
20th percentile: 1.5513768672943116
30th percentile: 1.5771695613861083
40th percentile: 1.5849222660064697
50th percentile: 1.592674970626831
60th percentile: 1.599066400527954
70th percentile: 1.6054578304290772
80th percentile: 1.7528075218200685
90th percentile: 2.041115474700928
95th percentile: 2.185269451141357
99th percentile: 2.300592632293701
mean time: 1.7135513305664063
Pipeline stage StressChecker completed in 9.85s
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 0.64s
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
alexxi19-f1-v1-nemo-ba_19525_v50 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-f1-v1-nemo-ba-19525-v50-profiler
Waiting for inference service alexxi19-f1-v1-nemo-ba-19525-v50-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 2583.33s
Shutdown handler de-registered
alexxi19-f1-v1-nemo-ba_19525_v50 status is now inactive due to auto deactivation removed underperforming models
alexxi19-f1-v1-nemo-ba_19525_v50 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1