developer_uid: huohuo12
submission_id: alexxi19-ft-v1-nemo-bas_27407_v8
model_name: alexxi19-ft-v1-nemo-bas_27407_v8
model_group: alexxi19/ft-v1-nemo-base
status: torndown
timestamp: 2025-02-21T08:52:11+00:00
num_battles: 6810
num_wins: 3367
celo_rating: 1264.66
family_friendly_score: 0.5604
family_friendly_standard_error: 0.007019285433717595
submission_type: basic
model_repo: alexxi19/ft-v1-nemo-base-merge-v1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6002045850964443, 'latency_mean': 1.666009510755539, 'latency_p50': 1.6722060441970825, 'latency_p90': 1.8367759227752685}, {'batch_size': 3, 'throughput': 1.0889637997601889, 'latency_mean': 2.7377679085731508, 'latency_p50': 2.7351651191711426, 'latency_p90': 3.014909291267395}, {'batch_size': 5, 'throughput': 1.307224377844202, 'latency_mean': 3.810584384202957, 'latency_p50': 3.8357114791870117, 'latency_p90': 4.2694333553314205}, {'batch_size': 6, 'throughput': 1.3725326625557974, 'latency_mean': 4.353878668546677, 'latency_p50': 4.347153425216675, 'latency_p90': 4.886695337295532}, {'batch_size': 8, 'throughput': 1.4423294574793804, 'latency_mean': 5.504193010330201, 'latency_p50': 5.507971167564392, 'latency_p90': 6.24728946685791}, {'batch_size': 10, 'throughput': 1.4689101495400974, 'latency_mean': 6.7542680537700654, 'latency_p50': 6.78416645526886, 'latency_p90': 7.59327609539032}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexxi19-ft-v1-nemo-bas_27407_v8
is_internal_developer: False
language_model: alexxi19/ft-v1-nemo-base-merge-v1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.3
us_pacific_date: 2025-02-21
win_ratio: 0.4944199706314244
generation_params: {'temperature': 0.75, 'top_p': 0.85, 'min_p': 0.12, 'top_k': 50, 'presence_penalty': 0.65, 'frequency_penalty': 0.1, '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 alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer to finish
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ Version: 0.12.8 ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: Downloaded to shared memory in 184.353s
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2_kclw16, device:0
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: quantized model in 40.750s
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 225.103s
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v8
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v8/config.json
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v8/special_tokens_map.json
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v8/tokenizer_config.json
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v8/tokenizer.json
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v8/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<19:00, 3.16s/it] Loading 0: 1%| | 3/363 [00:06<11:24, 1.90s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:16, 1.39it/s] Loading 0: 3%|▎ | 11/363 [00:06<01:45, 3.34it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:07, 5.15it/s] Loading 0: 5%|▍ | 18/363 [00:07<00:51, 6.76it/s] Loading 0: 6%|▌ | 22/363 [00:07<00:35, 9.57it/s] Loading 0: 7%|▋ | 25/363 [00:07<00:29, 11.37it/s] Loading 0: 8%|▊ | 29/363 [00:07<00:22, 15.01it/s] Loading 0: 9%|▉ | 33/363 [00:07<00:21, 15.05it/s] Loading 0: 10%|█ | 38/363 [00:07<00:15, 20.33it/s] Loading 0: 12%|█▏ | 42/363 [00:07<00:14, 21.74it/s] Loading 0: 13%|█▎ | 47/363 [00:08<00:11, 26.80it/s] Loading 0: 14%|█▍ | 51/363 [00:08<00:14, 22.05it/s] Loading 0: 15%|█▌ | 56/363 [00:08<00:11, 27.09it/s] Loading 0: 17%|█▋ | 60/363 [00:08<00:11, 26.78it/s] Loading 0: 18%|█▊ | 65/363 [00:08<00:09, 31.20it/s] Loading 0: 19%|█▉ | 69/363 [00:08<00:11, 24.68it/s] Loading 0: 21%|██ | 76/363 [00:09<00:08, 32.05it/s] Loading 0: 22%|██▏ | 80/363 [00:09<00:08, 31.59it/s] Loading 0: 23%|██▎ | 84/363 [00:09<00:09, 27.97it/s] Loading 0: 24%|██▍ | 88/363 [00:09<00:09, 27.85it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:08, 32.95it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:10, 26.17it/s] Loading 0: 28%|██▊ | 103/363 [00:09<00:08, 29.40it/s] Loading 0: 29%|██▉ | 107/363 [00:10<00:08, 29.87it/s] Loading 0: 31%|███ | 112/363 [00:10<00:07, 33.20it/s] Loading 0: 32%|███▏ | 116/363 [00:10<00:09, 27.06it/s] Loading 0: 33%|███▎ | 121/363 [00:10<00:07, 30.52it/s] Loading 0: 34%|███▍ | 125/363 [00:10<00:07, 30.67it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:08, 27.91it/s] Loading 0: 37%|███▋ | 134/363 [00:11<00:08, 28.21it/s] Loading 0: 38%|███▊ | 137/363 [00:11<00:07, 28.50it/s] Loading 0: 39%|███▉ | 141/363 [00:11<00:07, 27.92it/s] Loading 0: 40%|███▉ | 144/363 [00:11<00:07, 27.42it/s] Loading 0: 41%|████ | 148/363 [00:11<00:07, 28.58it/s] Loading 0: 42%|████▏ | 151/363 [00:11<00:07, 27.02it/s] Loading 0: 43%|████▎ | 157/363 [00:11<00:06, 33.27it/s] Loading 0: 44%|████▍ | 161/363 [00:12<00:07, 25.98it/s] Loading 0: 46%|████▌ | 166/363 [00:12<00:06, 29.56it/s] Loading 0: 47%|████▋ | 170/363 [00:12<00:06, 29.79it/s] Loading 0: 48%|████▊ | 174/363 [00:12<00:05, 32.07it/s] Loading 0: 49%|████▉ | 178/363 [00:12<00:07, 24.80it/s] Loading 0: 51%|█████ | 184/363 [00:12<00:05, 30.41it/s] Loading 0: 52%|█████▏ | 188/363 [00:12<00:05, 30.28it/s] Loading 0: 53%|█████▎ | 193/363 [00:13<00:06, 27.64it/s] Loading 0: 54%|█████▍ | 197/363 [00:13<00:05, 27.89it/s] Loading 0: 56%|█████▌ | 202/363 [00:13<00:05, 31.80it/s] Loading 0: 57%|█████▋ | 206/363 [00:13<00:04, 31.89it/s] Loading 0: 58%|█████▊ | 210/363 [00:13<00:05, 28.03it/s] Loading 0: 59%|█████▊ | 213/363 [00:13<00:05, 25.56it/s] Loading 0: 61%|██████ | 220/363 [00:13<00:04, 33.83it/s] Loading 0: 62%|██████▏ | 224/363 [00:14<00:05, 27.19it/s] Loading 0: 63%|██████▎ | 229/363 [00:14<00:04, 30.15it/s] Loading 0: 64%|██████▍ | 233/363 [00:14<00:04, 30.29it/s] Loading 0: 66%|██████▌ | 238/363 [00:14<00:03, 33.32it/s] Loading 0: 67%|██████▋ | 242/363 [00:14<00:04, 27.03it/s] Loading 0: 68%|██████▊ | 247/363 [00:14<00:03, 30.52it/s] Loading 0: 69%|██████▉ | 251/363 [00:15<00:03, 30.61it/s] Loading 0: 71%|███████ | 256/363 [00:15<00:03, 27.35it/s] Loading 0: 71%|███████▏ | 259/363 [00:15<00:04, 25.56it/s] Loading 0: 72%|███████▏ | 263/363 [00:15<00:03, 26.78it/s] Loading 0: 74%|███████▎ | 267/363 [00:15<00:03, 26.94it/s] Loading 0: 74%|███████▍ | 270/363 [00:15<00:03, 27.21it/s] Loading 0: 75%|███████▌ | 274/363 [00:15<00:03, 29.30it/s] Loading 0: 77%|███████▋ | 278/363 [00:16<00:02, 29.83it/s] Loading 0: 78%|███████▊ | 283/363 [00:16<00:02, 34.02it/s] Loading 0: 79%|███████▉ | 287/363 [00:16<00:02, 26.84it/s] Loading 0: 80%|████████ | 292/363 [00:16<00:02, 30.72it/s] Loading 0: 82%|████████▏ | 296/363 [00:16<00:02, 31.01it/s] Loading 0: 83%|████████▎ | 301/363 [00:16<00:01, 34.05it/s] Loading 0: 84%|████████▍ | 305/363 [00:16<00:02, 27.48it/s] Loading 0: 85%|████████▌ | 310/363 [00:17<00:01, 30.92it/s] Loading 0: 87%|████████▋ | 314/363 [00:17<00:01, 30.80it/s] Loading 0: 88%|████████▊ | 318/363 [00:17<00:01, 32.82it/s] Loading 0: 89%|████████▊ | 322/363 [00:17<00:01, 25.65it/s] Loading 0: 90%|████████▉ | 326/363 [00:17<00:01, 28.60it/s] Loading 0: 91%|█████████ | 330/363 [00:17<00:01, 27.38it/s] Loading 0: 92%|█████████▏| 334/363 [00:17<00:01, 28.50it/s] Loading 0: 93%|█████████▎| 338/363 [00:18<00:00, 28.56it/s] Loading 0: 94%|█████████▍| 342/363 [00:18<00:00, 29.92it/s] Loading 0: 95%|█████████▌| 346/363 [00:18<00:00, 31.61it/s] Loading 0: 96%|█████████▋| 350/363 [00:18<00:00, 24.98it/s] Loading 0: 98%|█████████▊| 355/363 [00:18<00:00, 28.89it/s] Loading 0: 99%|█████████▉| 359/363 [00:18<00:00, 29.26it/s]
Job alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer completed after 256.69s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-bas-27407-v8-mkmlizer
Pipeline stage MKMLizer completed in 257.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-bas-27407-v8
Waiting for inference service alexxi19-ft-v1-nemo-bas-27407-v8 to be ready
Inference service alexxi19-ft-v1-nemo-bas-27407-v8 ready after 220.7357177734375s
Pipeline stage MKMLDeployer completed in 221.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2920238971710205s
Received healthy response to inference request in 1.5345323085784912s
Received healthy response to inference request in 1.7738442420959473s
Received healthy response to inference request in 1.4851207733154297s
Received healthy response to inference request in 1.6162407398223877s
5 requests
0 failed requests
5th percentile: 1.495003080368042
10th percentile: 1.5048853874206543
20th percentile: 1.5246500015258788
30th percentile: 1.5508739948272705
40th percentile: 1.583557367324829
50th percentile: 1.6162407398223877
60th percentile: 1.6792821407318115
70th percentile: 1.7423235416412353
80th percentile: 1.877480173110962
90th percentile: 2.0847520351409914
95th percentile: 2.188387966156006
99th percentile: 2.2712967109680178
mean time: 1.7403523921966553
Pipeline stage StressChecker completed in 10.04s
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 0.67s
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 0.71s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-bas_27407_v8 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-ft-v1-nemo-bas-27407-v8-profiler
Waiting for inference service alexxi19-ft-v1-nemo-bas-27407-v8-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 2696.80s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-bas_27407_v8 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-bas_27407_v8 status is now torndown due to DeploymentManager action