developer_uid: leosheng
submission_id: alexxi19-ft-v1-nemo-ba_27407_v26
model_name: alexxi19-ft-v1-nemo-ba_27407_v26
model_group: alexxi19/ft-v1-nemo-base
status: torndown
timestamp: 2025-03-13T18:47:25+00:00
num_battles: 13541
num_wins: 6550
celo_rating: 1271.52
family_friendly_score: 0.5588
family_friendly_standard_error: 0.007022001993733695
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': 0.6061420116514176, 'latency_mean': 1.6497195553779602, 'latency_p50': 1.6556458473205566, 'latency_p90': 1.8122140884399414}, {'batch_size': 3, 'throughput': 1.1217190852901595, 'latency_mean': 2.6697155165672304, 'latency_p50': 2.648627996444702, 'latency_p90': 2.969234299659729}, {'batch_size': 5, 'throughput': 1.3563632773505916, 'latency_mean': 3.6690847194194793, 'latency_p50': 3.6388022899627686, 'latency_p90': 4.147846913337707}, {'batch_size': 6, 'throughput': 1.417545883456578, 'latency_mean': 4.210779757499695, 'latency_p50': 4.2095707654953, 'latency_p90': 4.715979528427124}, {'batch_size': 8, 'throughput': 1.4789229361806222, 'latency_mean': 5.377307778596878, 'latency_p50': 5.374284029006958, 'latency_p90': 6.080546092987061}, {'batch_size': 10, 'throughput': 1.5353335505388546, 'latency_mean': 6.473220096826553, 'latency_p50': 6.4959986209869385, 'latency_p90': 7.264059853553771}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexxi19-ft-v1-nemo-ba_27407_v26
is_internal_developer: False
language_model: alexxi19/ft-v1-nemo-base-merge-v1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2025-03-13
win_ratio: 0.483716121409054
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, '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 alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ Version: 0.12.8 ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: Downloaded to shared memory in 156.277s
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8mw8kuqj, device:0
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: quantized model in 39.619s
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 195.899s
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v26
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v26/config.json
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v26/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v26/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v26/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v26/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:57, 3.15s/it] Loading 0: 1%| | 3/363 [00:06<11:21, 1.89s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:14, 1.40it/s] Loading 0: 3%|▎ | 11/363 [00:06<01:44, 3.38it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:05, 5.28it/s] Loading 0: 5%|▌ | 19/363 [00:06<00:44, 7.75it/s] Loading 0: 6%|▋ | 23/363 [00:07<00:32, 10.53it/s] Loading 0: 7%|▋ | 27/363 [00:07<00:24, 13.89it/s] Loading 0: 9%|▉ | 32/363 [00:07<00:17, 18.42it/s] Loading 0: 10%|▉ | 36/363 [00:07<00:17, 18.63it/s] Loading 0: 11%|█ | 40/363 [00:07<00:14, 22.11it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:13, 24.47it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:10, 29.11it/s] Loading 0: 15%|█▍ | 53/363 [00:08<00:12, 24.95it/s] Loading 0: 16%|█▌ | 58/363 [00:08<00:10, 28.84it/s] Loading 0: 17%|█▋ | 62/363 [00:08<00:10, 29.81it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:10, 28.61it/s] Loading 0: 20%|█▉ | 71/363 [00:08<00:09, 29.63it/s] Loading 0: 21%|██ | 76/363 [00:08<00:08, 33.74it/s] Loading 0: 22%|██▏ | 80/363 [00:08<00:08, 33.40it/s] Loading 0: 23%|██▎ | 84/363 [00:09<00:09, 28.77it/s] Loading 0: 24%|██▍ | 88/363 [00:09<00:09, 28.42it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:07, 34.31it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:09, 27.09it/s] Loading 0: 28%|██▊ | 103/363 [00:09<00:08, 30.60it/s] Loading 0: 29%|██▉ | 107/363 [00:09<00:08, 30.12it/s] Loading 0: 31%|███ | 112/363 [00:09<00:07, 33.41it/s] Loading 0: 32%|███▏ | 116/363 [00:10<00:08, 27.85it/s] Loading 0: 33%|███▎ | 121/363 [00:10<00:07, 31.42it/s] Loading 0: 34%|███▍ | 125/363 [00:10<00:07, 31.92it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:07, 30.21it/s] Loading 0: 37%|███▋ | 134/363 [00:10<00:07, 30.55it/s] Loading 0: 38%|███▊ | 139/363 [00:10<00:06, 33.74it/s] Loading 0: 39%|███▉ | 143/363 [00:10<00:06, 32.67it/s] Loading 0: 40%|████ | 147/363 [00:11<00:07, 28.12it/s] Loading 0: 41%|████▏ | 150/363 [00:11<00:08, 25.82it/s] Loading 0: 43%|████▎ | 157/363 [00:11<00:06, 33.57it/s] Loading 0: 44%|████▍ | 161/363 [00:11<00:07, 27.65it/s] Loading 0: 46%|████▌ | 166/363 [00:11<00:06, 31.33it/s] Loading 0: 47%|████▋ | 170/363 [00:11<00:06, 31.93it/s] Loading 0: 48%|████▊ | 175/363 [00:11<00:05, 35.39it/s] Loading 0: 49%|████▉ | 179/363 [00:12<00:06, 29.40it/s] Loading 0: 51%|█████ | 184/363 [00:12<00:05, 32.34it/s] Loading 0: 52%|█████▏ | 188/363 [00:12<00:05, 33.01it/s] Loading 0: 53%|█████▎ | 193/363 [00:12<00:05, 31.33it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:05, 31.52it/s] Loading 0: 56%|█████▌ | 202/363 [00:12<00:04, 34.30it/s] Loading 0: 57%|█████▋ | 206/363 [00:12<00:04, 33.97it/s] Loading 0: 58%|█████▊ | 210/363 [00:13<00:05, 30.09it/s] Loading 0: 59%|█████▉ | 214/363 [00:13<00:05, 28.21it/s] Loading 0: 61%|██████ | 220/363 [00:13<00:04, 33.33it/s] Loading 0: 62%|██████▏ | 224/363 [00:13<00:05, 27.42it/s] Loading 0: 63%|██████▎ | 229/363 [00:13<00:04, 30.91it/s] Loading 0: 64%|██████▍ | 233/363 [00:13<00:04, 31.60it/s] Loading 0: 66%|██████▌ | 238/363 [00:13<00:03, 35.08it/s] Loading 0: 67%|██████▋ | 242/363 [00:14<00:04, 28.72it/s] Loading 0: 68%|██████▊ | 247/363 [00:14<00:03, 31.09it/s] Loading 0: 69%|██████▉ | 251/363 [00:14<00:03, 31.69it/s] Loading 0: 71%|███████ | 256/363 [00:14<00:03, 30.07it/s] Loading 0: 72%|███████▏ | 260/363 [00:14<00:03, 30.44it/s] Loading 0: 73%|███████▎ | 265/363 [00:14<00:02, 33.26it/s] Loading 0: 74%|███████▍ | 269/363 [00:14<00:02, 32.73it/s] Loading 0: 75%|███████▌ | 273/363 [00:15<00:03, 28.83it/s] Loading 0: 76%|███████▋ | 277/363 [00:15<00:03, 27.84it/s] Loading 0: 78%|███████▊ | 283/363 [00:15<00:02, 33.29it/s] Loading 0: 79%|███████▉ | 287/363 [00:15<00:02, 27.33it/s] Loading 0: 80%|████████ | 292/363 [00:15<00:02, 29.73it/s] Loading 0: 82%|████████▏ | 296/363 [00:15<00:02, 30.14it/s] Loading 0: 83%|████████▎ | 301/363 [00:16<00:01, 33.66it/s] Loading 0: 84%|████████▍ | 305/363 [00:16<00:02, 28.16it/s] Loading 0: 85%|████████▌ | 310/363 [00:16<00:01, 30.88it/s] Loading 0: 87%|████████▋ | 314/363 [00:16<00:01, 32.09it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:01, 30.39it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:01, 30.45it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:01, 33.64it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:00, 33.47it/s] Loading 0: 93%|█████████▎| 336/363 [00:17<00:00, 28.67it/s] Loading 0: 94%|█████████▎| 340/363 [00:17<00:00, 28.07it/s] Loading 0: 95%|█████████▌| 346/363 [00:17<00:00, 33.75it/s] Loading 0: 96%|█████████▋| 350/363 [00:17<00:00, 27.45it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 31.30it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 32.87it/s]
Job alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer completed after 227.2s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v26-mkmlizer
Pipeline stage MKMLizer completed in 227.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v26
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v26 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v26 ready after 100.40531516075134s
Pipeline stage MKMLDeployer completed in 100.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1973049640655518s
Received healthy response to inference request in 1.5759639739990234s
Received healthy response to inference request in 1.6417875289916992s
Received healthy response to inference request in 1.5534801483154297s
Received healthy response to inference request in 1.5457267761230469s
5 requests
0 failed requests
5th percentile: 1.5472774505615234
10th percentile: 1.548828125
20th percentile: 1.5519294738769531
30th percentile: 1.5579769134521484
40th percentile: 1.566970443725586
50th percentile: 1.5759639739990234
60th percentile: 1.6022933959960937
70th percentile: 1.628622817993164
80th percentile: 1.75289101600647
90th percentile: 1.9750979900360108
95th percentile: 2.086201477050781
99th percentile: 2.175084266662598
mean time: 1.7028526782989502
Pipeline stage StressChecker completed in 9.80s
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 0.73s
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
alexxi19-ft-v1-nemo-ba_27407_v26 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4022.16s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v26 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v26 status is now torndown due to DeploymentManager action