developer_uid: leosheng
submission_id: alexxi19-ft-v1-nemo-bas_27407_v4
model_name: alexxi19-ft-v1-nemo-bas_27407_v4
model_group: alexxi19/ft-v1-nemo-base
status: torndown
timestamp: 2025-02-21T04:45:00+00:00
num_battles: 7455
num_wins: 3612
celo_rating: 1263.61
family_friendly_score: 0.554
family_friendly_standard_error: 0.007029708386554879
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': 0.600699664420841, 'latency_mean': 1.664638148546219, 'latency_p50': 1.6785470247268677, 'latency_p90': 1.8354466915130614}, {'batch_size': 3, 'throughput': 1.0947330903411694, 'latency_mean': 2.7317041623592377, 'latency_p50': 2.72761332988739, 'latency_p90': 3.0048735857009885}, {'batch_size': 5, 'throughput': 1.3265212957518377, 'latency_mean': 3.750871742963791, 'latency_p50': 3.7206226587295532, 'latency_p90': 4.236097192764282}, {'batch_size': 6, 'throughput': 1.3910249967497428, 'latency_mean': 4.287012104988098, 'latency_p50': 4.267108678817749, 'latency_p90': 4.779125595092774}, {'batch_size': 8, 'throughput': 1.4680913914808813, 'latency_mean': 5.410163561105728, 'latency_p50': 5.4049694538116455, 'latency_p90': 6.0871056556701655}, {'batch_size': 10, 'throughput': 1.4911710522574144, 'latency_mean': 6.646388931274414, 'latency_p50': 6.6530327796936035, 'latency_p90': 7.666701865196228}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexxi19-ft-v1-nemo-bas_27407_v4
is_internal_developer: False
language_model: alexxi19/ft-v1-nemo-base-merge-v1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-02-20
win_ratio: 0.48450704225352115
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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-bas-27407-v4-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer to finish
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ Version: 0.12.8 ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: Downloaded to shared memory in 184.861s
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9y4m6hxh, device:0
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: quantized model in 39.834s
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 224.696s
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v4
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v4/special_tokens_map.json
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v4/config.json
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v4/tokenizer_config.json
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-bas-27407-v4/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:14, 3.03s/it] Loading 0: 1%| | 3/363 [00:06<10:58, 1.83s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:07, 1.45it/s] Loading 0: 3%|▎ | 11/363 [00:06<01:41, 3.47it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:04, 5.39it/s] Loading 0: 5%|▍ | 18/363 [00:06<00:48, 7.12it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:33, 10.16it/s] Loading 0: 7%|▋ | 25/363 [00:06<00:27, 12.08it/s] Loading 0: 8%|▊ | 29/363 [00:07<00:20, 15.97it/s] Loading 0: 9%|▉ | 33/363 [00:07<00:20, 15.73it/s] Loading 0: 11%|█ | 40/363 [00:07<00:13, 23.48it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:12, 25.11it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:10, 28.78it/s] Loading 0: 15%|█▍ | 53/363 [00:07<00:12, 24.36it/s] Loading 0: 16%|█▌ | 58/363 [00:08<00:10, 28.28it/s] Loading 0: 17%|█▋ | 62/363 [00:08<00:10, 28.95it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:11, 26.26it/s] Loading 0: 19%|█▉ | 70/363 [00:08<00:11, 25.67it/s] Loading 0: 21%|██ | 76/363 [00:08<00:09, 31.33it/s] Loading 0: 22%|██▏ | 80/363 [00:08<00:09, 30.43it/s] Loading 0: 23%|██▎ | 84/363 [00:09<00:10, 26.52it/s] Loading 0: 24%|██▍ | 87/363 [00:09<00:11, 24.97it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:08, 32.27it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:10, 25.78it/s] Loading 0: 28%|██▊ | 103/363 [00:09<00:08, 29.34it/s] Loading 0: 29%|██▉ | 107/363 [00:09<00:08, 29.71it/s] Loading 0: 31%|███ | 111/363 [00:09<00:07, 31.94it/s] Loading 0: 32%|███▏ | 115/363 [00:10<00:09, 24.81it/s] Loading 0: 33%|███▎ | 121/363 [00:10<00:07, 30.35it/s] Loading 0: 34%|███▍ | 125/363 [00:10<00:07, 30.44it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:08, 26.78it/s] Loading 0: 37%|███▋ | 133/363 [00:10<00:08, 26.24it/s] Loading 0: 38%|███▊ | 137/363 [00:10<00:07, 29.12it/s] Loading 0: 39%|███▉ | 141/363 [00:11<00:07, 28.60it/s] Loading 0: 40%|███▉ | 145/363 [00:11<00:07, 29.80it/s] Loading 0: 41%|████ | 149/363 [00:11<00:07, 30.35it/s] Loading 0: 42%|████▏ | 153/363 [00:11<00:06, 32.25it/s] Loading 0: 44%|████▎ | 158/363 [00:11<00:05, 35.80it/s] Loading 0: 45%|████▍ | 162/363 [00:11<00:06, 31.07it/s] Loading 0: 46%|████▌ | 167/363 [00:11<00:05, 34.46it/s] Loading 0: 47%|████▋ | 172/363 [00:11<00:04, 38.20it/s] Loading 0: 49%|████▉ | 177/363 [00:12<00:06, 29.15it/s] Loading 0: 51%|█████ | 185/363 [00:12<00:04, 37.88it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:04, 39.99it/s] Loading 0: 54%|█████▎ | 195/363 [00:12<00:05, 31.02it/s] Loading 0: 56%|█████▌ | 202/363 [00:12<00:04, 38.76it/s] Loading 0: 57%|█████▋ | 207/363 [00:12<00:04, 34.39it/s] Loading 0: 58%|█████▊ | 212/363 [00:13<00:04, 36.31it/s] Loading 0: 60%|█████▉ | 217/363 [00:13<00:03, 39.14it/s] Loading 0: 61%|██████ | 222/363 [00:13<00:05, 28.19it/s] Loading 0: 63%|██████▎ | 229/363 [00:13<00:03, 34.88it/s] Loading 0: 64%|██████▍ | 234/363 [00:13<00:03, 36.05it/s] Loading 0: 66%|██████▌ | 239/363 [00:13<00:03, 31.11it/s] Loading 0: 67%|██████▋ | 244/363 [00:13<00:03, 34.39it/s] Loading 0: 68%|██████▊ | 248/363 [00:14<00:03, 34.54it/s] Loading 0: 69%|██████▉ | 252/363 [00:14<00:03, 35.36it/s] Loading 0: 71%|███████ | 256/363 [00:14<00:03, 30.04it/s] Loading 0: 72%|███████▏ | 260/363 [00:14<00:03, 30.38it/s] Loading 0: 73%|███████▎ | 265/363 [00:14<00:02, 34.32it/s] Loading 0: 74%|███████▍ | 269/363 [00:14<00:02, 34.23it/s] Loading 0: 75%|███████▌ | 273/363 [00:14<00:03, 29.21it/s] Loading 0: 76%|███████▋ | 277/363 [00:15<00:02, 28.80it/s] Loading 0: 78%|███████▊ | 283/363 [00:15<00:02, 34.36it/s] Loading 0: 79%|███████▉ | 287/363 [00:15<00:02, 27.47it/s] Loading 0: 80%|████████ | 292/363 [00:15<00:02, 30.73it/s] Loading 0: 82%|████████▏ | 296/363 [00:15<00:02, 30.87it/s] Loading 0: 83%|████████▎ | 300/363 [00:15<00:01, 32.93it/s] Loading 0: 84%|████████▎ | 304/363 [00:16<00:02, 25.42it/s] Loading 0: 85%|████████▌ | 310/363 [00:16<00:01, 31.42it/s] Loading 0: 87%|████████▋ | 314/363 [00:16<00:01, 31.33it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:01, 28.28it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:01, 29.13it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:01, 32.54it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:00, 32.29it/s] Loading 0: 93%|█████████▎| 336/363 [00:17<00:00, 27.86it/s] Loading 0: 93%|█████████▎| 339/363 [00:17<00:00, 25.46it/s] Loading 0: 95%|█████████▍| 344/363 [00:17<00:00, 30.73it/s] Loading 0: 96%|█████████▌| 348/363 [00:17<00:00, 24.10it/s] Loading 0: 97%|█████████▋| 353/363 [00:17<00:00, 29.20it/s] Loading 0: 98%|█████████▊| 357/363 [00:17<00:00, 28.49it/s] Loading 0: 100%|█████████▉| 362/363 [00:17<00:00, 33.22it/s]
Job alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer completed after 258.28s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-bas-27407-v4-mkmlizer
Pipeline stage MKMLizer completed in 258.77s
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-bas-27407-v4
Waiting for inference service alexxi19-ft-v1-nemo-bas-27407-v4 to be ready
Inference service alexxi19-ft-v1-nemo-bas-27407-v4 ready after 200.68206882476807s
Pipeline stage MKMLDeployer completed in 201.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.404367208480835s
Received healthy response to inference request in 1.5103211402893066s
Received healthy response to inference request in 1.8392024040222168s
Received healthy response to inference request in 1.7743332386016846s
Received healthy response to inference request in 1.63533616065979s
5 requests
0 failed requests
5th percentile: 1.5353241443634034
10th percentile: 1.5603271484375
20th percentile: 1.6103331565856933
30th percentile: 1.663135576248169
40th percentile: 1.7187344074249267
50th percentile: 1.7743332386016846
60th percentile: 1.8002809047698975
70th percentile: 1.8262285709381103
80th percentile: 1.9522353649139406
90th percentile: 2.178301286697388
95th percentile: 2.2913342475891114
99th percentile: 2.3817606163024903
mean time: 1.8327120304107667
Pipeline stage StressChecker completed in 10.43s
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 0.61s
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 0.75s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-bas_27407_v4 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-v4-profiler
Waiting for inference service alexxi19-ft-v1-nemo-bas-27407-v4-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 2849.14s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-bas_27407_v4 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-bas_27407_v4 status is now torndown due to DeploymentManager action