alexxi19-ft-v1-nemo-ba_27407

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-ba_27407_v22

model_name: alexxi19-ft-v1-nemo-ba_27407_v22

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-03-07T04:09:26+00:00

num_battles: 9961

num_wins: 4735

celo_rating: 1261.62

family_friendly_score: 0.5372

family_friendly_standard_error: 0.007051470201312631

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': 0.6074342509893658, 'latency_mean': 1.6461689364910126, 'latency_p50': 1.6459929943084717, 'latency_p90': 1.821384859085083}, {'batch_size': 3, 'throughput': 1.10450211385566, 'latency_mean': 2.7056277430057527, 'latency_p50': 2.720320701599121, 'latency_p90': 2.9824560642242433}, {'batch_size': 5, 'throughput': 1.3347523813853401, 'latency_mean': 3.7258704340457918, 'latency_p50': 3.7305333614349365, 'latency_p90': 4.260681819915772}, {'batch_size': 6, 'throughput': 1.4022181828182696, 'latency_mean': 4.255892491340637, 'latency_p50': 4.24577271938324, 'latency_p90': 4.788452816009522}, {'batch_size': 8, 'throughput': 1.4672599230773897, 'latency_mean': 5.417462476491928, 'latency_p50': 5.413004159927368, 'latency_p90': 6.096821069717407}, {'batch_size': 10, 'throughput': 1.4990181186936697, 'latency_mean': 6.623145128488541, 'latency_p50': 6.685992002487183, 'latency_p90': 7.4640470266342165}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v22

is_internal_developer: False

language_model: alexxi19/ft-v1-nemo-base-merge-v1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-03-06

win_ratio: 0.47535388013251684

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-ba-27407-v22-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: Downloaded to shared memory in 160.511s
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0ij390su, device:0
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: quantized model in 36.474s
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 196.986s
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v22
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v22/config.json
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v22/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v22/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v22/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v22/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:07,  3.01s/it]
Loading 0:   1%|          | 3/363 [00:06<10:50,  1.81s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:02,  1.47it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:19,  4.40it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:51,  6.76it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:34,  9.93it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:23, 14.22it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:19, 16.70it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 23.44it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:11, 27.61it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.43it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:09, 32.82it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:08, 34.08it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:09, 30.67it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:09, 31.86it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 34.68it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:08, 31.90it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 35.73it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:07, 37.85it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:07, 33.30it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 39.66it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:06, 39.45it/s]
Loading 0:  32%|███▏      | 115/363 [00:09<00:07, 34.23it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:06, 39.62it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:05, 40.36it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.79it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 38.94it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 34.68it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:06, 35.08it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 34.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 44.16it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 39.88it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 35.53it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:04, 38.56it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:04, 38.96it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:04, 36.72it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 39.26it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:04, 40.95it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:03, 43.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:03, 39.62it/s]
Loading 0:  59%|█████▊    | 213/363 [00:11<00:04, 36.20it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 44.82it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 40.45it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:03, 36.07it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 37.45it/s]
Loading 0:  67%|██████▋   | 244/363 [00:12<00:02, 40.00it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 35.42it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 36.88it/s]
Loading 0:  72%|███████▏  | 260/363 [00:12<00:02, 36.15it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 38.27it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 36.41it/s]
Loading 0:  75%|███████▌  | 273/363 [00:13<00:02, 32.74it/s]
Loading 0:  76%|███████▋  | 277/363 [00:13<00:02, 32.07it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 37.21it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 30.36it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 35.88it/s]
Loading 0:  82%|████████▏ | 299/363 [00:14<00:01, 38.17it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:01, 33.82it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 39.91it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 39.51it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:01, 34.65it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 40.27it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 36.07it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 36.78it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 38.21it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 31.85it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 40.84it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 41.55it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer completed after 226.05s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v22-mkmlizer
Pipeline stage MKMLizer completed in 226.54s
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-v22
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v22 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v22 ready after 100.35946726799011s
Pipeline stage MKMLDeployer completed in 100.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3816335201263428s
Received healthy response to inference request in 1.4959423542022705s
Received healthy response to inference request in 1.700049638748169s
Received healthy response to inference request in 1.543043613433838s
Received healthy response to inference request in 1.846106767654419s
5 requests
0 failed requests
5th percentile: 1.505362606048584
10th percentile: 1.5147828578948974
20th percentile: 1.5336233615875243
30th percentile: 1.5744448184967041
40th percentile: 1.6372472286224364
50th percentile: 1.700049638748169
60th percentile: 1.758472490310669
70th percentile: 1.8168953418731688
80th percentile: 1.9532121181488038
90th percentile: 2.167422819137573
95th percentile: 2.274528169631958
99th percentile: 2.3602124500274657
mean time: 1.7933551788330078
Pipeline stage StressChecker completed in 10.23s
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 0.91s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v22 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v22-profiler
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v22-profiler to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v22-profiler ready after 90.53048467636108s
Pipeline stage MKMLProfilerDeployer completed in 90.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexxi19-ft-v1-nemo-1b1810491917020b027b8820c6908a42-deploglxwv:/code/chaiverse_profiler_1741321068 --namespace tenant-chaiml-guanaco
kubectl exec -it alexxi19-ft-v1-nemo-1b1810491917020b027b8820c6908a42-deploglxwv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741321068 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1741321068/summary.json'
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 2385.09s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v22 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v22 status is now torndown due to DeploymentManager action