alexxi19-ft-v1-nemo-ba_27407

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-ba_27407_v21

model_name: alexxi19-ft-v1-nemo-ba_27407_v21

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-03-07T04:09:21+00:00

num_battles: 10614

num_wins: 5109

celo_rating: 1263.62

family_friendly_score: 0.5358

family_friendly_standard_error: 0.007052919395541112

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': 0.6060270642401159, 'latency_mean': 1.6499961280822755, 'latency_p50': 1.635050654411316, 'latency_p90': 1.8251593112945557}, {'batch_size': 3, 'throughput': 1.1103750166595472, 'latency_mean': 2.698022722005844, 'latency_p50': 2.709299683570862, 'latency_p90': 3.006019639968872}, {'batch_size': 5, 'throughput': 1.3422500385424891, 'latency_mean': 3.7046299946308134, 'latency_p50': 3.7107725143432617, 'latency_p90': 4.1043397188186646}, {'batch_size': 6, 'throughput': 1.4071761867635413, 'latency_mean': 4.24265888094902, 'latency_p50': 4.235613703727722, 'latency_p90': 4.751762509346008}, {'batch_size': 8, 'throughput': 1.4696857353031798, 'latency_mean': 5.416523036956787, 'latency_p50': 5.442869424819946, 'latency_p90': 6.120939993858338}, {'batch_size': 10, 'throughput': 1.513626237323672, 'latency_mean': 6.556081838607788, 'latency_p50': 6.64879298210144, 'latency_p90': 7.415935325622558}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v21

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-03-06

win_ratio: 0.4813453928773318

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-v21-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: Downloaded to shared memory in 167.502s
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnl7rh66b, device:0
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: quantized model in 36.852s
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 204.354s
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v21
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v21/config.json
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v21/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v21/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v21/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v21/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v21-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<10:49,  1.81s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:02,  1.47it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:19,  4.41it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:50,  6.77it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:34,  9.94it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:23, 14.24it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:19, 16.67it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 23.41it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:11, 27.42it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.54it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:08, 34.26it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:08, 36.92it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:10, 29.27it/s]
Loading 0:  21%|██        | 76/363 [00:07<00:07, 36.78it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:08, 33.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 35.93it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:07, 37.12it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:08, 32.57it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 38.05it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 39.15it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:07, 33.97it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:06, 36.92it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:07, 33.03it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 35.37it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 35.21it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 38.27it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:06, 34.81it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:05, 36.91it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:05, 39.77it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:06, 31.10it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 39.70it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 40.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:05, 36.32it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 42.59it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:04, 42.37it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 37.14it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:03, 42.34it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:04, 37.64it/s]
Loading 0:  59%|█████▊    | 213/363 [00:11<00:04, 33.27it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 41.07it/s]
Loading 0:  62%|██████▏   | 226/363 [00:12<00:03, 36.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 36.26it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 36.71it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 33.23it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:03, 35.87it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 35.61it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 38.57it/s]
Loading 0:  72%|███████▏  | 260/363 [00:12<00:02, 37.56it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 40.88it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 36.49it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 35.46it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:02, 35.69it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 36.09it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 29.35it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 33.71it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:01, 34.09it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 37.52it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 30.08it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 35.29it/s]
Loading 0:  87%|████████▋ | 316/363 [00:14<00:01, 38.18it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:01, 28.62it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 36.77it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:00, 32.97it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 34.16it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 34.06it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 38.99it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 34.86it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 35.66it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 38.97it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer completed after 226.04s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v21-mkmlizer
Pipeline stage MKMLizer completed in 226.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v21
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v21 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v21 ready after 100.37265110015869s
Pipeline stage MKMLDeployer completed in 100.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3994553089141846s
Received healthy response to inference request in 1.7910304069519043s
Received healthy response to inference request in 1.6343629360198975s
Received healthy response to inference request in 1.6553735733032227s
Received healthy response to inference request in 1.6791529655456543s
5 requests
0 failed requests
5th percentile: 1.6385650634765625
10th percentile: 1.6427671909332275
20th percentile: 1.6511714458465576
30th percentile: 1.660129451751709
40th percentile: 1.6696412086486816
50th percentile: 1.6791529655456543
60th percentile: 1.7239039421081543
70th percentile: 1.7686549186706544
80th percentile: 1.9127153873443605
90th percentile: 2.1560853481292725
95th percentile: 2.2777703285217283
99th percentile: 2.3751183128356934
mean time: 1.8318750381469726
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 0.74s
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 1.03s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v21 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v21-profiler
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v21-profiler to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v21-profiler ready after 100.47260022163391s
Pipeline stage MKMLProfilerDeployer completed in 100.89s
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-3402cf5ae65b247042972fe9c372b90e-deplo7sw5x:/code/chaiverse_profiler_1741321066 --namespace tenant-chaiml-guanaco
kubectl exec -it alexxi19-ft-v1-nemo-3402cf5ae65b247042972fe9c372b90e-deplo7sw5x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741321066 && 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_1741321066/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 2322.25s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v21 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v21 status is now torndown due to DeploymentManager action