marinaraspaghetti-nemomi_1739

developer_uid: azuruce

submission_id: marinaraspaghetti-nemomi_1739_v5

model_name: marinaraspaghetti-nemomi_1739_v5

model_group: MarinaraSpaghetti/NemoMi

status: torndown

timestamp: 2024-09-26T02:08:54+00:00

num_battles: 8030

num_wins: 4138

celo_rating: 1270.3

family_friendly_score: 0.5654792414146592

family_friendly_standard_error: 0.005588007327495393

submission_type: basic

model_repo: MarinaraSpaghetti/NemoMix-Unleashed-12B

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6123578010855157, 'latency_mean': 1.6329694736003875, 'latency_p50': 1.6374634504318237, 'latency_p90': 1.7874932050704957}, {'batch_size': 3, 'throughput': 1.08172606171529, 'latency_mean': 2.766377379894257, 'latency_p50': 2.766950249671936, 'latency_p90': 3.041890835762024}, {'batch_size': 5, 'throughput': 1.2392785210565933, 'latency_mean': 4.010309193134308, 'latency_p50': 4.014888286590576, 'latency_p90': 4.471416020393372}, {'batch_size': 6, 'throughput': 1.2644917598970937, 'latency_mean': 4.72380671620369, 'latency_p50': 4.735833525657654, 'latency_p90': 5.330991268157959}, {'batch_size': 8, 'throughput': 1.2517587106563917, 'latency_mean': 6.356709369421005, 'latency_p50': 6.340768218040466, 'latency_p90': 7.281707334518432}, {'batch_size': 10, 'throughput': 1.210699731025774, 'latency_mean': 8.20531467437744, 'latency_p50': 8.244705080986023, 'latency_p90': 9.423895931243896}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: marinaraspaghetti-nemomi_1739_v5

is_internal_developer: True

language_model: MarinaraSpaghetti/NemoMix-Unleashed-12B

model_size: 13B

ranking_group: single

throughput_3p7s: 1.22

us_pacific_date: 2024-09-25

win_ratio: 0.5153175591531756

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', '<|eot_id|>', '<|end_of_text|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline %s
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLizer
Running pipeline stage MKMLizer
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=%s
Shutdown handler de-registered
MKMLizerError("module 'kubernetes.config' has no attribute 'load_kube_config'")
marinaraspaghetti-nemomi_1739_v6 status is now failed due to DeploymentManager action
Starting job with name marinaraspaghetti-nemomi-1739-v5-mkmlizer
Waiting for job on marinaraspaghetti-nemomi-1739-v5-mkmlizer to finish
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║     _____            __           __                                ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║       /___/                                                         ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║                                                                     ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  https://mk1.ai                                                     ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║                                                                     ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  belonging to:                                                      ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║                                                                     ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  Chai Research Corp.                                                ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ║                                                                     ║
marinaraspaghetti-nemomi-1739-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
marinaraspaghetti-nemomi-1739-v5-mkmlizer: Downloaded to shared memory in 29.357s
marinaraspaghetti-nemomi-1739-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp29ctpygp, device:0
marinaraspaghetti-nemomi-1739-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
marinaraspaghetti-nemomi-1739-v5-mkmlizer: quantized model in 37.901s
marinaraspaghetti-nemomi-1739-v5-mkmlizer: Processed model MarinaraSpaghetti/NemoMix-Unleashed-12B in 67.259s
marinaraspaghetti-nemomi-1739-v5-mkmlizer: creating bucket guanaco-mkml-models
marinaraspaghetti-nemomi-1739-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
marinaraspaghetti-nemomi-1739-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/marinaraspaghetti-nemomi-1739-v5
marinaraspaghetti-nemomi-1739-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/marinaraspaghetti-nemomi-1739-v5/special_tokens_map.json
marinaraspaghetti-nemomi-1739-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/marinaraspaghetti-nemomi-1739-v5/config.json
marinaraspaghetti-nemomi-1739-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/marinaraspaghetti-nemomi-1739-v5/tokenizer_config.json
marinaraspaghetti-nemomi-1739-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/marinaraspaghetti-nemomi-1739-v5/tokenizer.json
marinaraspaghetti-nemomi-1739-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/marinaraspaghetti-nemomi-1739-v5/flywheel_model.0.safetensors
marinaraspaghetti-nemomi-1739-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:24,  3.06s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.33it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.88it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  7.95it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.30it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.34it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:20, 15.62it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 17.97it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 22.14it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 24.09it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 28.33it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:10, 29.17it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 33.39it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:09, 32.28it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 34.87it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 34.04it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 37.10it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 35.31it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 37.50it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 35.54it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 37.41it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:07, 35.63it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 37.32it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:06, 36.42it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 27.67it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:08, 28.82it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 34.37it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:06, 37.83it/s]
Loading 0:  39%|███▉      | 141/363 [00:10<00:06, 33.44it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 41.22it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 41.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 42.96it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:04, 41.19it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 41.42it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:04, 46.30it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:04, 43.87it/s]
Loading 0:  52%|█████▏    | 187/363 [00:11<00:04, 41.74it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:03, 45.16it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:03, 43.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:05, 31.19it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:04, 32.38it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 34.72it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 37.69it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:04, 32.71it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 40.80it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 40.70it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 41.73it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 40.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 39.71it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 43.02it/s]
Loading 0:  72%|███████▏  | 261/363 [00:13<00:02, 42.49it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 42.55it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 43.36it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 35.49it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 31.08it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 31.27it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 34.07it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 33.49it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 35.54it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 34.34it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 37.08it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 36.26it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 38.15it/s]
Loading 0:  89%|████████▉ | 323/363 [00:14<00:01, 36.37it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 38.70it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 37.09it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 39.39it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 38.07it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 41.78it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 42.12it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 32.20it/s]
                                                            
Job marinaraspaghetti-nemomi-1739-v5-mkmlizer completed after 114.62s with status: succeeded
Stopping job with name marinaraspaghetti-nemomi-1739-v5-mkmlizer
Pipeline stage MKMLizer completed in 115.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service marinaraspaghetti-nemomi-1739-v5
Waiting for inference service marinaraspaghetti-nemomi-1739-v5 to be ready
Inference service marinaraspaghetti-nemomi-1739-v5 ready after 210.53226351737976s
Pipeline stage MKMLDeployer completed in 210.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.794487237930298s
Received healthy response to inference request in 1.644235372543335s
Received healthy response to inference request in 1.8564913272857666s
Received healthy response to inference request in 1.9195990562438965s
Received healthy response to inference request in 1.6267898082733154s
5 requests
0 failed requests
5th percentile: 1.6302789211273194
10th percentile: 1.6337680339813232
20th percentile: 1.640746259689331
30th percentile: 1.6866865634918213
40th percentile: 1.7715889453887939
50th percentile: 1.8564913272857666
60th percentile: 1.8817344188690186
70th percentile: 1.9069775104522706
80th percentile: 2.094576692581177
90th percentile: 2.4445319652557376
95th percentile: 2.6195096015930175
99th percentile: 2.7594917106628416
mean time: 1.9683205604553222
Pipeline stage StressChecker completed in 10.51s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.62s
Shutdown handler de-registered
marinaraspaghetti-nemomi_1739_v5 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 0.13s
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 marinaraspaghetti-nemomi-1739-v5-profiler
Waiting for inference service marinaraspaghetti-nemomi-1739-v5-profiler to be ready
Inference service marinaraspaghetti-nemomi-1739-v5-profiler ready after 220.57801818847656s
Pipeline stage MKMLProfilerDeployer completed in 220.94s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/marinaraspaghetti-ne7c0cab358653270c58439224a40a7812-deplo9ddk7:/code/chaiverse_profiler_1727317145 --namespace tenant-chaiml-guanaco
kubectl exec -it marinaraspaghetti-ne7c0cab358653270c58439224a40a7812-deplo9ddk7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727317145 && 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_1727317145/summary.json'
kubectl exec -it marinaraspaghetti-ne7c0cab358653270c58439224a40a7812-deplo9ddk7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727317145/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1161.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service marinaraspaghetti-nemomi-1739-v5-profiler is running
Tearing down inference service marinaraspaghetti-nemomi-1739-v5-profiler
Service marinaraspaghetti-nemomi-1739-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.13s
Shutdown handler de-registered
marinaraspaghetti-nemomi_1739_v5 status is now inactive due to auto deactivation removed underperforming models
marinaraspaghetti-nemomi_1739_v5 status is now torndown due to DeploymentManager action