chaiml-mistral31-24b-si_50063

developer_uid: NischayDnk

submission_id: chaiml-mistral31-24b-si_50063_v2

model_name: chaiml-mistral31-24b-si_50063_v2

model_group: ChaiML/mistral31-24b-sim

status: torndown

timestamp: 2025-05-11T11:59:04+00:00

num_battles: 17581

num_wins: 9257

celo_rating: 1306.0

family_friendly_score: 0.49639999999999995

family_friendly_standard_error: 0.0070708845274123945

submission_type: basic

model_repo: ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5510228272158568, 'latency_mean': 1.814736305475235, 'latency_p50': 1.8216794729232788, 'latency_p90': 2.0286321878433227}, {'batch_size': 4, 'throughput': 1.3840368569029777, 'latency_mean': 2.879742958545685, 'latency_p50': 2.867966413497925, 'latency_p90': 3.2128220558166505}, {'batch_size': 5, 'throughput': 1.5578881227388395, 'latency_mean': 3.196506838798523, 'latency_p50': 3.1604403257369995, 'latency_p90': 3.56541428565979}, {'batch_size': 8, 'throughput': 1.8850820888241986, 'latency_mean': 4.199425467252731, 'latency_p50': 4.176321744918823, 'latency_p90': 4.731363272666931}, {'batch_size': 10, 'throughput': 1.9876774305665301, 'latency_mean': 4.970436582565307, 'latency_p50': 4.95822811126709, 'latency_p90': 5.56039719581604}, {'batch_size': 12, 'throughput': 2.0610694142534074, 'latency_mean': 5.758304349184036, 'latency_p50': 5.749002814292908, 'latency_p90': 6.515941429138183}, {'batch_size': 15, 'throughput': 2.1424368538180074, 'latency_mean': 6.912000019550323, 'latency_p50': 6.927245855331421, 'latency_p90': 7.828799057006836}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-mistral31-24b-si_50063_v2

is_internal_developer: False

language_model: ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex

model_size: 24B

ranking_group: single

throughput_3p7s: 1.76

us_pacific_date: 2025-05-11

win_ratio: 0.5265343268301007

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 chaiml-mistral31-24b-si-50063-v2-mkmlizer
Waiting for job on chaiml-mistral31-24b-si-50063-v2-mkmlizer to finish
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-si-50063-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-24b-si-50063-v2-mkmlizer: Downloaded to shared memory in 59.730s
chaiml-mistral31-24b-si-50063-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxajopdxs, device:0
chaiml-mistral31-24b-si-50063-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-24b-si-50063-v2-mkmlizer: quantized model in 53.495s
chaiml-mistral31-24b-si-50063-v2-mkmlizer: Processed model ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex in 113.225s
chaiml-mistral31-24b-si-50063-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-24b-si-50063-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-24b-si-50063-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2
chaiml-mistral31-24b-si-50063-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2/config.json
chaiml-mistral31-24b-si-50063-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2/special_tokens_map.json
chaiml-mistral31-24b-si-50063-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2/tokenizer_config.json
chaiml-mistral31-24b-si-50063-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2/tokenizer.json
chaiml-mistral31-24b-si-50063-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2/flywheel_model.1.safetensors
chaiml-mistral31-24b-si-50063-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-si-50063-v2/flywheel_model.0.safetensors
chaiml-mistral31-24b-si-50063-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.96it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.57it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.87it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.97it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.70it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.25it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.40it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.14it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.57it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.60it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.49it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.45it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.00it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.12it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.92it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.55it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.96it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.20it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.32it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.50it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.19it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.16it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.33it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.89it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.90it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.84it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.66it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.85it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.32it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.43it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.25it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.15it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.71it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.68it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.34it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.58it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.10it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.12it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 24.61it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.51it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.80it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.04it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 24.86it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.63it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.73it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 23.98it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 23.98it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:00,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.14it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:22,  6.25it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.23it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 10.97it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.90it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.84it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.29it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.29it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.50it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.40it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.99it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.83it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 22.64it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 21.83it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.49it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.48it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.19it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.06it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.19it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.35it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.64it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.60it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.11it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.16it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.52it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.28it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 27.85it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:01, 27.52it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.08it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.66it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.78it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.48it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.72it/s]
                                                            
Job chaiml-mistral31-24b-si-50063-v2-mkmlizer completed after 145.98s with status: succeeded
Stopping job with name chaiml-mistral31-24b-si-50063-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.46s
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 chaiml-mistral31-24b-si-50063-v2
Waiting for inference service chaiml-mistral31-24b-si-50063-v2 to be ready
Inference service chaiml-mistral31-24b-si-50063-v2 ready after 120.65220665931702s
Pipeline stage MKMLDeployer completed in 121.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5367846488952637s
Received healthy response to inference request in 2.008826971054077s
Received healthy response to inference request in 1.8756308555603027s
Received healthy response to inference request in 1.8374650478363037s
Received healthy response to inference request in 2.1263949871063232s
5 requests
0 failed requests
5th percentile: 1.8450982093811035
10th percentile: 1.8527313709259032
20th percentile: 1.867997694015503
30th percentile: 1.9022700786590576
40th percentile: 1.9555485248565674
50th percentile: 2.008826971054077
60th percentile: 2.0558541774749757
70th percentile: 2.102881383895874
80th percentile: 2.2084729194641115
90th percentile: 2.3726287841796876
95th percentile: 2.4547067165374754
99th percentile: 2.520369062423706
mean time: 2.077020502090454
Pipeline stage StressChecker completed in 11.93s
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 0.65s
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 0.67s
Shutdown handler de-registered
chaiml-mistral31-24b-si_50063_v2 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 chaiml-mistral31-24b-si-50063-v2-profiler
Waiting for inference service chaiml-mistral31-24b-si-50063-v2-profiler to be ready
Inference service chaiml-mistral31-24b-si-50063-v2-profiler ready after 110.76650285720825s
Pipeline stage MKMLProfilerDeployer completed in 111.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mistral31-24b9854e974cbc104147d27754b027f7bf8-deploddxtf:/code/chaiverse_profiler_1746965566 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-mistral31-24b9854e974cbc104147d27754b027f7bf8-deploddxtf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1746965566 && 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 768 --output_tokens 64 --summary /code/chaiverse_profiler_1746965566/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 2616.47s
Shutdown handler de-registered
chaiml-mistral31-24b-si_50063_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-24b-si_50063_v2 status is now torndown due to DeploymentManager action