developer_uid: rirv938
submission_id: rirv938-mistral-24b-rou_85599_v1
model_name: rirv938-mistral-24b-rou_85599_v1
model_group: rirv938/mistral_24b_roun
status: torndown
timestamp: 2025-03-08T17:34:07+00:00
num_battles: 10961
num_wins: 5614
celo_rating: 1294.03
family_friendly_score: 0.5698
family_friendly_standard_error: 0.007001827761377739
submission_type: basic
model_repo: rirv938/mistral_24b_round_3_dpo_40k_60w_pref_10w_swear_2500_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3868157731732988, 'latency_mean': 2.585144981145859, 'latency_p50': 2.5648211240768433, 'latency_p90': 2.8839927196502684}, {'batch_size': 3, 'throughput': 0.7871564771747885, 'latency_mean': 3.7962842190265658, 'latency_p50': 3.7846802473068237, 'latency_p90': 4.218761849403381}, {'batch_size': 5, 'throughput': 1.0316807942474944, 'latency_mean': 4.8259086561203, 'latency_p50': 4.88102924823761, 'latency_p90': 5.335148882865906}, {'batch_size': 6, 'throughput': 1.1182139894555212, 'latency_mean': 5.325407735109329, 'latency_p50': 5.357113480567932, 'latency_p90': 5.997431039810181}, {'batch_size': 10, 'throughput': 1.2764797665763452, 'latency_mean': 7.766641548871994, 'latency_p50': 7.8189239501953125, 'latency_p90': 8.822281336784362}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-rou_85599_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_round_3_dpo_40k_60w_pref_10w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.77
us_pacific_date: 2025-03-08
win_ratio: 0.5121795456618922
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 rirv938-mistral-24b-rou-85599-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-rou-85599-v1-mkmlizer to finish
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-85599-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-rou-85599-v1-mkmlizer: Downloaded to shared memory in 166.502s
rirv938-mistral-24b-rou-85599-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxp2ycl9z, device:0
rirv938-mistral-24b-rou-85599-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-rou-85599-v1-mkmlizer: quantized model in 63.382s
rirv938-mistral-24b-rou-85599-v1-mkmlizer: Processed model rirv938/mistral_24b_round_3_dpo_40k_60w_pref_10w_swear_2500_v2 in 229.885s
rirv938-mistral-24b-rou-85599-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-rou-85599-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-rou-85599-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1
rirv938-mistral-24b-rou-85599-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1/config.json
rirv938-mistral-24b-rou-85599-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1/special_tokens_map.json
rirv938-mistral-24b-rou-85599-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1/tokenizer_config.json
rirv938-mistral-24b-rou-85599-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1/tokenizer.json
rirv938-mistral-24b-rou-85599-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-rou-85599-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-85599-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-rou-85599-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.26it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 13.93it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:16, 20.80it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.85it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:30, 11.32it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.47it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.20it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.41it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.20it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.71it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.04it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:24, 13.22it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:25, 12.58it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:19, 16.13it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 19.28it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.52it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 12.84it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.68it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 11.12it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.94it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.67it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.38it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.34it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:20, 13.76it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.41it/s]
Loading 0:  23%|██▎       | 83/363 [00:05<00:14, 19.69it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:14, 18.58it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:20, 13.40it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:14, 18.36it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.53it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.32it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.90it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.70it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:19, 13.35it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.85it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.20it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.27it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:12, 18.52it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:16, 14.16it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:14, 16.28it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:15, 14.68it/s]
Loading 0:  38%|███▊      | 137/363 [00:08<00:11, 20.13it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:11, 19.31it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:15, 14.51it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:13, 16.42it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:14, 15.00it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:10, 20.44it/s]
Loading 0:  44%|████▍     | 159/363 [00:09<00:10, 19.35it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:14, 14.34it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:12, 16.42it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:13, 14.82it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.89it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:09, 19.52it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:12, 14.82it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:10, 16.89it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:11, 15.26it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 19.16it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 22.80it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.76it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.13it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:49,  1.43s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:27,  1.06it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:47,  1.43it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:19,  1.89it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:00,  2.42it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:43,  3.29it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:33,  4.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:28<00:20,  6.66it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:15,  8.26it/s]
Loading 0:  64%|██████▍   | 234/363 [00:29<00:15,  8.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:12, 10.27it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:11, 10.64it/s]
Loading 0:  67%|██████▋   | 245/363 [00:29<00:07, 15.30it/s]
Loading 0:  69%|██████▊   | 249/363 [00:30<00:07, 16.00it/s]
Loading 0:  69%|██████▉   | 252/363 [00:30<00:08, 13.05it/s]
Loading 0:  70%|███████   | 255/363 [00:30<00:07, 15.19it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 13.72it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.67it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 21.55it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.66it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.40it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:07, 12.52it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.80it/s]
Loading 0:  79%|███████▊  | 285/363 [00:32<00:04, 18.48it/s]
Loading 0:  79%|███████▉  | 288/363 [00:32<00:05, 14.34it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:04, 16.21it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:04, 14.79it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.31it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.80it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 16.00it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.66it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.92it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 18.07it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 21.54it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 16.07it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.60it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.81it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.80it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.02it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.41it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 15.87it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.62it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.68it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.97it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.60it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.05it/s]
                                                            

Job rirv938-mistral-24b-rou-85599-v1-mkmlizer completed after 267.1s with status: succeeded
Stopping job with name rirv938-mistral-24b-rou-85599-v1-mkmlizer
Pipeline stage MKMLizer completed in 267.59s
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 rirv938-mistral-24b-rou-85599-v1
Waiting for inference service rirv938-mistral-24b-rou-85599-v1 to be ready
Inference service rirv938-mistral-24b-rou-85599-v1 ready after 90.33337187767029s
Pipeline stage MKMLDeployer completed in 90.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0278661251068115s
Received healthy response to inference request in 2.6388230323791504s
Received healthy response to inference request in 2.4406259059906006s
Received healthy response to inference request in 2.594330310821533s
Received healthy response to inference request in 2.418226718902588s
5 requests
0 failed requests
5th percentile: 2.4227065563201906
10th percentile: 2.427186393737793
20th percentile: 2.436146068572998
30th percentile: 2.471366786956787
40th percentile: 2.5328485488891603
50th percentile: 2.594330310821533
60th percentile: 2.61212739944458
70th percentile: 2.629924488067627
80th percentile: 2.7166316509246826
90th percentile: 2.872248888015747
95th percentile: 2.9500575065612793
99th percentile: 3.012304401397705
mean time: 2.623974418640137
Pipeline stage StressChecker completed in 14.46s
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 0.69s
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 0.70s
Shutdown handler de-registered
rirv938-mistral-24b-rou_85599_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-rou-85599-v1-profiler
Waiting for inference service rirv938-mistral-24b-rou-85599-v1-profiler to be ready
Inference service rirv938-mistral-24b-rou-85599-v1-profiler ready after 100.3977563381195s
Pipeline stage MKMLProfilerDeployer completed in 100.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-24b-69a788377acf8054eb47f7e6c171bf53-deplovlgnm:/code/chaiverse_profiler_1741455789 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-24b-69a788377acf8054eb47f7e6c171bf53-deplovlgnm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741455789 && 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_1741455789/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 2568.89s
Shutdown handler de-registered
rirv938-mistral-24b-rou_85599_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-rou_85599_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1