developer_uid: rirv938
submission_id: rirv938-mistral-24b-rou_67411_v1
model_name: rirv938-mistral-24b-rou_67411_v1
model_group: rirv938/mistral_24b_roun
status: torndown
timestamp: 2025-03-07T02:06:15+00:00
num_battles: 9426
num_wins: 4992
celo_rating: 1300.45
family_friendly_score: 0.5347999999999999
family_friendly_standard_error: 0.007053920328441483
submission_type: basic
model_repo: rirv938/mistral_24b_round_2_dpo_40k_95w_pref_25w_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': 0.39181358555137186, 'latency_mean': 2.552154160737991, 'latency_p50': 2.5537991523742676, 'latency_p90': 2.846723508834839}, {'batch_size': 3, 'throughput': 0.7924329079424798, 'latency_mean': 3.7621102964878084, 'latency_p50': 3.7989898920059204, 'latency_p90': 4.120059847831726}, {'batch_size': 5, 'throughput': 1.0472337395713167, 'latency_mean': 4.742058004140854, 'latency_p50': 4.717076778411865, 'latency_p90': 5.2413468837738035}, {'batch_size': 6, 'throughput': 1.1320526374474065, 'latency_mean': 5.267941755056381, 'latency_p50': 5.272156834602356, 'latency_p90': 5.917795634269714}, {'batch_size': 10, 'throughput': 1.294362078564466, 'latency_mean': 7.650942505598068, 'latency_p50': 7.660053014755249, 'latency_p90': 8.540325808525086}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-rou_67411_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_round_2_dpo_40k_95w_pref_25w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-03-06
win_ratio: 0.5295989815404201
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-67411-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-rou-67411-v1-mkmlizer to finish
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-rou-67411-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-rou-67411-v1-mkmlizer: Downloaded to shared memory in 167.864s
rirv938-mistral-24b-rou-67411-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeezk1uea, device:0
rirv938-mistral-24b-rou-67411-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-rou-67411-v1-mkmlizer: quantized model in 62.259s
rirv938-mistral-24b-rou-67411-v1-mkmlizer: Processed model rirv938/mistral_24b_round_2_dpo_40k_95w_pref_25w_swear_2500_v2 in 230.124s
rirv938-mistral-24b-rou-67411-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-rou-67411-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-rou-67411-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1
rirv938-mistral-24b-rou-67411-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1/config.json
rirv938-mistral-24b-rou-67411-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1/special_tokens_map.json
rirv938-mistral-24b-rou-67411-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1/tokenizer_config.json
rirv938-mistral-24b-rou-67411-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1/tokenizer.json
rirv938-mistral-24b-rou-67411-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-rou-67411-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-67411-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-rou-67411-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.05it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 14.16it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.28it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.25it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.64it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.31it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.70it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:15, 21.45it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 19.98it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:22, 14.73it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:19, 16.67it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:21, 14.82it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.54it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 22.41it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.98it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.46it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.69it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:15, 19.20it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:15, 18.48it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:20, 14.34it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.35it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:19, 14.62it/s]
Loading 0:  23%|██▎       | 83/363 [00:04<00:13, 20.01it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:14, 19.16it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:18, 14.56it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:12, 21.03it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.85it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:13, 18.63it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 14.19it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.74it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.42it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.25it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.59it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:12, 19.63it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:16, 14.71it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:13, 16.75it/s]
Loading 0:  36%|███▋      | 132/363 [00:07<00:15, 15.10it/s]
Loading 0:  38%|███▊      | 137/363 [00:08<00:10, 20.62it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:11, 19.57it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 14.53it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 16.48it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:14, 14.99it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:10, 19.05it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.75it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.94it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.45it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.61it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.84it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.52it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:13, 13.96it/s]
Loading 0:  50%|█████     | 183/363 [00:10<00:11, 15.93it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:12, 14.53it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.42it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:08, 19.28it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:11, 14.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<03:30,  1.30s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<02:51,  1.07s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<01:48,  1.44it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:18,  1.95it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<00:58,  2.56it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:48,  3.05it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:39,  3.67it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:31,  4.59it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:27,  5.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:28<00:13,  9.92it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:11, 11.64it/s]
Loading 0:  64%|██████▍   | 234/363 [00:28<00:12, 10.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:09, 12.76it/s]
Loading 0:  66%|██████▌   | 240/363 [00:28<00:09, 12.52it/s]
Loading 0:  67%|██████▋   | 245/363 [00:29<00:06, 17.77it/s]
Loading 0:  69%|██████▊   | 249/363 [00:29<00:06, 17.73it/s]
Loading 0:  69%|██████▉   | 252/363 [00:29<00:08, 13.77it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:06, 15.76it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 13.93it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.30it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.90it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.33it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.00it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:07, 12.48it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.34it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 20.47it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.31it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.09it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.61it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 17.89it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:03, 18.85it/s]
Loading 0:  84%|████████▍ | 306/363 [00:33<00:03, 14.49it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 16.29it/s]
Loading 0:  86%|████████▌ | 312/363 [00:33<00:03, 14.80it/s]
Loading 0:  87%|████████▋ | 317/363 [00:33<00:02, 20.08it/s]
Loading 0:  88%|████████▊ | 321/363 [00:33<00:02, 19.17it/s]
Loading 0:  89%|████████▉ | 324/363 [00:34<00:02, 14.75it/s]
Loading 0:  90%|█████████ | 327/363 [00:34<00:02, 16.66it/s]
Loading 0:  91%|█████████ | 330/363 [00:34<00:02, 14.89it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.66it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 22.19it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 16.14it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.79it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 13.25it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.74it/s]
Loading 0:  98%|█████████▊| 357/363 [00:42<00:03,  1.83it/s]
Loading 0:  99%|█████████▉| 360/363 [00:42<00:01,  2.32it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.73it/s]
                                                            

Job rirv938-mistral-24b-rou-67411-v1-mkmlizer completed after 266.92s with status: succeeded
Stopping job with name rirv938-mistral-24b-rou-67411-v1-mkmlizer
Pipeline stage MKMLizer completed in 267.47s
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-67411-v1
Waiting for inference service rirv938-mistral-24b-rou-67411-v1 to be ready
Inference service rirv938-mistral-24b-rou-67411-v1 ready after 100.36895251274109s
Pipeline stage MKMLDeployer completed in 100.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1156468391418457s
Received healthy response to inference request in 2.4564571380615234s
Received healthy response to inference request in 2.684953212738037s
Received healthy response to inference request in 2.6862497329711914s
Received healthy response to inference request in 2.4886980056762695s
5 requests
0 failed requests
5th percentile: 2.4629053115844726
10th percentile: 2.4693534851074217
20th percentile: 2.4822498321533204
30th percentile: 2.5279490470886232
40th percentile: 2.60645112991333
50th percentile: 2.684953212738037
60th percentile: 2.6854718208312987
70th percentile: 2.6859904289245606
80th percentile: 2.7721291542053224
90th percentile: 2.943887996673584
95th percentile: 3.0297674179077148
99th percentile: 3.0984709548950193
mean time: 2.6864009857177735
Pipeline stage StressChecker completed in 14.86s
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 0.70s
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 0.73s
Shutdown handler de-registered
rirv938-mistral-24b-rou_67411_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 0.09s
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 rirv938-mistral-24b-rou-67411-v1-profiler
Waiting for inference service rirv938-mistral-24b-rou-67411-v1-profiler to be ready
Inference service rirv938-mistral-24b-rou-67411-v1-profiler ready after 100.3876633644104s
Pipeline stage MKMLProfilerDeployer completed in 100.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-24b-679d4633b682700d4544b2632dda178c-deplo55t28:/code/chaiverse_profiler_1741313727 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-24b-679d4633b682700d4544b2632dda178c-deplo55t28 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741313727 && 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_1741313727/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 2743.42s
Shutdown handler de-registered
rirv938-mistral-24b-rou_67411_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-rou_67411_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1