developer_uid: rirv938
submission_id: rirv938-mistral-24b-bas_69595_v1
model_name: rirv938-mistral-24b-bas_69595_v1
model_group: rirv938/mistral_24b_base
status: inactive
timestamp: 2025-03-08T06:34:01+00:00
num_battles: 10929
num_wins: 5827
celo_rating: 1303.36
family_friendly_score: 0.5844
family_friendly_standard_error: 0.006969600275482089
submission_type: basic
model_repo: rirv938/mistral_24b_base_3_dpo_40k_70w_pref_10w_swear_2448_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': 0.386060157046127, 'latency_mean': 2.5901663076877592, 'latency_p50': 2.603297233581543, 'latency_p90': 2.869309496879578}, {'batch_size': 3, 'throughput': 0.7860995526034573, 'latency_mean': 3.811502858400345, 'latency_p50': 3.788197875022888, 'latency_p90': 4.2229238986969}, {'batch_size': 5, 'throughput': 1.0317122569238781, 'latency_mean': 4.812027785778046, 'latency_p50': 4.832036018371582, 'latency_p90': 5.327652406692504}, {'batch_size': 6, 'throughput': 1.1217319955540483, 'latency_mean': 5.314457973241806, 'latency_p50': 5.292649507522583, 'latency_p90': 5.961208391189575}, {'batch_size': 10, 'throughput': 1.280026545472381, 'latency_mean': 7.750096855163574, 'latency_p50': 7.751556873321533, 'latency_p90': 8.754165291786194}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-bas_69595_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_base_3_dpo_40k_70w_pref_10w_swear_2448_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.76
us_pacific_date: 2025-03-07
win_ratio: 0.5331686339097813
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-bas-69595-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-bas-69595-v1-mkmlizer to finish
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bas-69595-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-bas-69595-v1-mkmlizer: Downloaded to shared memory in 155.037s
rirv938-mistral-24b-bas-69595-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptvd6gf81, device:0
rirv938-mistral-24b-bas-69595-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-bas-69595-v1-mkmlizer: quantized model in 61.535s
rirv938-mistral-24b-bas-69595-v1-mkmlizer: Processed model rirv938/mistral_24b_base_3_dpo_40k_70w_pref_10w_swear_2448_v2 in 216.572s
rirv938-mistral-24b-bas-69595-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-bas-69595-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-bas-69595-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1
rirv938-mistral-24b-bas-69595-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1/config.json
rirv938-mistral-24b-bas-69595-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1/special_tokens_map.json
rirv938-mistral-24b-bas-69595-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1/tokenizer_config.json
rirv938-mistral-24b-bas-69595-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1/tokenizer.json
rirv938-mistral-24b-bas-69595-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-bas-69595-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-bas-69595-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-bas-69595-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 21.06it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.01it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.95it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.45it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:24, 13.89it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.67it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 14.09it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:15, 21.75it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.28it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:21, 15.05it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:18, 17.18it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:20, 15.37it/s]
Loading 0:  13%|█▎        | 47/363 [00:02<00:15, 21.05it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:15, 19.98it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:20, 15.01it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:17, 17.00it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 15.01it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:14, 20.51it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:15, 19.31it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:19, 14.59it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.64it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:18, 15.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:14, 18.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 22.53it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:16, 16.26it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.65it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:12, 21.90it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 23.12it/s]
Loading 0:  29%|██▊       | 104/363 [00:05<00:14, 18.20it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.36it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 14.05it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.74it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.07it/s]
Loading 0:  33%|███▎      | 119/363 [00:06<00:12, 20.15it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:12, 18.64it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:16, 14.28it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:14, 16.35it/s]
Loading 0:  36%|███▋      | 132/363 [00:07<00:15, 14.71it/s]
Loading 0:  38%|███▊      | 137/363 [00:07<00:11, 20.25it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:11, 19.09it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 14.50it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 16.56it/s]
Loading 0:  41%|████▏     | 150/363 [00:08<00:14, 14.72it/s]
Loading 0:  42%|████▏     | 154/363 [00:08<00:11, 18.04it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.02it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.34it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 15.92it/s]
Loading 0:  46%|████▌     | 166/363 [00:09<00:13, 14.17it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:14, 13.62it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.25it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 22.48it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 15.63it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:11, 16.15it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.71it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:08, 19.53it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:08, 18.79it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:11, 14.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<03:27,  1.28s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<02:49,  1.06s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<01:46,  1.46it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:17,  1.97it/s]
Loading 0:  59%|█████▊    | 213/363 [00:26<00:57,  2.59it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:47,  3.09it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:38,  3.76it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:30,  4.70it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:26,  5.27it/s]
Loading 0:  63%|██████▎   | 227/363 [00:27<00:13, 10.18it/s]
Loading 0:  64%|██████▎   | 231/363 [00:27<00:11, 11.81it/s]
Loading 0:  64%|██████▍   | 234/363 [00:28<00:12, 10.46it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:10, 12.57it/s]
Loading 0:  66%|██████▌   | 240/363 [00:28<00:09, 12.67it/s]
Loading 0:  67%|██████▋   | 245/363 [00:28<00:06, 17.92it/s]
Loading 0:  69%|██████▊   | 249/363 [00:28<00:06, 17.73it/s]
Loading 0:  69%|██████▉   | 252/363 [00:29<00:07, 14.11it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:06, 16.16it/s]
Loading 0:  71%|███████   | 258/363 [00:29<00:07, 14.68it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:05, 18.28it/s]
Loading 0:  73%|███████▎  | 266/363 [00:29<00:04, 21.25it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.51it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.34it/s]
Loading 0:  76%|███████▌  | 275/363 [00:30<00:06, 12.74it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:04, 17.56it/s]
Loading 0:  78%|███████▊  | 284/363 [00:30<00:03, 20.81it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.58it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.30it/s]
Loading 0:  81%|████████  | 293/363 [00:31<00:05, 13.17it/s]
Loading 0:  82%|████████▏ | 299/363 [00:31<00:03, 19.78it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:03, 19.31it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 14.86it/s]
Loading 0:  85%|████████▌ | 309/363 [00:32<00:03, 16.85it/s]
Loading 0:  86%|████████▌ | 312/363 [00:32<00:03, 15.51it/s]
Loading 0:  87%|████████▋ | 317/363 [00:32<00:02, 21.01it/s]
Loading 0:  88%|████████▊ | 321/363 [00:33<00:02, 19.50it/s]
Loading 0:  89%|████████▉ | 324/363 [00:33<00:02, 14.75it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:02, 16.79it/s]
Loading 0:  91%|█████████ | 330/363 [00:33<00:02, 15.12it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.69it/s]
Loading 0:  93%|█████████▎| 339/363 [00:34<00:01, 19.63it/s]
Loading 0:  94%|█████████▍| 342/363 [00:34<00:01, 15.03it/s]
Loading 0:  95%|█████████▌| 345/363 [00:34<00:01, 17.10it/s]
Loading 0:  96%|█████████▌| 348/363 [00:34<00:00, 15.44it/s]
Loading 0:  97%|█████████▋| 353/363 [00:35<00:00, 20.99it/s]
Loading 0:  98%|█████████▊| 357/363 [00:42<00:03,  1.74it/s]
Loading 0:  99%|█████████▉| 360/363 [00:42<00:01,  2.24it/s]
Loading 0: 100%|█████████▉| 362/363 [00:42<00:00,  2.65it/s]
                                                            

Job rirv938-mistral-24b-bas-69595-v1-mkmlizer completed after 246.82s with status: succeeded
Stopping job with name rirv938-mistral-24b-bas-69595-v1-mkmlizer
Pipeline stage MKMLizer completed in 247.27s
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-bas-69595-v1
Waiting for inference service rirv938-mistral-24b-bas-69595-v1 to be ready
Inference service rirv938-mistral-24b-bas-69595-v1 ready after 100.58130097389221s
Pipeline stage MKMLDeployer completed in 101.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9603447914123535s
Received healthy response to inference request in 2.4280269145965576s
Received healthy response to inference request in 2.492440938949585s
Received healthy response to inference request in 2.3793859481811523s
Received healthy response to inference request in 2.49336838722229s
5 requests
0 failed requests
5th percentile: 2.3891141414642334
10th percentile: 2.3988423347473145
20th percentile: 2.4182987213134766
30th percentile: 2.440909719467163
40th percentile: 2.466675329208374
50th percentile: 2.492440938949585
60th percentile: 2.492811918258667
70th percentile: 2.493182897567749
80th percentile: 2.586763668060303
90th percentile: 2.773554229736328
95th percentile: 2.8669495105743406
99th percentile: 2.941665735244751
mean time: 2.550713396072388
Pipeline stage StressChecker completed in 14.05s
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 0.62s
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 0.88s
Shutdown handler de-registered
rirv938-mistral-24b-bas_69595_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 0.12s
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-bas-69595-v1-profiler
Waiting for inference service rirv938-mistral-24b-bas-69595-v1-profiler to be ready
Inference service rirv938-mistral-24b-bas-69595-v1-profiler ready after 100.39667010307312s
Pipeline stage MKMLProfilerDeployer completed in 100.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-24b-8eb86ab973033a8b4b89af443609c17a-deplocgldr:/code/chaiverse_profiler_1741416141 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-24b-8eb86ab973033a8b4b89af443609c17a-deplocgldr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741416141 && 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_1741416141/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 2747.98s
Shutdown handler de-registered
rirv938-mistral-24b-bas_69595_v1 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1