rirv938-mistral-24b-grp_72186

developer_uid: rirv938

submission_id: rirv938-mistral-24b-grp_72186_v1

model_name: rirv938-mistral-24b-grp_72186_v1

model_group: rirv938/mistral_24b_grpo

status: torndown

timestamp: 2025-04-29T17:19:50+00:00

num_battles: 6279

num_wins: 3455

celo_rating: 1340.35

family_friendly_score: 0.5456

family_friendly_standard_error: 0.007041599818223129

submission_type: basic

model_repo: rirv938/mistral_24b_grpo_40k_cp1184_95ff_merged

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': 0.5548943162030818, 'latency_mean': 1.8020781588554382, 'latency_p50': 1.787339448928833, 'latency_p90': 2.0043713092803954}, {'batch_size': 4, 'throughput': 1.3865437447977282, 'latency_mean': 2.873157559633255, 'latency_p50': 2.870163679122925, 'latency_p90': 3.261533999443054}, {'batch_size': 5, 'throughput': 1.5401423333170818, 'latency_mean': 3.226993292570114, 'latency_p50': 3.2392160892486572, 'latency_p90': 3.542436671257019}, {'batch_size': 8, 'throughput': 1.8724404998703783, 'latency_mean': 4.25067871928215, 'latency_p50': 4.286529779434204, 'latency_p90': 4.729354286193848}, {'batch_size': 10, 'throughput': 1.9844547173774014, 'latency_mean': 4.9866464698314665, 'latency_p50': 4.994381904602051, 'latency_p90': 5.64722638130188}, {'batch_size': 12, 'throughput': 2.082923063069254, 'latency_mean': 5.703664860725403, 'latency_p50': 5.710420489311218, 'latency_p90': 6.501925158500671}, {'batch_size': 15, 'throughput': 2.1140782565721365, 'latency_mean': 6.992486890554428, 'latency_p50': 6.964777112007141, 'latency_p90': 8.01034677028656}]

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

display_name: rirv938-mistral-24b-grp_72186_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_grpo_40k_cp1184_95ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2025-04-29

win_ratio: 0.5502468545946807

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.2, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['###', 'You:', '\n', '</s>'], 'max_input_tokens': 768, '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': '{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-grp-72186-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-72186-v1-mkmlizer to finish
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-72186-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-72186-v1-mkmlizer: Downloaded to shared memory in 166.956s
rirv938-mistral-24b-grp-72186-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptfwc4h29, device:0
rirv938-mistral-24b-grp-72186-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-72186-v1-mkmlizer: quantized model in 63.821s
rirv938-mistral-24b-grp-72186-v1-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp1184_95ff_merged in 230.777s
rirv938-mistral-24b-grp-72186-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-72186-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-72186-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1
rirv938-mistral-24b-grp-72186-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1/config.json
rirv938-mistral-24b-grp-72186-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1/special_tokens_map.json
rirv938-mistral-24b-grp-72186-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1/tokenizer_config.json
rirv938-mistral-24b-grp-72186-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1/tokenizer.json
rirv938-mistral-24b-grp-72186-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-72186-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-72186-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-grp-72186-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.90it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 13.87it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.96it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.62it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.19it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.88it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.46it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:15, 20.89it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:17, 18.85it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:23, 14.20it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:19, 16.28it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:22, 14.58it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.43it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.52it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.32it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.79it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.46it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.49it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.28it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.84it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:23, 12.32it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.30it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.89it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.40it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.50it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.25it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:12, 21.51it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.57it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.86it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.48it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.18it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 11.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.04it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.83it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.30it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:15, 15.65it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 12.19it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.19it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.65it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.44it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 15.96it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:17, 12.38it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.36it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.57it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.20it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.86it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.58it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.44it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:09, 20.58it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.27it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 16.00it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 12.82it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.67it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.97it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.57it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.18it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:48,  1.43s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:27,  1.05it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:48,  1.42it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:20,  1.87it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:01,  2.39it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:44,  3.24it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:34,  4.11it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:23,  5.92it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:16,  8.16it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:16,  8.12it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:14,  8.66it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:12,  9.83it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:13,  9.18it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 14.46it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.02it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:08, 13.82it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.46it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:08, 13.11it/s]
Loading 0:  71%|███████   | 258/363 [00:31<00:08, 12.61it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.47it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.58it/s]
Loading 0:  75%|███████▍  | 271/363 [00:31<00:06, 13.82it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:06, 14.63it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 11.95it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 18.13it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.79it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 15.11it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.73it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.29it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.51it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.26it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.64it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 16.33it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.92it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 18.12it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 21.57it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 16.01it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 16.42it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.96it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.21it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 15.72it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.23it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.92it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.64it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.77it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.60it/s]
Loading 0:  99%|█████████▉| 361/363 [00:44<00:01,  1.88it/s]
                                                            
Job rirv938-mistral-24b-grp-72186-v1-mkmlizer completed after 259.04s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-72186-v1-mkmlizer
Pipeline stage MKMLizer completed in 259.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-grp-72186-v1
Waiting for inference service rirv938-mistral-24b-grp-72186-v1 to be ready
Inference service rirv938-mistral-24b-grp-72186-v1 ready after 140.58392357826233s
Pipeline stage MKMLDeployer completed in 141.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.573184013366699s
Received healthy response to inference request in 2.2068896293640137s
Received healthy response to inference request in 1.908491611480713s
Received healthy response to inference request in 1.8490309715270996s
Received healthy response to inference request in 2.223724842071533s
5 requests
0 failed requests
5th percentile: 1.8609230995178223
10th percentile: 1.872815227508545
20th percentile: 1.8965994834899902
30th percentile: 1.9681712150573731
40th percentile: 2.087530422210693
50th percentile: 2.2068896293640137
60th percentile: 2.2136237144470217
70th percentile: 2.220357799530029
80th percentile: 2.2936166763305663
90th percentile: 2.433400344848633
95th percentile: 2.503292179107666
99th percentile: 2.5592056465148927
mean time: 2.152264213562012
Pipeline stage StressChecker completed in 12.38s
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 0.76s
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 0.76s
Shutdown handler de-registered
rirv938-mistral-24b-grp_72186_v1 status is now deployed due to DeploymentManager action
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 2856.62s
Shutdown handler de-registered
rirv938-mistral-24b-grp_72186_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_72186_v1 status is now torndown due to DeploymentManager action