rirv938-mistral-24b-grp_36770

developer_uid: rirv938

submission_id: rirv938-mistral-24b-grp_36770_v2

model_name: rirv938-mistral-24b-grp_36770_v2

model_group: rirv938/mistral_24b_grpo

status: torndown

timestamp: 2025-04-29T17:20:11+00:00

num_battles: 6195

num_wins: 3222

celo_rating: 1318.73

family_friendly_score: 0.5791999999999999

family_friendly_standard_error: 0.006981795757539746

submission_type: basic

model_repo: rirv938/mistral_24b_grpo_40k_cp296_92ff_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': 0.552050719349219, 'latency_mean': 1.8113538086414338, 'latency_p50': 1.8218276500701904, 'latency_p90': 2.010990595817566}, {'batch_size': 4, 'throughput': 1.3858381577232326, 'latency_mean': 2.8787942004203795, 'latency_p50': 2.839886784553528, 'latency_p90': 3.1898330211639405}, {'batch_size': 5, 'throughput': 1.5414806052078693, 'latency_mean': 3.222665584087372, 'latency_p50': 3.2592111825942993, 'latency_p90': 3.5384016752243044}, {'batch_size': 8, 'throughput': 1.86417560929057, 'latency_mean': 4.247705197334289, 'latency_p50': 4.240220785140991, 'latency_p90': 4.807822036743164}, {'batch_size': 10, 'throughput': 2.014743708721628, 'latency_mean': 4.924024950265885, 'latency_p50': 4.888450980186462, 'latency_p90': 5.6498997688293455}, {'batch_size': 12, 'throughput': 2.0624377084710814, 'latency_mean': 5.748541934490204, 'latency_p50': 5.797289252281189, 'latency_p90': 6.467415428161621}, {'batch_size': 15, 'throughput': 2.1394028802849965, 'latency_mean': 6.893518072366715, 'latency_p50': 6.944236636161804, 'latency_p90': 7.812350416183471}]

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

display_name: rirv938-mistral-24b-grp_36770_v2

is_internal_developer: True

language_model: rirv938/mistral_24b_grpo_40k_cp296_92ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2025-04-29

win_ratio: 0.5200968523002422

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-36770-v2-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-36770-v2-mkmlizer to finish
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-36770-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-36770-v2-mkmlizer: Downloaded to shared memory in 174.222s
rirv938-mistral-24b-grp-36770-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm4dbhx08, device:0
rirv938-mistral-24b-grp-36770-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-36770-v2-mkmlizer: quantized model in 63.057s
rirv938-mistral-24b-grp-36770-v2-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp296_92ff_merged in 237.280s
rirv938-mistral-24b-grp-36770-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-36770-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-36770-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2
rirv938-mistral-24b-grp-36770-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2/config.json
rirv938-mistral-24b-grp-36770-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2/special_tokens_map.json
rirv938-mistral-24b-grp-36770-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2/tokenizer_config.json
rirv938-mistral-24b-grp-36770-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2/tokenizer.json
rirv938-mistral-24b-grp-36770-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-36770-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v2/flywheel_model.0.safetensors
rirv938-mistral-24b-grp-36770-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.22it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.61it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.38it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.37it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.02it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.01it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.46it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 12.64it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.13it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.50it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.48it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.80it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:22, 14.05it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:23, 13.48it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.47it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:15, 20.66it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 14.76it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:21, 14.24it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 15.26it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.40it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.44it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.71it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.68it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.41it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.65it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.47it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.47it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.00it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.46it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.71it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 20.92it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.46it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.31it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.44it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.09it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.09it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.52it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.69it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:13, 18.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.31it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:16, 13.96it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:15, 14.88it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.36it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.63it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:09, 22.32it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 15.75it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.41it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.95it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 15.30it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 16.04it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.83it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.67it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:09, 20.74it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.30it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.99it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 12.82it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.64it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.30it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.10it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.93it/s]
Loading 0:  55%|█████▌    | 200/363 [00:26<00:10, 15.93it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:30,  1.67s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:27,  1.30s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:01,  1.29it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:25,  1.80it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:02,  2.40it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:50,  2.91it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.55it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.49it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  4.97it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.70it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 11.83it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.77it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.20it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:10, 11.64it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:10, 11.58it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.57it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 19.12it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.27it/s]
Loading 0:  70%|██████▉   | 253/363 [00:30<00:07, 13.86it/s]
Loading 0:  70%|███████   | 255/363 [00:30<00:07, 14.82it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.05it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 18.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 21.35it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.99it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 15.91it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:06, 14.19it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:06, 13.65it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.74it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.15it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 15.06it/s]
Loading 0:  80%|███████▉  | 289/363 [00:32<00:05, 14.39it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:04, 15.35it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.25it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.30it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.82it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.77it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.53it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.52it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.55it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.82it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.43it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.24it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.99it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 18.01it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.22it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.77it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.51it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 13.12it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.16it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.50it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.62it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.09it/s]
                                                            
Job rirv938-mistral-24b-grp-36770-v2-mkmlizer completed after 268.86s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-36770-v2-mkmlizer
Pipeline stage MKMLizer completed in 269.30s
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-grp-36770-v2
Waiting for inference service rirv938-mistral-24b-grp-36770-v2 to be ready
Inference service rirv938-mistral-24b-grp-36770-v2 ready after 140.49602580070496s
Pipeline stage MKMLDeployer completed in 140.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4681179523468018s
Received healthy response to inference request in 2.2995920181274414s
Received healthy response to inference request in 1.9635510444641113s
Received healthy response to inference request in 2.0679728984832764s
Received healthy response to inference request in 2.1247503757476807s
5 requests
0 failed requests
5th percentile: 1.9844354152679444
10th percentile: 2.0053197860717775
20th percentile: 2.0470885276794433
30th percentile: 2.0793283939361573
40th percentile: 2.1020393848419188
50th percentile: 2.1247503757476807
60th percentile: 2.194687032699585
70th percentile: 2.264623689651489
80th percentile: 2.3332972049713137
90th percentile: 2.4007075786590577
95th percentile: 2.4344127655029295
99th percentile: 2.461376914978027
mean time: 2.184796857833862
Pipeline stage StressChecker completed in 12.37s
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 0.63s
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
rirv938-mistral-24b-grp_36770_v2 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 2863.76s
Shutdown handler de-registered
rirv938-mistral-24b-grp_36770_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_36770_v2 status is now torndown due to DeploymentManager action