developer_uid: rirv938
submission_id: rirv938-mistral-24b-grp_39559_v2
model_name: rirv938-mistral-24b-grp_39559_v2
model_group: rirv938/mistral_24b_grpo
status: torndown
timestamp: 2025-04-29T01:12:47+00:00
num_battles: 8569
num_wins: 4313
celo_rating: 1294.0
family_friendly_score: 0.5774
family_friendly_standard_error: 0.006985831947592212
submission_type: basic
model_repo: rirv938/mistral_24b_grpo_40k_cp148_95ff_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5318322127838074, 'latency_mean': 1.8802266705036164, 'latency_p50': 1.8855761289596558, 'latency_p90': 2.0878856420516967}, {'batch_size': 3, 'throughput': 1.0991762647065608, 'latency_mean': 2.7115214681625366, 'latency_p50': 2.705918073654175, 'latency_p90': 2.9912447214126585}, {'batch_size': 5, 'throughput': 1.4031349771673562, 'latency_mean': 3.540031806230545, 'latency_p50': 3.5276154279708862, 'latency_p90': 3.989394998550415}, {'batch_size': 6, 'throughput': 1.5291828712132678, 'latency_mean': 3.8974206137657164, 'latency_p50': 3.9231488704681396, 'latency_p90': 4.424249482154846}, {'batch_size': 8, 'throughput': 1.661586551112345, 'latency_mean': 4.777930997610092, 'latency_p50': 4.764765739440918, 'latency_p90': 5.373130488395691}, {'batch_size': 10, 'throughput': 1.7617196827382058, 'latency_mean': 5.632223051786423, 'latency_p50': 5.637709021568298, 'latency_p90': 6.3297686100006105}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-mistral-24b-grp_39559_v2
is_internal_developer: True
language_model: rirv938/mistral_24b_grpo_40k_cp148_95ff_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.47
us_pacific_date: 2025-04-28
win_ratio: 0.5033259423503326
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:', '</s>', '\n', '###'], 'max_input_tokens': 1024, '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-39559-v2-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-39559-v2-mkmlizer to finish
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ║ ║
rirv938-mistral-24b-grp-39559-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-39559-v2-mkmlizer: Downloaded to shared memory in 161.986s
rirv938-mistral-24b-grp-39559-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0vwiq4vc, device:0
rirv938-mistral-24b-grp-39559-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-39559-v2-mkmlizer: quantized model in 64.955s
rirv938-mistral-24b-grp-39559-v2-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp148_95ff_merged in 226.941s
rirv938-mistral-24b-grp-39559-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-39559-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-39559-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-39559-v2
rirv938-mistral-24b-grp-39559-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-39559-v2/tokenizer_config.json
rirv938-mistral-24b-grp-39559-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-39559-v2/tokenizer.json
rirv938-mistral-24b-grp-39559-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-39559-v2/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-39559-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-39559-v2/flywheel_model.0.safetensors
rirv938-mistral-24b-grp-39559-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 28.92it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:25, 13.80it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:16, 20.87it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:25, 13.78it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:31, 11.08it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:21, 15.81it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:22, 15.22it/s] Loading 0: 7%|▋ | 25/363 [00:01<00:21, 15.44it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:18, 17.88it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:15, 21.82it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:22, 14.86it/s] Loading 0: 10%|█ | 38/363 [00:02<00:21, 15.46it/s] Loading 0: 11%|█ | 40/363 [00:02<00:23, 13.70it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:24, 13.12it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 17.33it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:14, 21.26it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:21, 14.71it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:22, 13.75it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:21, 14.57it/s] Loading 0: 16%|█▋ | 59/363 [00:03<00:25, 11.78it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:16, 18.00it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:13, 21.86it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.94it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.55it/s] Loading 0: 21%|██ | 77/363 [00:05<00:23, 12.26it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 17.33it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.77it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 15.04it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.30it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:14, 19.01it/s] Loading 0: 27%|██▋ | 99/363 [00:06<00:12, 20.54it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:13, 18.84it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:18, 14.30it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:19, 13.13it/s] Loading 0: 30%|███ | 109/363 [00:06<00:19, 12.80it/s] Loading 0: 31%|███ | 111/363 [00:07<00:18, 13.67it/s] Loading 0: 31%|███ | 113/363 [00:07<00:22, 11.01it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:14, 17.24it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.11it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:16, 14.62it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:15, 15.20it/s] Loading 0: 36%|███▌ | 130/363 [00:08<00:17, 13.52it/s] Loading 0: 36%|███▋ | 132/363 [00:08<00:17, 12.94it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:13, 17.31it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 21.08it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:15, 14.52it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:15, 13.64it/s] Loading 0: 40%|████ | 147/363 [00:09<00:14, 14.42it/s] Loading 0: 41%|████ | 149/363 [00:09<00:18, 11.54it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:12, 17.31it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 20.54it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:14, 14.38it/s] Loading 0: 45%|████▍ | 163/363 [00:10<00:14, 13.37it/s] Loading 0: 45%|████▌ | 165/363 [00:10<00:13, 14.22it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:17, 11.40it/s] Loading 0: 47%|████▋ | 172/363 [00:11<00:11, 17.23it/s] Loading 0: 48%|████▊ | 176/363 [00:11<00:09, 20.56it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 14.47it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:11, 15.10it/s] Loading 0: 51%|█████ | 184/363 [00:11<00:13, 13.50it/s] Loading 0: 51%|█████ | 186/363 [00:12<00:13, 12.92it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:10, 17.24it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:07, 21.36it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:10, 15.33it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 16.00it/s] Loading 0: 56%|█████▌ | 202/363 [00:27<04:26, 1.65s/it] Loading 0: 56%|█████▌ | 203/363 [00:28<03:53, 1.46s/it] Loading 0: 57%|█████▋ | 207/363 [00:28<02:11, 1.19it/s] Loading 0: 58%|█████▊ | 210/363 [00:28<01:30, 1.69it/s] Loading 0: 59%|█████▊ | 213/363 [00:28<01:05, 2.30it/s] Loading 0: 59%|█████▉ | 215/363 [00:28<00:52, 2.80it/s] Loading 0: 60%|█████▉ | 217/363 [00:28<00:42, 3.44it/s] Loading 0: 60%|██████ | 219/363 [00:29<00:33, 4.36it/s] Loading 0: 61%|██████ | 221/363 [00:29<00:28, 4.90it/s] Loading 0: 62%|██████▏ | 226/363 [00:29<00:15, 8.69it/s] Loading 0: 63%|██████▎ | 230/363 [00:29<00:11, 11.81it/s] Loading 0: 64%|██████▍ | 233/363 [00:29<00:12, 10.68it/s] Loading 0: 65%|██████▌ | 236/363 [00:30<00:10, 11.84it/s] Loading 0: 66%|██████▌ | 238/363 [00:30<00:11, 11.13it/s] Loading 0: 66%|██████▌ | 240/363 [00:30<00:11, 11.16it/s] Loading 0: 67%|██████▋ | 244/363 [00:30<00:07, 15.27it/s] Loading 0: 68%|██████▊ | 248/363 [00:30<00:06, 18.92it/s] Loading 0: 69%|██████▉ | 251/363 [00:31<00:08, 13.89it/s] Loading 0: 70%|██████▉ | 253/363 [00:31<00:08, 13.27it/s] Loading 0: 70%|███████ | 255/363 [00:31<00:07, 14.08it/s] Loading 0: 71%|███████ | 257/363 [00:31<00:09, 11.44it/s] Loading 0: 72%|███████▏ | 262/363 [00:31<00:05, 17.24it/s] Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 20.53it/s] Loading 0: 74%|███████▍ | 269/363 [00:32<00:06, 14.68it/s] Loading 0: 75%|███████▍ | 271/363 [00:32<00:06, 13.86it/s] Loading 0: 75%|███████▌ | 273/363 [00:32<00:06, 14.65it/s] Loading 0: 76%|███████▌ | 275/363 [00:32<00:07, 11.79it/s] Loading 0: 77%|███████▋ | 280/363 [00:32<00:04, 17.85it/s] Loading 0: 78%|███████▊ | 284/363 [00:33<00:03, 21.13it/s] Loading 0: 79%|███████▉ | 287/363 [00:33<00:05, 15.10it/s] Loading 0: 80%|███████▉ | 290/363 [00:33<00:04, 15.61it/s] Loading 0: 80%|████████ | 292/363 [00:33<00:05, 13.83it/s] Loading 0: 81%|████████ | 294/363 [00:33<00:05, 13.16it/s] Loading 0: 82%|████████▏ | 298/363 [00:34<00:03, 17.48it/s] Loading 0: 83%|████████▎ | 302/363 [00:34<00:02, 20.93it/s] Loading 0: 84%|████████▍ | 305/363 [00:34<00:03, 14.58it/s] Loading 0: 85%|████████▍ | 307/363 [00:34<00:04, 13.79it/s] Loading 0: 85%|████████▌ | 309/363 [00:34<00:03, 14.56it/s] Loading 0: 86%|████████▌ | 311/363 [00:35<00:04, 11.88it/s] Loading 0: 87%|████████▋ | 316/363 [00:35<00:02, 17.82it/s] Loading 0: 88%|████████▊ | 320/363 [00:35<00:02, 21.29it/s] Loading 0: 89%|████████▉ | 323/363 [00:35<00:02, 15.13it/s] Loading 0: 90%|████████▉ | 326/363 [00:35<00:02, 15.68it/s] Loading 0: 90%|█████████ | 328/363 [00:36<00:02, 13.87it/s] Loading 0: 91%|█████████ | 330/363 [00:36<00:02, 13.30it/s] Loading 0: 92%|█████████▏| 334/363 [00:36<00:01, 17.41it/s] Loading 0: 93%|█████████▎| 338/363 [00:36<00:01, 21.00it/s] Loading 0: 94%|█████████▍| 341/363 [00:36<00:01, 14.88it/s] Loading 0: 94%|█████████▍| 343/363 [00:36<00:01, 14.01it/s] Loading 0: 95%|█████████▌| 345/363 [00:37<00:01, 14.83it/s] Loading 0: 96%|█████████▌| 347/363 [00:37<00:01, 12.01it/s] Loading 0: 97%|█████████▋| 352/363 [00:37<00:00, 18.52it/s] Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 22.48it/s] Loading 0: 99%|█████████▉| 359/363 [00:44<00:02, 1.47it/s] Loading 0: 99%|█████████▉| 361/363 [00:45<00:01, 1.75it/s]
Job rirv938-mistral-24b-grp-39559-v2-mkmlizer completed after 256.88s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-39559-v2-mkmlizer
Pipeline stage MKMLizer completed in 257.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-grp-39559-v2
Waiting for inference service rirv938-mistral-24b-grp-39559-v2 to be ready
Inference service rirv938-mistral-24b-grp-39559-v2 ready after 140.46811771392822s
Pipeline stage MKMLDeployer completed in 140.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.752701759338379s
Received healthy response to inference request in 2.2046656608581543s
Received healthy response to inference request in 1.8121185302734375s
Received healthy response to inference request in 2.072726011276245s
Received healthy response to inference request in 1.9602394104003906s
5 requests
0 failed requests
5th percentile: 1.841742706298828
10th percentile: 1.8713668823242187
20th percentile: 1.930615234375
30th percentile: 1.9827367305755614
40th percentile: 2.0277313709259035
50th percentile: 2.072726011276245
60th percentile: 2.125501871109009
70th percentile: 2.1782777309417725
80th percentile: 2.314272880554199
90th percentile: 2.533487319946289
95th percentile: 2.643094539642334
99th percentile: 2.73078031539917
mean time: 2.1604902744293213
Pipeline stage StressChecker completed in 12.14s
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 0.88s
Shutdown handler de-registered
rirv938-mistral-24b-grp_39559_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 2984.01s
Shutdown handler de-registered
rirv938-mistral-24b-grp_39559_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_39559_v2 status is now torndown due to DeploymentManager action