developer_uid: rirv938
submission_id: rirv938-mistral-24b-grp_67535_v1
model_name: rirv938-mistral-24b-grp_67535_v1
model_group: rirv938/mistral_24b_grpo
status: torndown
timestamp: 2025-05-15T15:56:48+00:00
num_battles: 5982
num_wins: 3034
celo_rating: 1296.01
family_friendly_score: 0.595
family_friendly_standard_error: 0.00694226187924368
submission_type: basic
model_repo: rirv938/mistral_24b_grpo_40k_cp888_92ff_ww_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': 0.5524320666500783, 'latency_mean': 1.810074062347412, 'latency_p50': 1.814723014831543, 'latency_p90': 2.033937621116638}, {'batch_size': 3, 'throughput': 1.16768444143564, 'latency_mean': 2.5606588387489317, 'latency_p50': 2.549596428871155, 'latency_p90': 2.809132623672485}, {'batch_size': 5, 'throughput': 1.5320153882458254, 'latency_mean': 3.2515930843353273, 'latency_p50': 3.22283399105072, 'latency_p90': 3.6754236698150633}, {'batch_size': 6, 'throughput': 1.6632856247122823, 'latency_mean': 3.587069389820099, 'latency_p50': 3.5854365825653076, 'latency_p90': 4.003976678848266}, {'batch_size': 8, 'throughput': 1.8427588099789265, 'latency_mean': 4.311741468906402, 'latency_p50': 4.315009951591492, 'latency_p90': 4.834504461288452}, {'batch_size': 10, 'throughput': 1.9555916349686056, 'latency_mean': 5.058131496906281, 'latency_p50': 5.034966468811035, 'latency_p90': 5.737210583686829}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-mistral-24b-grp_67535_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_grpo_40k_cp888_92ff_ww_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.71
us_pacific_date: 2025-05-15
win_ratio: 0.5071882313607489
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': ['\n', '###', '</s>', 'You:'], '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-67535-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-67535-v1-mkmlizer to finish
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-67535-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-67535-v1-mkmlizer: Downloaded to shared memory in 154.000s
rirv938-mistral-24b-grp-67535-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvkdb4eb3, device:0
rirv938-mistral-24b-grp-67535-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-67535-v1-mkmlizer: quantized model in 63.001s
rirv938-mistral-24b-grp-67535-v1-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp888_92ff_ww_merged in 217.002s
rirv938-mistral-24b-grp-67535-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-67535-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-67535-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-67535-v1
rirv938-mistral-24b-grp-67535-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-67535-v1/config.json
rirv938-mistral-24b-grp-67535-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-67535-v1/tokenizer.json
rirv938-mistral-24b-grp-67535-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-67535-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-67535-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 29.39it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:26, 13.54it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:16, 21.20it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:25, 13.51it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:26, 13.21it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:21, 16.32it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:21, 15.78it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:23, 14.43it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:17, 18.99it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.68it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:21, 15.22it/s] Loading 0: 10%|█ | 38/363 [00:02<00:20, 16.06it/s] Loading 0: 11%|█▏ | 41/363 [00:02<00:25, 12.52it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 17.50it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:15, 20.64it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:20, 15.12it/s] Loading 0: 15%|█▌ | 56/363 [00:03<00:19, 15.83it/s] Loading 0: 16%|█▋ | 59/363 [00:03<00:24, 12.44it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:17, 17.24it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 20.28it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.97it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.77it/s] Loading 0: 21%|██ | 77/363 [00:04<00:22, 12.58it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 17.43it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.39it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 14.94it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.51it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:13, 19.23it/s] Loading 0: 27%|██▋ | 99/363 [00:05<00:12, 20.71it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:13, 19.31it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:17, 14.79it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:18, 13.66it/s] Loading 0: 30%|███ | 109/363 [00:06<00:19, 13.18it/s] Loading 0: 31%|███ | 111/363 [00:06<00:18, 13.70it/s] Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.48it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 17.66it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.19it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.06it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 15.91it/s] Loading 0: 36%|███▌ | 130/363 [00:08<00:16, 14.27it/s] Loading 0: 36%|███▋ | 132/363 [00:08<00:17, 13.41it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:13, 17.40it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 20.74it/s] Loading 0: 39%|███▉ | 143/363 [00:08<00:15, 14.53it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:15, 14.04it/s] Loading 0: 40%|████ | 147/363 [00:09<00:14, 14.96it/s] Loading 0: 41%|████ | 149/363 [00:09<00:17, 12.07it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 17.93it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 21.19it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:13, 14.92it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 15.73it/s] Loading 0: 46%|████▌ | 166/363 [00:10<00:13, 14.14it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:14, 13.49it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:10, 17.37it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:09, 20.74it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 14.78it/s] Loading 0: 50%|████▉ | 181/363 [00:11<00:12, 14.16it/s] Loading 0: 50%|█████ | 183/363 [00:11<00:11, 15.05it/s] Loading 0: 51%|█████ | 185/363 [00:11<00:14, 12.21it/s] Loading 0: 52%|█████▏ | 190/363 [00:11<00:09, 18.20it/s] Loading 0: 53%|█████▎ | 194/363 [00:11<00:07, 21.62it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:10, 15.29it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 16.06it/s] Loading 0: 56%|█████▌ | 202/363 [00:26<04:11, 1.56s/it] Loading 0: 56%|█████▌ | 203/363 [00:27<03:42, 1.39s/it] Loading 0: 57%|█████▋ | 207/363 [00:27<02:05, 1.24it/s] Loading 0: 58%|█████▊ | 210/363 [00:27<01:26, 1.76it/s] Loading 0: 59%|█████▊ | 213/363 [00:27<01:02, 2.39it/s] Loading 0: 59%|█████▉ | 215/363 [00:27<00:50, 2.91it/s] Loading 0: 60%|█████▉ | 217/363 [00:27<00:40, 3.58it/s] Loading 0: 60%|██████ | 219/363 [00:28<00:31, 4.53it/s] Loading 0: 61%|██████ | 221/363 [00:28<00:27, 5.09it/s] Loading 0: 62%|██████▏ | 226/363 [00:28<00:15, 8.88it/s] Loading 0: 63%|██████▎ | 230/363 [00:28<00:11, 11.66it/s] Loading 0: 64%|██████▍ | 233/363 [00:28<00:12, 10.43it/s] Loading 0: 65%|██████▍ | 235/363 [00:29<00:12, 10.58it/s] Loading 0: 65%|██████▌ | 237/363 [00:29<00:10, 11.77it/s] Loading 0: 66%|██████▌ | 239/363 [00:29<00:12, 9.59it/s] Loading 0: 67%|██████▋ | 244/363 [00:29<00:07, 14.94it/s] Loading 0: 68%|██████▊ | 248/363 [00:29<00:06, 18.37it/s] Loading 0: 69%|██████▉ | 251/363 [00:30<00:08, 13.99it/s] Loading 0: 70%|██████▉ | 253/363 [00:30<00:08, 13.61it/s] Loading 0: 70%|███████ | 255/363 [00:30<00:07, 14.55it/s] Loading 0: 71%|███████ | 257/363 [00:30<00:08, 11.96it/s] Loading 0: 72%|███████▏ | 262/363 [00:30<00:05, 17.78it/s] Loading 0: 73%|███████▎ | 266/363 [00:30<00:04, 21.39it/s] Loading 0: 74%|███████▍ | 269/363 [00:31<00:06, 15.43it/s] Loading 0: 75%|███████▍ | 272/363 [00:31<00:05, 16.19it/s] Loading 0: 76%|███████▌ | 275/363 [00:31<00:06, 12.84it/s] Loading 0: 77%|███████▋ | 280/363 [00:31<00:04, 17.85it/s] Loading 0: 78%|███████▊ | 284/363 [00:32<00:03, 20.96it/s] Loading 0: 79%|███████▉ | 287/363 [00:32<00:04, 15.62it/s] Loading 0: 80%|███████▉ | 290/363 [00:32<00:04, 16.47it/s] Loading 0: 81%|████████ | 293/363 [00:32<00:05, 12.92it/s] Loading 0: 82%|████████▏ | 298/363 [00:33<00:03, 17.77it/s] Loading 0: 83%|████████▎ | 302/363 [00:33<00:02, 20.74it/s] Loading 0: 84%|████████▍ | 305/363 [00:33<00:03, 15.45it/s] Loading 0: 85%|████████▍ | 308/363 [00:33<00:03, 16.35it/s] Loading 0: 86%|████████▌ | 311/363 [00:34<00:04, 12.79it/s] Loading 0: 87%|████████▋ | 316/363 [00:34<00:02, 17.63it/s] Loading 0: 88%|████████▊ | 320/363 [00:34<00:02, 20.64it/s] Loading 0: 89%|████████▉ | 323/363 [00:34<00:02, 15.31it/s] Loading 0: 90%|████████▉ | 326/363 [00:34<00:02, 16.22it/s] Loading 0: 91%|█████████ | 329/363 [00:35<00:02, 12.86it/s] Loading 0: 92%|█████████▏| 334/363 [00:35<00:01, 17.64it/s] Loading 0: 93%|█████████▎| 338/363 [00:35<00:01, 20.55it/s] Loading 0: 94%|█████████▍| 341/363 [00:35<00:01, 15.35it/s] Loading 0: 95%|█████████▍| 344/363 [00:35<00:01, 16.08it/s] Loading 0: 96%|█████████▌| 347/363 [00:36<00:01, 12.58it/s] Loading 0: 97%|█████████▋| 352/363 [00:36<00:00, 17.12it/s] Loading 0: 98%|█████████▊| 356/363 [00:36<00:00, 19.67it/s] Loading 0: 99%|█████████▉| 359/363 [00:43<00:02, 1.59it/s] Loading 0: 99%|█████████▉| 361/363 [00:43<00:01, 1.88it/s]
Job rirv938-mistral-24b-grp-67535-v1-mkmlizer completed after 247.56s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-67535-v1-mkmlizer
Pipeline stage MKMLizer completed in 248.08s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-grp-67535-v1
Waiting for inference service rirv938-mistral-24b-grp-67535-v1 to be ready
Inference service rirv938-mistral-24b-grp-67535-v1 ready after 130.57293891906738s
Pipeline stage MKMLDeployer completed in 131.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5389788150787354s
Received healthy response to inference request in 2.243330478668213s
Received healthy response to inference request in 2.1590521335601807s
Received healthy response to inference request in 1.9856088161468506s
Received healthy response to inference request in 2.297039747238159s
5 requests
0 failed requests
5th percentile: 2.020297479629517
10th percentile: 2.0549861431121825
20th percentile: 2.1243634700775145
30th percentile: 2.1759078025817873
40th percentile: 2.209619140625
50th percentile: 2.243330478668213
60th percentile: 2.2648141860961912
70th percentile: 2.28629789352417
80th percentile: 2.3454275608062742
90th percentile: 2.442203187942505
95th percentile: 2.4905910015106203
99th percentile: 2.529301252365112
mean time: 2.2448019981384277
Pipeline stage StressChecker completed in 12.67s
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 0.74s
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 0.92s
Shutdown handler de-registered
rirv938-mistral-24b-grp_67535_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-grp-67535-v1-profiler
Waiting for inference service rirv938-mistral-24b-grp-67535-v1-profiler to be ready
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 3035.18s
Shutdown handler de-registered
rirv938-mistral-24b-grp_67535_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_67535_v1 status is now torndown due to DeploymentManager action