developer_uid: rirv938
submission_id: rirv938-mistral-24b-grp_42042_v1
model_name: rirv938-mistral-24b-grp_42042_v1
model_group: rirv938/mistral_24b_grpo
status: torndown
timestamp: 2025-04-29T17:19:54+00:00
num_battles: 6112
num_wins: 3231
celo_rating: 1327.43
family_friendly_score: 0.5552
family_friendly_standard_error: 0.007027844050631744
submission_type: basic
model_repo: rirv938/mistral_24b_grpo_40k_cp888_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': 0.5585945481577018, 'latency_mean': 1.790148628950119, 'latency_p50': 1.788651704788208, 'latency_p90': 1.9897201776504516}, {'batch_size': 4, 'throughput': 1.3695621753116378, 'latency_mean': 2.9117168974876404, 'latency_p50': 2.929626703262329, 'latency_p90': 3.214649486541748}, {'batch_size': 5, 'throughput': 1.5561149310302143, 'latency_mean': 3.2043900299072265, 'latency_p50': 3.2156916856765747, 'latency_p90': 3.52838020324707}, {'batch_size': 8, 'throughput': 1.886275627586414, 'latency_mean': 4.21451500415802, 'latency_p50': 4.211136698722839, 'latency_p90': 4.73323860168457}, {'batch_size': 10, 'throughput': 2.010384575710401, 'latency_mean': 4.92975685596466, 'latency_p50': 4.948309659957886, 'latency_p90': 5.458712911605835}, {'batch_size': 12, 'throughput': 2.085643958902207, 'latency_mean': 5.693359321355819, 'latency_p50': 5.686737775802612, 'latency_p90': 6.444723320007324}, {'batch_size': 15, 'throughput': 2.144786106931259, 'latency_mean': 6.878700680732727, 'latency_p50': 6.857690334320068, 'latency_p90': 7.874667239189148}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-mistral-24b-grp_42042_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_grpo_40k_cp888_95ff_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.75
us_pacific_date: 2025-04-29
win_ratio: 0.5286321989528796
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': ['</s>', '###', 'You:', '\n'], '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-42042-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-42042-v1-mkmlizer to finish
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-42042-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-42042-v1-mkmlizer: Downloaded to shared memory in 160.785s
rirv938-mistral-24b-grp-42042-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpys_7r9lo, device:0
rirv938-mistral-24b-grp-42042-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-42042-v1-mkmlizer: quantized model in 66.333s
rirv938-mistral-24b-grp-42042-v1-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp888_95ff_merged in 227.118s
rirv938-mistral-24b-grp-42042-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-42042-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-42042-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1
rirv938-mistral-24b-grp-42042-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1/config.json
rirv938-mistral-24b-grp-42042-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1/special_tokens_map.json
rirv938-mistral-24b-grp-42042-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1/tokenizer_config.json
rirv938-mistral-24b-grp-42042-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1/tokenizer.json
rirv938-mistral-24b-grp-42042-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-42042-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-42042-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-grp-42042-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 29.26it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:26, 13.43it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:17, 20.55it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:26, 13.41it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:31, 10.88it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:22, 15.61it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:23, 14.56it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:25, 13.50it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:19, 17.50it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:15, 20.71it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:23, 14.13it/s] Loading 0: 10%|█ | 37/363 [00:02<00:24, 13.44it/s] Loading 0: 11%|█ | 39/363 [00:02<00:22, 14.22it/s] Loading 0: 11%|█▏ | 41/363 [00:02<00:28, 11.25it/s] Loading 0: 13%|█▎ | 46/363 [00:03<00:18, 16.92it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:15, 20.12it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:22, 14.02it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:23, 13.30it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:21, 14.04it/s] Loading 0: 16%|█▋ | 59/363 [00:04<00:27, 11.26it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:17, 16.89it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 20.26it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:21, 13.82it/s] Loading 0: 20%|██ | 73/363 [00:04<00:22, 13.15it/s] Loading 0: 21%|██ | 75/363 [00:05<00:20, 13.97it/s] Loading 0: 21%|██ | 77/363 [00:05<00:25, 11.30it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 16.96it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.01it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:19, 14.09it/s] Loading 0: 25%|██▌ | 91/363 [00:06<00:20, 13.21it/s] Loading 0: 26%|██▌ | 95/363 [00:06<00:15, 16.79it/s] Loading 0: 27%|██▋ | 99/363 [00:06<00:13, 19.86it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:14, 17.98it/s] Loading 0: 29%|██▉ | 105/363 [00:07<00:19, 13.36it/s] Loading 0: 29%|██▉ | 107/363 [00:07<00:20, 12.49it/s] Loading 0: 30%|███ | 109/363 [00:07<00:20, 12.20it/s] Loading 0: 31%|███ | 111/363 [00:07<00:19, 13.19it/s] Loading 0: 31%|███ | 113/363 [00:07<00:23, 10.44it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:15, 16.15it/s] Loading 0: 34%|███▎ | 122/363 [00:08<00:12, 19.63it/s] Loading 0: 34%|███▍ | 125/363 [00:08<00:17, 13.96it/s] Loading 0: 35%|███▍ | 127/363 [00:08<00:17, 13.33it/s] Loading 0: 36%|███▌ | 129/363 [00:08<00:16, 14.09it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:20, 11.20it/s] Loading 0: 37%|███▋ | 136/363 [00:09<00:13, 16.86it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:11, 20.16it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:15, 14.12it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:16, 13.48it/s] Loading 0: 40%|████ | 147/363 [00:09<00:15, 14.29it/s] Loading 0: 41%|████ | 149/363 [00:10<00:19, 11.25it/s] Loading 0: 42%|████▏ | 154/363 [00:10<00:12, 16.98it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:10, 19.83it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:14, 14.05it/s] Loading 0: 45%|████▍ | 163/363 [00:11<00:15, 13.27it/s] Loading 0: 45%|████▌ | 165/363 [00:11<00:14, 14.00it/s] Loading 0: 46%|████▌ | 167/363 [00:11<00:17, 11.20it/s] Loading 0: 47%|████▋ | 172/363 [00:11<00:11, 16.75it/s] Loading 0: 48%|████▊ | 176/363 [00:11<00:09, 19.91it/s] Loading 0: 49%|████▉ | 179/363 [00:12<00:12, 14.22it/s] Loading 0: 50%|████▉ | 181/363 [00:12<00:13, 13.43it/s] Loading 0: 50%|█████ | 183/363 [00:12<00:12, 14.26it/s] Loading 0: 51%|█████ | 185/363 [00:12<00:15, 11.48it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:10, 17.11it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:08, 20.38it/s] Loading 0: 54%|█████▍ | 197/363 [00:13<00:11, 14.48it/s] Loading 0: 55%|█████▍ | 199/363 [00:13<00:11, 13.70it/s] Loading 0: 55%|█████▌ | 201/363 [00:28<04:48, 1.78s/it] Loading 0: 56%|█████▌ | 203/363 [00:28<03:41, 1.38s/it] Loading 0: 57%|█████▋ | 207/363 [00:29<02:08, 1.21it/s] Loading 0: 58%|█████▊ | 210/363 [00:29<01:29, 1.71it/s] Loading 0: 59%|█████▊ | 213/363 [00:29<01:06, 2.27it/s] Loading 0: 59%|█████▉ | 215/363 [00:29<00:54, 2.74it/s] Loading 0: 60%|█████▉ | 217/363 [00:29<00:43, 3.35it/s] Loading 0: 60%|██████ | 219/363 [00:30<00:33, 4.24it/s] Loading 0: 61%|██████ | 221/363 [00:30<00:29, 4.77it/s] Loading 0: 62%|██████▏ | 226/363 [00:30<00:16, 8.39it/s] Loading 0: 63%|██████▎ | 230/363 [00:30<00:11, 11.44it/s] Loading 0: 64%|██████▍ | 233/363 [00:30<00:12, 10.39it/s] Loading 0: 65%|██████▍ | 235/363 [00:31<00:12, 10.52it/s] Loading 0: 65%|██████▌ | 237/363 [00:31<00:10, 11.68it/s] Loading 0: 66%|██████▌ | 239/363 [00:31<00:12, 9.96it/s] Loading 0: 67%|██████▋ | 244/363 [00:31<00:07, 15.29it/s] Loading 0: 68%|██████▊ | 248/363 [00:31<00:06, 18.61it/s] Loading 0: 69%|██████▉ | 251/363 [00:32<00:08, 13.83it/s] Loading 0: 70%|██████▉ | 253/363 [00:32<00:08, 13.03it/s] Loading 0: 70%|███████ | 255/363 [00:32<00:07, 13.86it/s] Loading 0: 71%|███████ | 257/363 [00:32<00:09, 11.33it/s] Loading 0: 72%|███████▏ | 262/363 [00:32<00:05, 16.97it/s] Loading 0: 73%|███████▎ | 266/363 [00:32<00:04, 20.14it/s] Loading 0: 74%|███████▍ | 269/363 [00:33<00:06, 14.22it/s] Loading 0: 75%|███████▍ | 271/363 [00:33<00:06, 13.34it/s] Loading 0: 75%|███████▌ | 273/363 [00:33<00:06, 14.13it/s] Loading 0: 76%|███████▌ | 275/363 [00:33<00:07, 11.45it/s] Loading 0: 77%|███████▋ | 280/363 [00:34<00:04, 17.04it/s] Loading 0: 78%|███████▊ | 284/363 [00:34<00:03, 20.30it/s] Loading 0: 79%|███████▉ | 287/363 [00:34<00:05, 14.42it/s] Loading 0: 80%|███████▉ | 289/363 [00:34<00:05, 13.60it/s] Loading 0: 80%|████████ | 291/363 [00:34<00:05, 14.36it/s] Loading 0: 81%|████████ | 293/363 [00:35<00:06, 11.55it/s] Loading 0: 82%|████████▏ | 298/363 [00:35<00:03, 17.39it/s] Loading 0: 83%|████████▎ | 302/363 [00:35<00:02, 20.50it/s] Loading 0: 84%|████████▍ | 305/363 [00:35<00:03, 14.51it/s] Loading 0: 85%|████████▍ | 307/363 [00:35<00:04, 13.66it/s] Loading 0: 85%|████████▌ | 309/363 [00:36<00:03, 14.35it/s] Loading 0: 86%|████████▌ | 311/363 [00:36<00:04, 11.34it/s] Loading 0: 87%|████████▋ | 316/363 [00:36<00:02, 16.99it/s] Loading 0: 88%|████████▊ | 320/363 [00:36<00:02, 20.25it/s] Loading 0: 89%|████████▉ | 323/363 [00:36<00:02, 14.23it/s] Loading 0: 90%|████████▉ | 325/363 [00:37<00:02, 13.50it/s] Loading 0: 90%|█████████ | 327/363 [00:37<00:02, 14.34it/s] Loading 0: 91%|█████████ | 329/363 [00:37<00:03, 11.24it/s] Loading 0: 92%|█████████▏| 334/363 [00:37<00:01, 16.93it/s] Loading 0: 93%|█████████▎| 338/363 [00:37<00:01, 20.32it/s] Loading 0: 94%|█████████▍| 341/363 [00:38<00:01, 14.32it/s] Loading 0: 95%|█████████▍| 344/363 [00:38<00:01, 14.76it/s] Loading 0: 95%|█████████▌| 346/363 [00:38<00:01, 13.22it/s] Loading 0: 96%|█████████▌| 348/363 [00:38<00:01, 12.74it/s] Loading 0: 97%|█████████▋| 352/363 [00:38<00:00, 16.78it/s] Loading 0: 98%|█████████▊| 356/363 [00:38<00:00, 20.00it/s] Loading 0: 99%|█████████▉| 359/363 [00:46<00:02, 1.42it/s] Loading 0: 99%|█████████▉| 361/363 [00:46<00:01, 1.70it/s]
Job rirv938-mistral-24b-grp-42042-v1-mkmlizer completed after 258.73s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-42042-v1-mkmlizer
Pipeline stage MKMLizer completed in 259.21s
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-42042-v1
Waiting for inference service rirv938-mistral-24b-grp-42042-v1 to be ready
Inference service rirv938-mistral-24b-grp-42042-v1 ready after 140.50532054901123s
Pipeline stage MKMLDeployer completed in 141.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8290369510650635s
Received healthy response to inference request in 2.0002315044403076s
Received healthy response to inference request in 2.1345510482788086s
Received healthy response to inference request in 2.150435447692871s
Received healthy response to inference request in 2.556203842163086s
5 requests
0 failed requests
5th percentile: 2.027095413208008
10th percentile: 2.053959321975708
20th percentile: 2.1076871395111083
30th percentile: 2.1377279281616213
40th percentile: 2.144081687927246
50th percentile: 2.150435447692871
60th percentile: 2.312742805480957
70th percentile: 2.4750501632690427
80th percentile: 2.6107704639434814
90th percentile: 2.7199037075042725
95th percentile: 2.774470329284668
99th percentile: 2.818123626708984
mean time: 2.3340917587280274
Pipeline stage StressChecker completed in 13.30s
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 0.71s
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 0.68s
Shutdown handler de-registered
rirv938-mistral-24b-grp_42042_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-grp-42042-v1-profiler
Waiting for inference service rirv938-mistral-24b-grp-42042-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 2863.07s
Shutdown handler de-registered
rirv938-mistral-24b-grp_42042_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_42042_v1 status is now torndown due to DeploymentManager action