developer_uid: rirv938
submission_id: rirv938-100p-0ff-rirv93_43678_v1
model_name: rirv938-100p-0ff-rirv93_43678_v1
model_group: rirv938/100p_0ff_rirv938
status: torndown
timestamp: 2025-04-18T22:40:54+00:00
num_battles: 6266
num_wins: 3220
celo_rating: 1298.43
family_friendly_score: 0.4778
family_friendly_standard_error: 0.007064094563353466
submission_type: basic
model_repo: rirv938/100p_0ff_rirv938_mistral_24b_oai_77698_v2_cp748_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': 0.36919210167650457, 'latency_mean': 2.708550922870636, 'latency_p50': 2.7052791118621826, 'latency_p90': 2.9803679704666135}, {'batch_size': 2, 'throughput': 0.5731607709051888, 'latency_mean': 3.4831779623031616, 'latency_p50': 3.471834182739258, 'latency_p90': 3.829288196563721}, {'batch_size': 3, 'throughput': 0.7252693200010389, 'latency_mean': 4.128477759361267, 'latency_p50': 4.140302300453186, 'latency_p90': 4.577710819244385}, {'batch_size': 4, 'throughput': 0.8495389627559845, 'latency_mean': 4.68381700515747, 'latency_p50': 4.647618770599365, 'latency_p90': 5.233551216125488}, {'batch_size': 5, 'throughput': 0.9367019655478206, 'latency_mean': 5.319039454460144, 'latency_p50': 5.234690189361572, 'latency_p90': 5.992461109161377}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-100p-0ff-rirv93_43678_v1
is_internal_developer: True
language_model: rirv938/100p_0ff_rirv938_mistral_24b_oai_77698_v2_cp748_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-04-18
win_ratio: 0.5138844557931694
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['You:', '###', '\n', '</s>'], '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 rirv938-100p-0ff-rirv93-43678-v1-mkmlizer
Waiting for job on rirv938-100p-0ff-rirv93-43678-v1-mkmlizer to finish
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ _____ __ __ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ /___/ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ belonging to: ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ║ ║
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: Downloaded to shared memory in 160.492s
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7gb8p7z_, device:0
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: quantized model in 76.675s
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: Processed model rirv938/100p_0ff_rirv938_mistral_24b_oai_77698_v2_cp748_merged in 237.169s
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1/config.json
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1/special_tokens_map.json
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1/tokenizer_config.json
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1/tokenizer.json
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1/flywheel_model.1.safetensors
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-43678-v1/flywheel_model.0.safetensors
rirv938-100p-0ff-rirv93-43678-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:14, 25.37it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:31, 11.32it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:22, 15.74it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:31, 11.05it/s] Loading 0: 4%|▍ | 14/363 [00:01<00:35, 9.94it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:36, 9.62it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:29, 11.76it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:27, 12.37it/s] Loading 0: 6%|▋ | 23/363 [00:02<00:37, 9.02it/s] Loading 0: 8%|▊ | 28/363 [00:02<00:24, 13.70it/s] Loading 0: 9%|▉ | 32/363 [00:02<00:20, 16.43it/s] Loading 0: 9%|▉ | 34/363 [00:02<00:27, 11.86it/s] Loading 0: 10%|▉ | 36/363 [00:03<00:34, 9.53it/s] Loading 0: 11%|█ | 39/363 [00:03<00:27, 11.73it/s] Loading 0: 11%|█▏ | 41/363 [00:03<00:33, 9.62it/s] Loading 0: 13%|█▎ | 46/363 [00:03<00:22, 14.05it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:18, 16.76it/s] Loading 0: 15%|█▍ | 53/363 [00:04<00:26, 11.57it/s] Loading 0: 15%|█▌ | 55/363 [00:04<00:27, 11.13it/s] Loading 0: 16%|█▌ | 57/363 [00:04<00:25, 11.86it/s] Loading 0: 16%|█▋ | 59/363 [00:05<00:30, 9.94it/s] Loading 0: 18%|█▊ | 64/363 [00:05<00:20, 14.92it/s] Loading 0: 19%|█▊ | 68/363 [00:05<00:16, 17.40it/s] Loading 0: 20%|█▉ | 71/363 [00:05<00:22, 12.96it/s] Loading 0: 20%|██ | 73/363 [00:05<00:23, 12.34it/s] Loading 0: 21%|██ | 75/363 [00:06<00:21, 13.20it/s] Loading 0: 21%|██ | 77/363 [00:06<00:26, 10.92it/s] Loading 0: 23%|██▎ | 82/363 [00:06<00:17, 16.11it/s] Loading 0: 24%|██▎ | 86/363 [00:06<00:14, 19.36it/s] Loading 0: 25%|██▍ | 89/363 [00:07<00:21, 12.96it/s] Loading 0: 25%|██▌ | 91/363 [00:07<00:22, 12.25it/s] Loading 0: 26%|██▌ | 95/363 [00:07<00:17, 15.49it/s] Loading 0: 27%|██▋ | 99/363 [00:07<00:14, 17.89it/s] Loading 0: 28%|██▊ | 102/363 [00:07<00:16, 15.88it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:18, 13.75it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:25, 10.16it/s] Loading 0: 30%|██▉ | 108/363 [00:08<00:29, 8.64it/s] Loading 0: 31%|███ | 111/363 [00:08<00:22, 10.97it/s] Loading 0: 31%|███ | 113/363 [00:09<00:27, 8.93it/s] Loading 0: 33%|███▎ | 118/363 [00:09<00:18, 13.55it/s] Loading 0: 34%|███▎ | 122/363 [00:09<00:14, 16.32it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:20, 11.68it/s] Loading 0: 35%|███▍ | 127/363 [00:10<00:21, 11.21it/s] Loading 0: 36%|███▌ | 129/363 [00:10<00:19, 12.16it/s] Loading 0: 36%|███▌ | 131/363 [00:10<00:23, 9.76it/s] Loading 0: 37%|███▋ | 136/363 [00:10<00:15, 14.70it/s] Loading 0: 39%|███▊ | 140/363 [00:10<00:12, 17.45it/s] Loading 0: 39%|███▉ | 143/363 [00:11<00:17, 12.28it/s] Loading 0: 40%|███▉ | 145/363 [00:11<00:18, 11.65it/s] Loading 0: 40%|████ | 147/363 [00:11<00:17, 12.33it/s] Loading 0: 41%|████ | 149/363 [00:12<00:22, 9.52it/s] Loading 0: 42%|████▏ | 154/363 [00:12<00:14, 14.38it/s] Loading 0: 44%|████▎ | 158/363 [00:12<00:11, 17.16it/s] Loading 0: 44%|████▍ | 161/363 [00:12<00:16, 12.40it/s] Loading 0: 45%|████▍ | 163/363 [00:12<00:16, 12.12it/s] Loading 0: 45%|████▌ | 165/363 [00:13<00:15, 13.14it/s] Loading 0: 46%|████▌ | 167/363 [00:13<00:17, 10.96it/s] Loading 0: 47%|████▋ | 172/363 [00:13<00:11, 16.63it/s] Loading 0: 48%|████▊ | 176/363 [00:13<00:09, 19.78it/s] Loading 0: 49%|████▉ | 179/363 [00:13<00:13, 13.74it/s] Loading 0: 50%|████▉ | 181/363 [00:14<00:13, 13.01it/s] Loading 0: 50%|█████ | 183/363 [00:14<00:13, 13.52it/s] Loading 0: 51%|█████ | 185/363 [00:14<00:17, 10.34it/s] Loading 0: 52%|█████▏ | 190/363 [00:14<00:11, 15.33it/s] Loading 0: 53%|█████▎ | 194/363 [00:14<00:09, 17.91it/s] Loading 0: 54%|█████▍ | 197/363 [00:15<00:13, 12.28it/s] Loading 0: 55%|█████▍ | 199/363 [00:15<00:14, 11.64it/s] Loading 0: 55%|█████▌ | 200/363 [00:33<00:14, 11.64it/s] Loading 0: 55%|█████▌ | 201/363 [00:33<05:33, 2.06s/it] Loading 0: 56%|█████▌ | 202/363 [00:33<04:48, 1.79s/it] Loading 0: 56%|█████▌ | 204/363 [00:33<03:31, 1.33s/it] Loading 0: 57%|█████▋ | 207/363 [00:33<02:10, 1.19it/s] Loading 0: 58%|█████▊ | 209/363 [00:33<01:37, 1.58it/s] Loading 0: 58%|█████▊ | 212/363 [00:33<01:03, 2.37it/s] Loading 0: 59%|█████▉ | 214/363 [00:34<00:52, 2.82it/s] Loading 0: 60%|█████▉ | 216/363 [00:34<00:44, 3.28it/s] Loading 0: 60%|██████ | 219/363 [00:34<00:30, 4.75it/s] Loading 0: 61%|██████ | 221/363 [00:35<00:27, 5.11it/s] Loading 0: 62%|██████▏ | 226/363 [00:35<00:15, 8.71it/s] Loading 0: 63%|██████▎ | 230/363 [00:35<00:11, 11.58it/s] Loading 0: 64%|██████▍ | 233/363 [00:35<00:12, 10.04it/s] Loading 0: 65%|██████▍ | 235/363 [00:36<00:13, 9.63it/s] Loading 0: 65%|██████▌ | 237/363 [00:36<00:12, 10.46it/s] Loading 0: 66%|██████▌ | 239/363 [00:36<00:13, 9.02it/s] Loading 0: 67%|██████▋ | 244/363 [00:36<00:08, 13.96it/s] Loading 0: 68%|██████▊ | 248/363 [00:36<00:06, 17.09it/s] Loading 0: 69%|██████▉ | 251/363 [00:37<00:09, 12.27it/s] Loading 0: 70%|██████▉ | 253/363 [00:37<00:09, 11.70it/s] Loading 0: 70%|███████ | 255/363 [00:37<00:08, 12.49it/s] Loading 0: 71%|███████ | 257/363 [00:37<00:10, 10.22it/s] Loading 0: 72%|███████▏ | 262/363 [00:37<00:06, 14.98it/s] Loading 0: 73%|███████▎ | 266/363 [00:38<00:05, 17.34it/s] Loading 0: 74%|███████▍ | 269/363 [00:38<00:07, 12.22it/s] Loading 0: 75%|███████▍ | 271/363 [00:38<00:07, 11.60it/s] Loading 0: 75%|███████▌ | 273/363 [00:38<00:07, 12.14it/s] Loading 0: 76%|███████▌ | 275/363 [00:39<00:09, 9.54it/s] Loading 0: 77%|███████▋ | 280/363 [00:39<00:05, 13.98it/s] Loading 0: 78%|███████▊ | 284/363 [00:39<00:04, 16.64it/s] Loading 0: 79%|███████▉ | 286/363 [00:39<00:06, 12.26it/s] Loading 0: 79%|███████▉ | 288/363 [00:40<00:07, 9.64it/s] Loading 0: 80%|████████ | 291/363 [00:40<00:06, 11.69it/s] Loading 0: 81%|████████ | 293/363 [00:40<00:07, 9.53it/s] Loading 0: 82%|████████▏ | 298/363 [00:40<00:04, 14.16it/s] Loading 0: 83%|████████▎ | 302/363 [00:41<00:03, 16.61it/s] Loading 0: 84%|████████▍ | 305/363 [00:41<00:05, 11.28it/s] Loading 0: 85%|████████▍ | 307/363 [00:41<00:05, 11.12it/s] Loading 0: 85%|████████▌ | 309/363 [00:41<00:04, 11.94it/s] Loading 0: 86%|████████▌ | 311/363 [00:42<00:05, 9.88it/s] Loading 0: 87%|████████▋ | 316/363 [00:42<00:03, 14.85it/s] Loading 0: 88%|████████▊ | 320/363 [00:42<00:02, 17.84it/s] Loading 0: 89%|████████▉ | 323/363 [00:42<00:03, 12.96it/s] Loading 0: 90%|████████▉ | 325/363 [00:43<00:03, 12.49it/s] Loading 0: 90%|█████████ | 327/363 [00:43<00:02, 13.26it/s] Loading 0: 91%|█████████ | 329/363 [00:43<00:03, 10.03it/s] Loading 0: 92%|█████████▏| 334/363 [00:43<00:01, 14.76it/s] Loading 0: 93%|█████████▎| 338/363 [00:43<00:01, 16.61it/s] Loading 0: 94%|█████████▎| 340/363 [00:44<00:01, 11.93it/s] Loading 0: 94%|█████████▍| 342/363 [00:44<00:02, 10.00it/s] Loading 0: 95%|█████████▌| 345/363 [00:44<00:01, 12.34it/s] Loading 0: 96%|█████████▌| 347/363 [00:44<00:01, 10.44it/s] Loading 0: 97%|█████████▋| 352/363 [00:45<00:00, 15.80it/s] Loading 0: 98%|█████████▊| 356/363 [00:45<00:00, 18.90it/s] Loading 0: 99%|█████████▉| 359/363 [00:53<00:03, 1.30it/s] Loading 0: 99%|█████████▉| 361/363 [00:53<00:01, 1.54it/s]
Job rirv938-100p-0ff-rirv93-43678-v1-mkmlizer completed after 484.38s with status: succeeded
Stopping job with name rirv938-100p-0ff-rirv93-43678-v1-mkmlizer
Pipeline stage MKMLizer completed in 484.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-100p-0ff-rirv93-43678-v1
Waiting for inference service rirv938-100p-0ff-rirv93-43678-v1 to be ready
Inference service rirv938-100p-0ff-rirv93-43678-v1 ready after 130.505553483963s
Pipeline stage MKMLDeployer completed in 131.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2525837421417236s
Received healthy response to inference request in 2.608013391494751s
Received healthy response to inference request in 2.740176200866699s
Received healthy response to inference request in 2.6467607021331787s
Received healthy response to inference request in 2.438392400741577s
5 requests
0 failed requests
5th percentile: 2.2897454738616942
10th percentile: 2.326907205581665
20th percentile: 2.4012306690216065
30th percentile: 2.472316598892212
40th percentile: 2.5401649951934813
50th percentile: 2.608013391494751
60th percentile: 2.623512315750122
70th percentile: 2.6390112400054933
80th percentile: 2.6654438018798827
90th percentile: 2.702810001373291
95th percentile: 2.721493101119995
99th percentile: 2.7364395809173585
mean time: 2.537185287475586
Pipeline stage StressChecker completed in 14.06s
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 0.73s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_43678_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 0.13s
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 rirv938-100p-0ff-rirv93-43678-v1-profiler
Waiting for inference service rirv938-100p-0ff-rirv93-43678-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 2972.35s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_43678_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-100p-0ff-rirv93_43678_v1 status is now torndown due to DeploymentManager action