developer_uid: rirv938
submission_id: rirv938-original-96p-4f_90259_v1
model_name: rirv938-original-96p-4f_90259_v1
model_group: rirv938/original_96p_4ff
status: inactive
timestamp: 2025-03-31T20:48:54+00:00
num_battles: 7452
num_wins: 4258
celo_rating: 1335.48
family_friendly_score: 0.5147999999999999
family_friendly_standard_error: 0.007067969439662285
submission_type: basic
model_repo: rirv938/original_96p_4ff_rirv938_98p_2ff_rirv938_42155_v1_cp936_v3
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3905102064004194, 'latency_mean': 2.560684006214142, 'latency_p50': 2.538808226585388, 'latency_p90': 2.8593735456466676}, {'batch_size': 3, 'throughput': 0.7988458728920943, 'latency_mean': 3.7400894486904144, 'latency_p50': 3.7523415088653564, 'latency_p90': 4.150444912910461}, {'batch_size': 5, 'throughput': 1.0556951913710055, 'latency_mean': 4.716373012065888, 'latency_p50': 4.758758544921875, 'latency_p90': 5.249689364433289}, {'batch_size': 6, 'throughput': 1.1426525202135163, 'latency_mean': 5.212061855792999, 'latency_p50': 5.207188606262207, 'latency_p90': 5.891396474838257}, {'batch_size': 10, 'throughput': 1.3277691513244851, 'latency_mean': 7.470663529634476, 'latency_p50': 7.458192229270935, 'latency_p90': 8.532504439353943}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-original-96p-4f_90259_v1
is_internal_developer: True
language_model: rirv938/original_96p_4ff_rirv938_98p_2ff_rirv938_42155_v1_cp936_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.79
us_pacific_date: 2025-03-31
win_ratio: 0.5713902308105206
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, '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': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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-original-96p-4f-90259-v1-mkmlizer
Waiting for job on rirv938-original-96p-4f-90259-v1-mkmlizer to finish
rirv938-original-96p-4f-90259-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ _____ __ __ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ /___/ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ belonging to: ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ║ ║
rirv938-original-96p-4f-90259-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-original-96p-4f-90259-v1-mkmlizer: Downloaded to shared memory in 173.632s
rirv938-original-96p-4f-90259-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgw3t7vd1, device:0
rirv938-original-96p-4f-90259-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-original-96p-4f-90259-v1-mkmlizer: quantized model in 66.427s
rirv938-original-96p-4f-90259-v1-mkmlizer: Processed model rirv938/original_96p_4ff_rirv938_98p_2ff_rirv938_42155_v1_cp936_v3 in 240.060s
rirv938-original-96p-4f-90259-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-original-96p-4f-90259-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-original-96p-4f-90259-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1
rirv938-original-96p-4f-90259-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1/config.json
rirv938-original-96p-4f-90259-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1/special_tokens_map.json
rirv938-original-96p-4f-90259-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1/tokenizer_config.json
rirv938-original-96p-4f-90259-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1/tokenizer.json
rirv938-original-96p-4f-90259-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1/flywheel_model.1.safetensors
rirv938-original-96p-4f-90259-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-original-96p-4f-90259-v1/flywheel_model.0.safetensors
rirv938-original-96p-4f-90259-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 28.15it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:27, 12.81it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:18, 18.84it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:25, 13.49it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:31, 11.04it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:21, 15.77it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:22, 15.19it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:23, 14.26it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:17, 18.66it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.12it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:22, 14.88it/s] Loading 0: 10%|█ | 38/363 [00:02<00:21, 15.41it/s] Loading 0: 11%|█ | 40/363 [00:02<00:24, 13.43it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:24, 12.85it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 16.87it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:15, 20.73it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:21, 14.22it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:22, 13.44it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:21, 14.31it/s] Loading 0: 16%|█▋ | 59/363 [00:04<00:26, 11.50it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:17, 17.53it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:13, 21.40it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.98it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.45it/s] Loading 0: 21%|██ | 76/363 [00:05<00:21, 13.54it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:22, 12.86it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 16.88it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.41it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:19, 13.73it/s] Loading 0: 25%|██▌ | 91/363 [00:06<00:20, 12.99it/s] Loading 0: 26%|██▌ | 95/363 [00:06<00:15, 16.89it/s] Loading 0: 27%|██▋ | 99/363 [00:06<00:12, 20.42it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:14, 18.30it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:18, 13.69it/s] Loading 0: 29%|██▉ | 107/363 [00:07<00:20, 12.57it/s] Loading 0: 30%|███ | 109/363 [00:07<00:20, 12.14it/s] Loading 0: 31%|███ | 111/363 [00:07<00:19, 12.98it/s] Loading 0: 31%|███ | 113/363 [00:07<00:23, 10.48it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:15, 16.21it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:12, 19.59it/s] Loading 0: 34%|███▍ | 125/363 [00:08<00:17, 13.75it/s] Loading 0: 35%|███▍ | 127/363 [00:08<00:18, 12.95it/s] Loading 0: 36%|███▌ | 129/363 [00:08<00:17, 13.65it/s] Loading 0: 36%|███▌ | 131/363 [00:08<00:21, 10.82it/s] Loading 0: 37%|███▋ | 136/363 [00:09<00:13, 16.30it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:11, 19.50it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:16, 13.65it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:16, 12.92it/s] Loading 0: 40%|████ | 147/363 [00:09<00:15, 13.65it/s] Loading 0: 41%|████ | 149/363 [00:10<00:19, 11.10it/s] Loading 0: 42%|████▏ | 154/363 [00:10<00:12, 16.70it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:10, 20.10it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:14, 14.36it/s] Loading 0: 45%|████▍ | 163/363 [00:10<00:14, 13.48it/s] Loading 0: 45%|████▌ | 165/363 [00:11<00:14, 14.14it/s] Loading 0: 46%|████▌ | 167/363 [00:11<00:17, 11.32it/s] Loading 0: 47%|████▋ | 172/363 [00:11<00:11, 16.98it/s] Loading 0: 48%|████▊ | 176/363 [00:11<00:09, 20.38it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 14.42it/s] Loading 0: 50%|████▉ | 181/363 [00:12<00:13, 13.53it/s] Loading 0: 50%|█████ | 183/363 [00:12<00:12, 14.18it/s] Loading 0: 51%|█████ | 185/363 [00:12<00:15, 11.29it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:10, 16.97it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:08, 20.43it/s] Loading 0: 54%|█████▍ | 197/363 [00:13<00:11, 14.56it/s] Loading 0: 55%|█████▌ | 200/363 [00:13<00:10, 15.04it/s] Loading 0: 56%|█████▌ | 202/363 [00:28<04:32, 1.69s/it] Loading 0: 56%|█████▌ | 203/363 [00:29<03:59, 1.50s/it] Loading 0: 57%|█████▋ | 207/363 [00:29<02:15, 1.15it/s] Loading 0: 58%|█████▊ | 210/363 [00:29<01:33, 1.63it/s] Loading 0: 59%|█████▊ | 213/363 [00:29<01:07, 2.21it/s] Loading 0: 59%|█████▉ | 215/363 [00:29<00:55, 2.68it/s] Loading 0: 60%|█████▉ | 217/363 [00:30<00:44, 3.30it/s] Loading 0: 60%|██████ | 219/363 [00:30<00:34, 4.20it/s] Loading 0: 61%|██████ | 221/363 [00:30<00:29, 4.75it/s] Loading 0: 62%|██████▏ | 226/363 [00:30<00:16, 8.41it/s] Loading 0: 63%|██████▎ | 230/363 [00:30<00:11, 11.54it/s] Loading 0: 64%|██████▍ | 233/363 [00:31<00:12, 10.37it/s] Loading 0: 65%|██████▌ | 236/363 [00:31<00:10, 11.61it/s] Loading 0: 66%|██████▌ | 238/363 [00:31<00:11, 11.09it/s] Loading 0: 66%|██████▌ | 240/363 [00:31<00:11, 11.13it/s] Loading 0: 67%|██████▋ | 244/363 [00:31<00:07, 15.21it/s] Loading 0: 68%|██████▊ | 248/363 [00:31<00:06, 19.02it/s] Loading 0: 69%|██████▉ | 251/363 [00:32<00:08, 13.82it/s] Loading 0: 70%|██████▉ | 253/363 [00:32<00:08, 13.00it/s] Loading 0: 70%|███████ | 255/363 [00:32<00:07, 13.99it/s] Loading 0: 71%|███████ | 257/363 [00:32<00:09, 11.54it/s] Loading 0: 72%|███████▏ | 262/363 [00:32<00:05, 17.44it/s] Loading 0: 73%|███████▎ | 266/363 [00:33<00:04, 21.27it/s] Loading 0: 74%|███████▍ | 269/363 [00:33<00:06, 14.94it/s] Loading 0: 75%|███████▍ | 272/363 [00:33<00:05, 15.56it/s] Loading 0: 75%|███████▌ | 274/363 [00:33<00:06, 14.01it/s] Loading 0: 76%|███████▌ | 276/363 [00:33<00:06, 13.38it/s] Loading 0: 77%|███████▋ | 280/363 [00:34<00:04, 17.48it/s] Loading 0: 78%|███████▊ | 284/363 [00:34<00:03, 21.02it/s] Loading 0: 79%|███████▉ | 287/363 [00:34<00:05, 14.86it/s] Loading 0: 80%|███████▉ | 289/363 [00:34<00:05, 13.86it/s] Loading 0: 80%|████████ | 291/363 [00:34<00:04, 14.63it/s] Loading 0: 81%|████████ | 293/363 [00:35<00:06, 11.50it/s] Loading 0: 82%|████████▏ | 298/363 [00:35<00:03, 17.37it/s] Loading 0: 83%|████████▎ | 302/363 [00:35<00:02, 20.95it/s] Loading 0: 84%|████████▍ | 305/363 [00:35<00:03, 14.63it/s] Loading 0: 85%|████████▍ | 308/363 [00:35<00:03, 15.20it/s] Loading 0: 85%|████████▌ | 310/363 [00:36<00:03, 13.47it/s] Loading 0: 86%|████████▌ | 312/363 [00:36<00:03, 12.92it/s] Loading 0: 87%|████████▋ | 316/363 [00:36<00:02, 17.07it/s] Loading 0: 88%|████████▊ | 320/363 [00:36<00:02, 20.73it/s] Loading 0: 89%|████████▉ | 323/363 [00:36<00:02, 14.69it/s] Loading 0: 90%|████████▉ | 325/363 [00:37<00:02, 13.82it/s] Loading 0: 90%|█████████ | 327/363 [00:37<00:02, 14.36it/s] Loading 0: 91%|█████████ | 329/363 [00:37<00:02, 11.50it/s] Loading 0: 92%|█████████▏| 334/363 [00:37<00:01, 17.43it/s] Loading 0: 93%|█████████▎| 338/363 [00:37<00:01, 20.92it/s] Loading 0: 94%|█████████▍| 341/363 [00:38<00:01, 14.75it/s] Loading 0: 95%|█████████▍| 344/363 [00:38<00:01, 15.26it/s] Loading 0: 95%|█████████▌| 346/363 [00:38<00:01, 13.34it/s] Loading 0: 96%|█████████▌| 348/363 [00:38<00:01, 12.79it/s] Loading 0: 97%|█████████▋| 352/363 [00:38<00:00, 16.95it/s] Loading 0: 98%|█████████▊| 356/363 [00:38<00:00, 20.82it/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-original-96p-4f-90259-v1-mkmlizer completed after 268.63s with status: succeeded
Stopping job with name rirv938-original-96p-4f-90259-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.08s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.34s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-original-96p-4f-90259-v1
Waiting for inference service rirv938-original-96p-4f-90259-v1 to be ready
Inference service rirv938-original-96p-4f-90259-v1 ready after 120.44013667106628s
Pipeline stage MKMLDeployer completed in 120.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1627328395843506s
Received healthy response to inference request in 2.6916189193725586s
Received healthy response to inference request in 2.627507209777832s
Received healthy response to inference request in 2.5195302963256836s
Received healthy response to inference request in 7.621849298477173s
5 requests
0 failed requests
5th percentile: 2.541125679016113
10th percentile: 2.562721061706543
20th percentile: 2.6059118270874024
30th percentile: 2.6403295516967775
40th percentile: 2.665974235534668
50th percentile: 2.6916189193725586
60th percentile: 2.8800644874572754
70th percentile: 3.068510055541992
80th percentile: 4.054556131362916
90th percentile: 5.838202714920044
95th percentile: 6.7300260066986075
99th percentile: 7.44348464012146
mean time: 3.7246477127075197
Pipeline stage StressChecker completed in 19.88s
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 0.70s
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 0.66s
Shutdown handler de-registered
rirv938-original-96p-4f_90259_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 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-original-96p-4f-90259-v1-profiler
Waiting for inference service rirv938-original-96p-4f-90259-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5420.22s
Shutdown handler de-registered
rirv938-original-96p-4f_90259_v1 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1