developer_uid: rirv938
submission_id: rirv938-mistral-24b-base_5319_v1
model_name: rirv938-mistral-24b-base_5319_v1
model_group: rirv938/mistral_24b_base
status: torndown
timestamp: 2025-03-07T02:06:14+00:00
num_battles: 10819
num_wins: 5713
celo_rating: 1298.79
family_friendly_score: 0.5418000000000001
family_friendly_standard_error: 0.007046314781501037
submission_type: basic
model_repo: rirv938/mistral_24b_base_2_dpo_40k_95w_pref_25w_swear_2500_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3853790081804874, 'latency_mean': 2.594785076379776, 'latency_p50': 2.598857283592224, 'latency_p90': 2.8747041702270506}, {'batch_size': 3, 'throughput': 0.7889934497287522, 'latency_mean': 3.787984173297882, 'latency_p50': 3.7821837663650513, 'latency_p90': 4.247061038017273}, {'batch_size': 5, 'throughput': 1.0327493269866057, 'latency_mean': 4.80115574836731, 'latency_p50': 4.8427228927612305, 'latency_p90': 5.350171852111816}, {'batch_size': 6, 'throughput': 1.1206808361375098, 'latency_mean': 5.3088847219944, 'latency_p50': 5.279218912124634, 'latency_p90': 5.98392071723938}, {'batch_size': 10, 'throughput': 1.282893284936363, 'latency_mean': 7.706728655099869, 'latency_p50': 7.699681401252747, 'latency_p90': 8.69133403301239}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-base_5319_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_base_2_dpo_40k_95w_pref_25w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.77
us_pacific_date: 2025-03-06
win_ratio: 0.528052500231075
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-mistral-24b-base-5319-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-base-5319-v1-mkmlizer to finish
rirv938-mistral-24b-base-5319-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ║ ║
rirv938-mistral-24b-base-5319-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-base-5319-v1-mkmlizer: Downloaded to shared memory in 166.507s
rirv938-mistral-24b-base-5319-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp12dt47tm, device:0
rirv938-mistral-24b-base-5319-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-base-5319-v1-mkmlizer: quantized model in 62.282s
rirv938-mistral-24b-base-5319-v1-mkmlizer: Processed model rirv938/mistral_24b_base_2_dpo_40k_95w_pref_25w_swear_2500_v2 in 228.789s
rirv938-mistral-24b-base-5319-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-base-5319-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-base-5319-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1
rirv938-mistral-24b-base-5319-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1/config.json
rirv938-mistral-24b-base-5319-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1/special_tokens_map.json
rirv938-mistral-24b-base-5319-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1/tokenizer_config.json
rirv938-mistral-24b-base-5319-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1/tokenizer.json
rirv938-mistral-24b-base-5319-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-base-5319-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-base-5319-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-base-5319-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:17, 21.11it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:20, 17.54it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:15, 22.03it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:25, 13.87it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:25, 13.52it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:19, 17.38it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:24, 13.90it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:15, 21.75it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:16, 19.97it/s] Loading 0: 10%|▉ | 36/363 [00:02<00:21, 15.04it/s] Loading 0: 11%|█ | 39/363 [00:02<00:18, 17.17it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:20, 15.44it/s] Loading 0: 13%|█▎ | 47/363 [00:02<00:15, 20.93it/s] Loading 0: 14%|█▍ | 51/363 [00:02<00:15, 19.64it/s] Loading 0: 15%|█▍ | 54/363 [00:03<00:21, 14.64it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:18, 16.64it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:20, 14.63it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:16, 18.39it/s] Loading 0: 19%|█▊ | 68/363 [00:03<00:13, 22.01it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:18, 15.51it/s] Loading 0: 20%|██ | 74/363 [00:04<00:17, 16.08it/s] Loading 0: 21%|██ | 77/363 [00:04<00:22, 12.55it/s] Loading 0: 23%|██▎ | 82/363 [00:04<00:15, 17.61it/s] Loading 0: 24%|██▎ | 86/363 [00:04<00:13, 20.98it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:17, 15.23it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.73it/s] Loading 0: 27%|██▋ | 97/363 [00:05<00:12, 20.65it/s] Loading 0: 28%|██▊ | 101/363 [00:05<00:12, 21.23it/s] Loading 0: 29%|██▊ | 104/363 [00:06<00:14, 17.78it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:18, 14.02it/s] Loading 0: 30%|███ | 109/363 [00:06<00:18, 13.74it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.36it/s] Loading 0: 31%|███ | 113/363 [00:06<00:20, 12.05it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 18.41it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:10, 22.40it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.71it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 16.32it/s] Loading 0: 36%|███▌ | 131/363 [00:07<00:18, 12.82it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 18.33it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:11, 19.14it/s] Loading 0: 40%|███▉ | 144/363 [00:08<00:14, 14.81it/s] Loading 0: 40%|████ | 147/363 [00:08<00:12, 16.81it/s] Loading 0: 41%|████▏ | 150/363 [00:09<00:13, 15.23it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:10, 20.55it/s] Loading 0: 44%|████▍ | 159/363 [00:09<00:10, 19.57it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:13, 14.88it/s] Loading 0: 45%|████▌ | 165/363 [00:09<00:11, 16.91it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:12, 15.23it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:09, 20.78it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:09, 19.74it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:12, 14.97it/s] Loading 0: 50%|█████ | 183/363 [00:10<00:10, 16.72it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:11, 15.01it/s] Loading 0: 52%|█████▏ | 190/363 [00:11<00:09, 18.67it/s] Loading 0: 53%|█████▎ | 194/363 [00:11<00:07, 22.11it/s] Loading 0: 54%|█████▍ | 197/363 [00:11<00:10, 16.04it/s] Loading 0: 55%|█████▌ | 200/363 [00:11<00:09, 16.73it/s] Loading 0: 56%|█████▌ | 203/363 [00:26<03:49, 1.44s/it] Loading 0: 57%|█████▋ | 207/363 [00:26<02:27, 1.06it/s] Loading 0: 58%|█████▊ | 210/363 [00:27<01:47, 1.43it/s] Loading 0: 59%|█████▊ | 213/363 [00:27<01:19, 1.89it/s] Loading 0: 60%|█████▉ | 216/363 [00:27<01:00, 2.43it/s] Loading 0: 60%|██████ | 219/363 [00:27<00:43, 3.30it/s] Loading 0: 61%|██████ | 222/363 [00:28<00:33, 4.16it/s] Loading 0: 62%|██████▏ | 226/363 [00:28<00:22, 6.12it/s] Loading 0: 64%|██████▎ | 231/363 [00:28<00:15, 8.45it/s] Loading 0: 64%|██████▍ | 234/363 [00:28<00:15, 8.48it/s] Loading 0: 65%|██████▌ | 237/363 [00:28<00:12, 10.40it/s] Loading 0: 66%|██████▌ | 240/363 [00:29<00:11, 10.79it/s] Loading 0: 67%|██████▋ | 244/363 [00:29<00:08, 14.21it/s] Loading 0: 68%|██████▊ | 248/363 [00:29<00:06, 17.93it/s] Loading 0: 69%|██████▉ | 251/363 [00:29<00:07, 14.20it/s] Loading 0: 70%|██████▉ | 254/363 [00:29<00:07, 15.34it/s] Loading 0: 71%|███████ | 257/363 [00:30<00:08, 12.43it/s] Loading 0: 72%|███████▏ | 263/363 [00:30<00:05, 18.98it/s] Loading 0: 74%|███████▎ | 267/363 [00:30<00:05, 18.65it/s] Loading 0: 74%|███████▍ | 270/363 [00:30<00:06, 14.53it/s] Loading 0: 75%|███████▌ | 273/363 [00:30<00:05, 16.51it/s] Loading 0: 76%|███████▌ | 276/363 [00:31<00:05, 14.92it/s] Loading 0: 77%|███████▋ | 281/363 [00:31<00:04, 20.31it/s] Loading 0: 79%|███████▊ | 285/363 [00:31<00:03, 19.64it/s] Loading 0: 79%|███████▉ | 288/363 [00:31<00:05, 14.99it/s] Loading 0: 80%|████████ | 291/363 [00:31<00:04, 17.06it/s] Loading 0: 81%|████████ | 294/363 [00:32<00:04, 15.60it/s] Loading 0: 82%|████████▏ | 299/363 [00:32<00:03, 21.20it/s] Loading 0: 83%|████████▎ | 303/363 [00:32<00:02, 20.04it/s] Loading 0: 84%|████████▍ | 306/363 [00:32<00:03, 14.95it/s] Loading 0: 85%|████████▌ | 309/363 [00:32<00:03, 17.07it/s] Loading 0: 86%|████████▌ | 312/363 [00:33<00:03, 15.64it/s] Loading 0: 87%|████████▋ | 317/363 [00:33<00:02, 21.16it/s] Loading 0: 88%|████████▊ | 321/363 [00:33<00:02, 19.86it/s] Loading 0: 89%|████████▉ | 324/363 [00:33<00:02, 14.93it/s] Loading 0: 90%|█████████ | 327/363 [00:34<00:02, 17.04it/s] Loading 0: 91%|█████████ | 330/363 [00:34<00:02, 15.52it/s] Loading 0: 92%|█████████▏| 335/363 [00:34<00:01, 20.99it/s] Loading 0: 93%|█████████▎| 339/363 [00:34<00:01, 19.89it/s] Loading 0: 94%|█████████▍| 342/363 [00:34<00:01, 14.89it/s] Loading 0: 95%|█████████▌| 345/363 [00:35<00:01, 16.90it/s] Loading 0: 96%|█████████▌| 348/363 [00:35<00:01, 14.92it/s] Loading 0: 97%|█████████▋| 352/363 [00:35<00:00, 18.89it/s] Loading 0: 98%|█████████▊| 356/363 [00:35<00:00, 22.59it/s] Loading 0: 99%|█████████▉| 359/363 [00:42<00:02, 1.56it/s] Loading 0: 100%|█████████▉| 362/363 [00:42<00:00, 2.04it/s]
Job rirv938-mistral-24b-base-5319-v1-mkmlizer completed after 256.7s with status: succeeded
Stopping job with name rirv938-mistral-24b-base-5319-v1-mkmlizer
Pipeline stage MKMLizer completed in 257.18s
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-base-5319-v1
Waiting for inference service rirv938-mistral-24b-base-5319-v1 to be ready
Inference service rirv938-mistral-24b-base-5319-v1 ready after 100.36657333374023s
Pipeline stage MKMLDeployer completed in 100.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1800453662872314s
Received healthy response to inference request in 2.4850573539733887s
Received healthy response to inference request in 2.646446943283081s
Received healthy response to inference request in 2.199324607849121s
Received healthy response to inference request in 2.4271533489227295s
5 requests
0 failed requests
5th percentile: 2.2448903560638427
10th percentile: 2.2904561042785643
20th percentile: 2.381587600708008
30th percentile: 2.4387341499328614
40th percentile: 2.461895751953125
50th percentile: 2.4850573539733887
60th percentile: 2.549613189697266
70th percentile: 2.6141690254211425
80th percentile: 2.7531666278839113
90th percentile: 2.9666059970855714
95th percentile: 3.073325681686401
99th percentile: 3.158701429367065
mean time: 2.58760552406311
Pipeline stage StressChecker completed in 14.26s
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 0.64s
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 0.71s
Shutdown handler de-registered
rirv938-mistral-24b-base_5319_v1 status is now deployed due to DeploymentManager action
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 2816.78s
Shutdown handler de-registered
rirv938-mistral-24b-base_5319_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-base_5319_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1