developer_uid: rirv938
submission_id: rirv938-mistral-24b-rou_91022_v1
model_name: rirv938-mistral-24b-rou_91022_v1
model_group: rirv938/mistral_24b_roun
status: torndown
timestamp: 2025-03-07T06:02:18+00:00
num_battles: 11624
num_wins: 6098
celo_rating: 1302.87
family_friendly_score: 0.5436000000000001
family_friendly_standard_error: 0.007044132877792696
submission_type: basic
model_repo: rirv938/mistral_24b_round_2_dpo_40k_85w_pref_20w_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': 0.38816988298374006, 'latency_mean': 2.5761041045188904, 'latency_p50': 2.573341131210327, 'latency_p90': 2.8480101346969606}, {'batch_size': 3, 'throughput': 0.7958748043504767, 'latency_mean': 3.755689650774002, 'latency_p50': 3.7131587266921997, 'latency_p90': 4.161172866821289}, {'batch_size': 5, 'throughput': 1.0338392559256235, 'latency_mean': 4.820035419464111, 'latency_p50': 4.810384273529053, 'latency_p90': 5.390421462059021}, {'batch_size': 6, 'throughput': 1.1038275397265982, 'latency_mean': 5.390008786916733, 'latency_p50': 5.407987475395203, 'latency_p90': 6.003326153755188}, {'batch_size': 10, 'throughput': 1.2782886212798732, 'latency_mean': 7.746423470973968, 'latency_p50': 7.7511807680130005, 'latency_p90': 8.770734405517578}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-rou_91022_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_round_2_dpo_40k_85w_pref_20w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.79
us_pacific_date: 2025-03-06
win_ratio: 0.5246042670337233
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-rou-91022-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-rou-91022-v1-mkmlizer to finish
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-rou-91022-v1-mkmlizer: Downloaded to shared memory in 154.082s
rirv938-mistral-24b-rou-91022-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpef_65l4s, device:0
rirv938-mistral-24b-rou-91022-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-rou-91022-v1-mkmlizer: quantized model in 61.205s
rirv938-mistral-24b-rou-91022-v1-mkmlizer: Processed model rirv938/mistral_24b_round_2_dpo_40k_85w_pref_20w_swear_2500_v2 in 215.288s
rirv938-mistral-24b-rou-91022-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-rou-91022-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-rou-91022-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1
rirv938-mistral-24b-rou-91022-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1/config.json
rirv938-mistral-24b-rou-91022-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1/special_tokens_map.json
rirv938-mistral-24b-rou-91022-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1/tokenizer_config.json
rirv938-mistral-24b-rou-91022-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1/tokenizer.json
rirv938-mistral-24b-rou-91022-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-rou-91022-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-rou-91022-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:17, 21.02it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:19, 18.12it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:15, 23.33it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:23, 14.59it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:24, 14.07it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:19, 17.90it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:24, 14.04it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:15, 21.73it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:16, 20.11it/s] Loading 0: 10%|▉ | 36/363 [00:02<00:21, 14.92it/s] Loading 0: 11%|█ | 39/363 [00:02<00:19, 17.00it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:20, 15.52it/s] Loading 0: 13%|█▎ | 47/363 [00:02<00:15, 20.97it/s] Loading 0: 14%|█▍ | 51/363 [00:02<00:15, 19.69it/s] Loading 0: 15%|█▍ | 54/363 [00:03<00:20, 14.82it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:18, 16.96it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:20, 15.04it/s] Loading 0: 18%|█▊ | 65/363 [00:03<00:14, 20.44it/s] Loading 0: 19%|█▊ | 68/363 [00:03<00:13, 21.70it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.86it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.61it/s] Loading 0: 21%|██ | 77/363 [00:04<00:22, 12.46it/s] Loading 0: 23%|██▎ | 82/363 [00:04<00:15, 17.74it/s] Loading 0: 24%|██▎ | 86/363 [00:04<00:13, 21.27it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:17, 15.71it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:16, 16.03it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:13, 19.85it/s] Loading 0: 28%|██▊ | 101/363 [00:05<00:12, 21.71it/s] Loading 0: 29%|██▊ | 104/363 [00:05<00:14, 18.37it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:17, 14.47it/s] Loading 0: 30%|███ | 109/363 [00:06<00:18, 13.69it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.39it/s] Loading 0: 31%|███ | 113/363 [00:06<00:20, 12.03it/s] Loading 0: 33%|███▎ | 119/363 [00:06<00:12, 20.05it/s] Loading 0: 34%|███▍ | 123/363 [00:07<00:12, 19.20it/s] Loading 0: 35%|███▍ | 126/363 [00:07<00:16, 14.54it/s] Loading 0: 36%|███▌ | 129/363 [00:07<00:13, 16.77it/s] Loading 0: 36%|███▋ | 132/363 [00:07<00:15, 14.67it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 18.35it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:11, 18.98it/s] Loading 0: 40%|███▉ | 144/363 [00:08<00:15, 14.43it/s] Loading 0: 40%|████ | 147/363 [00:08<00:13, 16.43it/s] Loading 0: 41%|████▏ | 150/363 [00:08<00:14, 15.07it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:10, 20.55it/s] Loading 0: 44%|████▍ | 159/363 [00:09<00:10, 19.42it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:13, 14.70it/s] Loading 0: 45%|████▌ | 165/363 [00:09<00:11, 16.81it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:12, 15.18it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:09, 20.56it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:09, 19.64it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:12, 14.84it/s] Loading 0: 50%|█████ | 183/363 [00:10<00:10, 16.92it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:11, 15.27it/s] Loading 0: 53%|█████▎ | 191/363 [00:11<00:08, 20.86it/s] Loading 0: 54%|█████▎ | 195/363 [00:11<00:08, 19.44it/s] Loading 0: 55%|█████▍ | 198/363 [00:11<00:11, 14.73it/s] Loading 0: 55%|█████▌ | 201/363 [00:25<03:29, 1.29s/it] Loading 0: 56%|█████▌ | 203/363 [00:26<02:50, 1.06s/it] Loading 0: 57%|█████▋ | 207/363 [00:26<01:46, 1.46it/s] Loading 0: 58%|█████▊ | 210/363 [00:26<01:17, 1.98it/s] Loading 0: 59%|█████▊ | 213/363 [00:26<00:57, 2.59it/s] Loading 0: 59%|█████▉ | 215/363 [00:26<00:47, 3.09it/s] Loading 0: 60%|█████▉ | 217/363 [00:27<00:38, 3.76it/s] Loading 0: 60%|██████ | 219/363 [00:27<00:30, 4.70it/s] Loading 0: 61%|██████ | 221/363 [00:27<00:26, 5.27it/s] Loading 0: 62%|██████▏ | 226/363 [00:27<00:14, 9.28it/s] Loading 0: 63%|██████▎ | 230/363 [00:27<00:10, 12.65it/s] Loading 0: 64%|██████▍ | 233/363 [00:27<00:11, 11.34it/s] Loading 0: 65%|██████▌ | 236/363 [00:28<00:10, 12.67it/s] Loading 0: 66%|██████▌ | 239/363 [00:28<00:11, 11.02it/s] Loading 0: 67%|██████▋ | 244/363 [00:28<00:07, 15.80it/s] Loading 0: 69%|██████▊ | 249/363 [00:28<00:06, 17.34it/s] Loading 0: 69%|██████▉ | 252/363 [00:29<00:07, 14.01it/s] Loading 0: 70%|███████ | 255/363 [00:29<00:06, 16.10it/s] Loading 0: 71%|███████ | 258/363 [00:29<00:07, 14.61it/s] Loading 0: 72%|███████▏ | 262/363 [00:29<00:05, 18.48it/s] Loading 0: 74%|███████▎ | 267/363 [00:29<00:04, 19.53it/s] Loading 0: 74%|███████▍ | 270/363 [00:30<00:06, 14.94it/s] Loading 0: 75%|███████▌ | 273/363 [00:30<00:05, 16.98it/s] Loading 0: 76%|███████▌ | 276/363 [00:30<00:05, 15.56it/s] Loading 0: 77%|███████▋ | 281/363 [00:30<00:03, 21.12it/s] Loading 0: 79%|███████▊ | 285/363 [00:30<00:03, 19.78it/s] Loading 0: 79%|███████▉ | 288/363 [00:31<00:05, 14.87it/s] Loading 0: 80%|████████ | 291/363 [00:31<00:04, 16.92it/s] Loading 0: 81%|████████ | 294/363 [00:31<00:04, 15.18it/s] Loading 0: 82%|████████▏ | 299/363 [00:31<00:03, 20.73it/s] Loading 0: 83%|████████▎ | 303/363 [00:31<00:03, 19.67it/s] Loading 0: 84%|████████▍ | 306/363 [00:32<00:03, 14.85it/s] Loading 0: 85%|████████▌ | 309/363 [00:32<00:03, 16.81it/s] Loading 0: 86%|████████▌ | 312/363 [00:32<00:03, 15.43it/s] Loading 0: 87%|████████▋ | 316/363 [00:32<00:02, 19.50it/s] Loading 0: 88%|████████▊ | 321/363 [00:33<00:02, 19.94it/s] Loading 0: 89%|████████▉ | 324/363 [00:33<00:02, 15.01it/s] Loading 0: 90%|█████████ | 327/363 [00:33<00:02, 17.07it/s] Loading 0: 91%|█████████ | 330/363 [00:33<00:02, 15.41it/s] Loading 0: 92%|█████████▏| 335/363 [00:33<00:01, 20.78it/s] Loading 0: 93%|█████████▎| 339/363 [00:34<00:01, 19.51it/s] Loading 0: 94%|█████████▍| 342/363 [00:34<00:01, 14.87it/s] Loading 0: 95%|█████████▌| 345/363 [00:34<00:01, 16.97it/s] Loading 0: 96%|█████████▌| 348/363 [00:34<00:00, 15.01it/s] Loading 0: 97%|█████████▋| 353/363 [00:34<00:00, 20.63it/s] Loading 0: 98%|█████████▊| 357/363 [00:41<00:03, 1.73it/s] Loading 0: 99%|█████████▉| 360/363 [00:42<00:01, 2.23it/s] Loading 0: 100%|█████████▉| 362/363 [00:42<00:00, 2.65it/s]
Job rirv938-mistral-24b-rou-91022-v1-mkmlizer completed after 246.11s with status: succeeded
Stopping job with name rirv938-mistral-24b-rou-91022-v1-mkmlizer
Pipeline stage MKMLizer completed in 246.58s
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-rou-91022-v1
Waiting for inference service rirv938-mistral-24b-rou-91022-v1 to be ready
Inference service rirv938-mistral-24b-rou-91022-v1 ready after 100.44481325149536s
Pipeline stage MKMLDeployer completed in 101.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.151977777481079s
Received healthy response to inference request in 2.5547142028808594s
Received healthy response to inference request in 2.6373088359832764s
Received healthy response to inference request in 2.4665911197662354s
Received healthy response to inference request in 2.6106879711151123s
5 requests
0 failed requests
5th percentile: 2.48421573638916
10th percentile: 2.501840353012085
20th percentile: 2.5370895862579346
30th percentile: 2.56590895652771
40th percentile: 2.588298463821411
50th percentile: 2.6106879711151123
60th percentile: 2.621336317062378
70th percentile: 2.6319846630096437
80th percentile: 2.740242624282837
90th percentile: 2.946110200881958
95th percentile: 3.0490439891815186
99th percentile: 3.131391019821167
mean time: 2.6842559814453124
Pipeline stage StressChecker completed in 14.85s
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 0.72s
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 0.84s
Shutdown handler de-registered
rirv938-mistral-24b-rou_91022_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 2709.70s
Shutdown handler de-registered
rirv938-mistral-24b-rou_91022_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-rou_91022_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1