developer_uid: rirv938
submission_id: rirv938-mistral-24b-bas_75050_v1
model_name: rirv938-mistral-24b-bas_75050_v1
model_group: rirv938/mistral_24b_base
status: torndown
timestamp: 2025-03-08T02:31:32+00:00
num_battles: 13206
num_wins: 6926
celo_rating: 1296.19
family_friendly_score: 0.5982000000000001
family_friendly_standard_error: 0.0069333507051064424
submission_type: basic
model_repo: rirv938/mistral_24b_base_2_dpo_40k_65w_pref_16w_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': 0.38807456017239533, 'latency_mean': 2.5767410612106323, 'latency_p50': 2.5872585773468018, 'latency_p90': 2.87187602519989}, {'batch_size': 3, 'throughput': 0.7998918458309078, 'latency_mean': 3.7446460223197935, 'latency_p50': 3.757636308670044, 'latency_p90': 4.126891875267029}, {'batch_size': 5, 'throughput': 1.0387746688796213, 'latency_mean': 4.780353182554245, 'latency_p50': 4.802917003631592, 'latency_p90': 5.278630065917969}, {'batch_size': 6, 'throughput': 1.1251082769489353, 'latency_mean': 5.3082474112510685, 'latency_p50': 5.311513662338257, 'latency_p90': 5.95469000339508}, {'batch_size': 10, 'throughput': 1.2783009380067822, 'latency_mean': 7.75801138162613, 'latency_p50': 7.770398259162903, 'latency_p90': 8.789356327056884}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-bas_75050_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_base_2_dpo_40k_65w_pref_16w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.79
us_pacific_date: 2025-03-07
win_ratio: 0.5244585794335908
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-bas-75050-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-bas-75050-v1-mkmlizer to finish
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ║ ║
rirv938-mistral-24b-bas-75050-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-bas-75050-v1-mkmlizer: Downloaded to shared memory in 158.939s
rirv938-mistral-24b-bas-75050-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb65guhjj, device:0
rirv938-mistral-24b-bas-75050-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-bas-75050-v1-mkmlizer: quantized model in 61.117s
rirv938-mistral-24b-bas-75050-v1-mkmlizer: Processed model rirv938/mistral_24b_base_2_dpo_40k_65w_pref_16w_swear_2500_v2 in 220.056s
rirv938-mistral-24b-bas-75050-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-bas-75050-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-bas-75050-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1
rirv938-mistral-24b-bas-75050-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1/config.json
rirv938-mistral-24b-bas-75050-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1/special_tokens_map.json
rirv938-mistral-24b-bas-75050-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1/tokenizer_config.json
rirv938-mistral-24b-bas-75050-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1/tokenizer.json
rirv938-mistral-24b-bas-75050-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-bas-75050-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-bas-75050-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-bas-75050-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:17, 20.32it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:20, 17.35it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:15, 22.20it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:25, 13.49it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:26, 13.20it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:20, 17.05it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:25, 13.51it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:17, 19.64it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 23.31it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:20, 16.15it/s] Loading 0: 10%|█ | 38/363 [00:02<00:19, 16.91it/s] Loading 0: 11%|█▏ | 41/363 [00:02<00:24, 13.32it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:16, 18.66it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:14, 22.33it/s] Loading 0: 15%|█▍ | 54/363 [00:03<00:21, 14.33it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:18, 16.25it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:20, 14.98it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:15, 18.69it/s] Loading 0: 19%|█▊ | 68/363 [00:03<00:13, 22.52it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:18, 16.15it/s] Loading 0: 20%|██ | 74/363 [00:04<00:17, 16.86it/s] Loading 0: 21%|██ | 77/363 [00:04<00:21, 13.14it/s] Loading 0: 23%|██▎ | 83/363 [00:04<00:14, 19.76it/s] Loading 0: 24%|██▍ | 87/363 [00:05<00:14, 18.73it/s] Loading 0: 25%|██▍ | 90/363 [00:05<00:18, 14.59it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:12, 20.83it/s] Loading 0: 28%|██▊ | 101/363 [00:05<00:11, 22.78it/s] Loading 0: 29%|██▊ | 104/363 [00:05<00:13, 19.07it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:17, 14.92it/s] Loading 0: 30%|███ | 109/363 [00:06<00:18, 14.10it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.80it/s] Loading 0: 31%|███ | 113/363 [00:06<00:20, 12.34it/s] Loading 0: 33%|███▎ | 118/363 [00:06<00:13, 18.50it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:10, 22.51it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.70it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 16.47it/s] Loading 0: 36%|███▌ | 131/363 [00:07<00:18, 12.88it/s] Loading 0: 38%|███▊ | 137/363 [00:08<00:11, 19.64it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:11, 18.79it/s] Loading 0: 40%|███▉ | 144/363 [00:08<00:15, 14.59it/s] Loading 0: 40%|████ | 147/363 [00:08<00:12, 16.71it/s] Loading 0: 41%|████▏ | 150/363 [00:08<00:14, 15.06it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:10, 20.48it/s] Loading 0: 44%|████▍ | 159/363 [00:09<00:10, 19.28it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:13, 14.76it/s] Loading 0: 45%|████▌ | 165/363 [00:09<00:11, 16.86it/s] Loading 0: 46%|████▋ | 168/363 [00:09<00:12, 15.28it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:09, 20.69it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:09, 19.59it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:12, 14.08it/s] Loading 0: 50%|█████ | 183/363 [00:10<00:11, 16.14it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:12, 14.56it/s] Loading 0: 53%|█████▎ | 191/363 [00:11<00:08, 19.93it/s] Loading 0: 54%|█████▎ | 195/363 [00:11<00:08, 18.89it/s] Loading 0: 55%|█████▍ | 198/363 [00:11<00:11, 14.50it/s] Loading 0: 55%|█████▌ | 201/363 [00:25<03:29, 1.29s/it] Loading 0: 56%|█████▌ | 203/363 [00:26<02:49, 1.06s/it] Loading 0: 57%|█████▋ | 207/363 [00:26<01:46, 1.46it/s] Loading 0: 58%|█████▊ | 210/363 [00:26<01:17, 1.99it/s] Loading 0: 59%|█████▊ | 213/363 [00:26<00:57, 2.61it/s] Loading 0: 59%|█████▉ | 215/363 [00:26<00:47, 3.11it/s] Loading 0: 60%|█████▉ | 217/363 [00:27<00:38, 3.77it/s] Loading 0: 60%|██████ | 219/363 [00:27<00:30, 4.72it/s] Loading 0: 61%|██████ | 221/363 [00:27<00:26, 5.32it/s] Loading 0: 63%|██████▎ | 227/363 [00:27<00:13, 10.20it/s] Loading 0: 64%|██████▎ | 231/363 [00:27<00:11, 11.82it/s] Loading 0: 64%|██████▍ | 234/363 [00:28<00:12, 10.69it/s] Loading 0: 65%|██████▌ | 237/363 [00:28<00:09, 12.90it/s] Loading 0: 66%|██████▌ | 240/363 [00:28<00:09, 12.75it/s] Loading 0: 67%|██████▋ | 245/363 [00:28<00:06, 17.92it/s] Loading 0: 69%|██████▊ | 249/363 [00:28<00:06, 17.95it/s] Loading 0: 69%|██████▉ | 252/363 [00:29<00:07, 14.03it/s] Loading 0: 70%|███████ | 255/363 [00:29<00:06, 16.25it/s] Loading 0: 71%|███████ | 258/363 [00:29<00:07, 14.91it/s] Loading 0: 72%|███████▏ | 263/363 [00:29<00:04, 20.52it/s] Loading 0: 74%|███████▎ | 267/363 [00:29<00:04, 19.71it/s] Loading 0: 74%|███████▍ | 270/363 [00:30<00:06, 14.80it/s] Loading 0: 75%|███████▌ | 273/363 [00:30<00:05, 16.96it/s] Loading 0: 76%|███████▌ | 276/363 [00:30<00:05, 15.23it/s] Loading 0: 77%|███████▋ | 281/363 [00:30<00:03, 20.65it/s] Loading 0: 79%|███████▊ | 285/363 [00:30<00:03, 19.84it/s] Loading 0: 79%|███████▉ | 288/363 [00:31<00:04, 15.00it/s] Loading 0: 80%|████████ | 291/363 [00:31<00:04, 17.18it/s] Loading 0: 81%|████████ | 294/363 [00:31<00:04, 15.36it/s] Loading 0: 82%|████████▏ | 299/363 [00:31<00:03, 20.93it/s] Loading 0: 83%|████████▎ | 303/363 [00:31<00:03, 19.56it/s] Loading 0: 84%|████████▍ | 306/363 [00:32<00:03, 14.67it/s] Loading 0: 85%|████████▌ | 309/363 [00:32<00:03, 16.74it/s] Loading 0: 86%|████████▌ | 312/363 [00:32<00:03, 14.92it/s] Loading 0: 87%|████████▋ | 317/363 [00:32<00:02, 20.31it/s] Loading 0: 88%|████████▊ | 321/363 [00:32<00:02, 19.28it/s] Loading 0: 89%|████████▉ | 324/363 [00:33<00:02, 14.58it/s] Loading 0: 90%|█████████ | 327/363 [00:33<00:02, 16.66it/s] Loading 0: 91%|█████████ | 330/363 [00:33<00:02, 14.99it/s] Loading 0: 92%|█████████▏| 334/363 [00:33<00:01, 19.05it/s] Loading 0: 93%|█████████▎| 339/363 [00:34<00:01, 19.55it/s] Loading 0: 94%|█████████▍| 342/363 [00:34<00:01, 14.94it/s] Loading 0: 95%|█████████▌| 345/363 [00:34<00:01, 16.91it/s] Loading 0: 96%|█████████▌| 348/363 [00:34<00:00, 15.24it/s] Loading 0: 97%|█████████▋| 353/363 [00:34<00:00, 20.63it/s] Loading 0: 98%|█████████▊| 357/363 [00:41<00:03, 1.74it/s] Loading 0: 99%|█████████▉| 360/363 [00:42<00:01, 2.24it/s] Loading 0: 100%|█████████▉| 362/363 [00:42<00:00, 2.64it/s]
Job rirv938-mistral-24b-bas-75050-v1-mkmlizer completed after 246.72s with status: succeeded
Stopping job with name rirv938-mistral-24b-bas-75050-v1-mkmlizer
Pipeline stage MKMLizer completed in 247.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-bas-75050-v1
Waiting for inference service rirv938-mistral-24b-bas-75050-v1 to be ready
Inference service rirv938-mistral-24b-bas-75050-v1 ready after 90.34636044502258s
Pipeline stage MKMLDeployer completed in 90.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0116961002349854s
Received healthy response to inference request in 2.6359145641326904s
Received healthy response to inference request in 2.762310743331909s
Received healthy response to inference request in 2.4481558799743652s
Received healthy response to inference request in 2.4053590297698975s
5 requests
0 failed requests
5th percentile: 2.413918399810791
10th percentile: 2.4224777698516844
20th percentile: 2.4395965099334718
30th percentile: 2.4857076168060304
40th percentile: 2.56081109046936
50th percentile: 2.6359145641326904
60th percentile: 2.686473035812378
70th percentile: 2.7370315074920653
80th percentile: 2.8121878147125243
90th percentile: 2.911941957473755
95th percentile: 2.96181902885437
99th percentile: 3.0017206859588623
mean time: 2.6526872634887697
Pipeline stage StressChecker completed in 14.47s
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 0.63s
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-mistral-24b-bas_75050_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5211.83s
Shutdown handler de-registered
rirv938-mistral-24b-bas_75050_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-bas_75050_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1