developer_uid: NischayDnk
submission_id: chaiml-nitral-dpos1-beta_5231_v3
model_name: chaiml-nitral-dpos1-beta_5231_v3
model_group: ChaiML/nitral-dpos1-beta
status: torndown
timestamp: 2025-07-09T22:54:17+00:00
num_battles: 7320
num_wins: 3921
celo_rating: 1312.96
family_friendly_score: 0.5167999999999999
family_friendly_standard_error: 0.00706707520831638
submission_type: basic
model_repo: ChaiML/nitral-dpos1-beta06-exp1-10kpref-1800-lowlr-2e-2-1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1800
max_output_tokens: 74
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4490135631957712, 'latency_mean': 2.22699192404747, 'latency_p50': 2.2259632349014282, 'latency_p90': 2.4012506008148193}, {'batch_size': 2, 'throughput': 0.6438612230613902, 'latency_mean': 3.1060486030578613, 'latency_p50': 3.1012232303619385, 'latency_p90': 3.3557344675064087}, {'batch_size': 3, 'throughput': 0.7479893449703338, 'latency_mean': 3.999581274986267, 'latency_p50': 4.0118221044540405, 'latency_p90': 4.321756649017334}, {'batch_size': 4, 'throughput': 0.8183215046938799, 'latency_mean': 4.8768510389328, 'latency_p50': 4.87317955493927, 'latency_p90': 5.298964262008667}, {'batch_size': 5, 'throughput': 0.8617161836488199, 'latency_mean': 5.78804347038269, 'latency_p50': 5.761058568954468, 'latency_p90': 6.372122025489807}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nitral-dpos1-beta_5231_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/nitral-dpos1-beta06-exp1-10kpref-1800-lowlr-2e-2-1
model_size: 13B
ranking_group: single
throughput_3p7s: 0.72
us_pacific_date: 2025-07-09
win_ratio: 0.535655737704918
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['</s>', '<|im_end|>', '<|im_start|>', '###', '\n'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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 chaiml-nitral-dpos1-beta-5231-v3-mkmlizer
Waiting for job on chaiml-nitral-dpos1-beta-5231-v3-mkmlizer to finish
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ Version: 0.29.15 ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ belonging to: ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ║ ║
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: Downloaded to shared memory in 44.035s
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: Checking if ChaiML/nitral-dpos1-beta06-exp1-10kpref-1800-lowlr-2e-2-1 already exists in ChaiML
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbsr7g53_, device:0
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: quantized model in 31.168s
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: Processed model ChaiML/nitral-dpos1-beta06-exp1-10kpref-1800-lowlr-2e-2-1 in 75.205s
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nitral-dpos1-beta-5231-v3/nvidia
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nitral-dpos1-beta-5231-v3/nvidia/tokenizer.json
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nitral-dpos1-beta-5231-v3/nvidia/flywheel_model.0.safetensors
chaiml-nitral-dpos1-beta-5231-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.64it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.90it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 42.83it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 40.97it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:07, 45.35it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:07, 44.34it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 44.04it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:07, 45.07it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:08, 36.78it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:07, 42.24it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 30.32it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 30.35it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 36.37it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 37.36it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 38.82it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 40.89it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 34.06it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 41.11it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 41.09it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 42.77it/s] Loading 0: 31%|███ | 113/363 [00:02<00:07, 35.71it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 35.58it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 41.61it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 40.78it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 40.56it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 42.12it/s] Loading 0: 40%|███▉ | 145/363 [00:03<00:08, 25.11it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 25.69it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 33.03it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 34.52it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 35.87it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:05, 38.35it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 32.79it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 39.58it/s] Loading 0: 52%|█████▏ | 188/363 [00:05<00:04, 39.87it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:04, 39.69it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:04, 40.97it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 33.97it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 40.70it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 40.83it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 41.65it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 25.73it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 28.03it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.06it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 36.47it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 37.66it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 39.85it/s] Loading 0: 71%|███████ | 257/363 [00:07<00:03, 32.97it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 39.19it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 39.95it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 40.46it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:02, 41.58it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 35.10it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 41.75it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 41.61it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 41.58it/s] Loading 0: 84%|████████▍ | 306/363 [00:08<00:02, 21.88it/s] Loading 0: 85%|████████▌ | 310/363 [00:08<00:02, 23.33it/s] Loading 0: 87%|████████▋ | 314/363 [00:08<00:01, 25.60it/s] Loading 0: 88%|████████▊ | 320/363 [00:08<00:01, 31.23it/s] Loading 0: 90%|████████▉ | 326/363 [00:09<00:01, 32.97it/s] Loading 0: 91%|█████████ | 330/363 [00:09<00:01, 32.76it/s] Loading 0: 93%|█████████▎| 337/363 [00:09<00:00, 40.29it/s] Loading 0: 94%|█████████▍| 342/363 [00:09<00:00, 40.23it/s] Loading 0: 96%|█████████▌| 347/363 [00:09<00:00, 41.03it/s] Loading 0: 97%|█████████▋| 352/363 [00:09<00:00, 42.86it/s] Loading 0: 98%|█████████▊| 357/363 [00:09<00:00, 35.93it/s]
Job chaiml-nitral-dpos1-beta-5231-v3-mkmlizer completed after 137.88s with status: succeeded
Stopping job with name chaiml-nitral-dpos1-beta-5231-v3-mkmlizer
Pipeline stage MKMLizer completed in 138.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nitral-dpos1-beta-5231-v3
Waiting for inference service chaiml-nitral-dpos1-beta-5231-v3 to be ready
Inference service chaiml-nitral-dpos1-beta-5231-v3 ready after 201.25465989112854s
Pipeline stage MKMLDeployer completed in 202.76s
run pipeline stage %s
Running pipeline stage StressChecker
('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Received unhealthy response to inference request!
Received healthy response to inference request in 2.783531427383423s
Received healthy response to inference request in 2.136356830596924s
Received healthy response to inference request in 2.5042662620544434s
Received healthy response to inference request in 2.140994071960449s
5 requests
1 failed requests
5th percentile: 0.7515686988830567
10th percentile: 1.0977657318115235
20th percentile: 1.7901597976684571
30th percentile: 2.137284278869629
40th percentile: 2.139139175415039
50th percentile: 2.140994071960449
60th percentile: 2.286302947998047
70th percentile: 2.4316118240356444
80th percentile: 2.560119295120239
90th percentile: 2.6718253612518312
95th percentile: 2.727678394317627
99th percentile: 2.7723608207702637
mean time: 1.9941040515899657
%s, retrying in %s seconds...
Received healthy response to inference request in 2.4425361156463623s
Received healthy response to inference request in 2.067023992538452s
Received healthy response to inference request in 2.6368937492370605s
Received healthy response to inference request in 2.3553295135498047s
Received healthy response to inference request in 1.7288684844970703s
5 requests
0 failed requests
5th percentile: 1.7964995861053468
10th percentile: 1.864130687713623
20th percentile: 1.9993928909301757
30th percentile: 2.1246850967407225
40th percentile: 2.2400073051452636
50th percentile: 2.3553295135498047
60th percentile: 2.390212154388428
70th percentile: 2.425094795227051
80th percentile: 2.481407642364502
90th percentile: 2.5591506958007812
95th percentile: 2.598022222518921
99th percentile: 2.6291194438934324
mean time: 2.24613037109375
Pipeline stage StressChecker completed in 30.14s
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 2.66s
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 1.99s
Shutdown handler de-registered
chaiml-nitral-dpos1-beta_5231_v3 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nitral-dpos1-beta-5231-v3-profiler
Waiting for inference service chaiml-nitral-dpos1-beta-5231-v3-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 6342.40s
Shutdown handler de-registered
chaiml-nitral-dpos1-beta_5231_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nitral-dpos1-beta_5231_v3 status is now torndown due to DeploymentManager action