chaiml-nitral12b-dpos1-_95096

developer_uid: NischayDnk

submission_id: chaiml-nitral12b-dpos1-_95096_v5

model_name: chaiml-nitral12b-dpos1-_95096_v5

model_group: ChaiML/nitral12b-dpos1-b

status: torndown

timestamp: 2025-06-23T06:16:33+00:00

num_battles: 8953

num_wins: 4358

celo_rating: 1281.92

family_friendly_score: 0.5454

family_friendly_standard_error: 0.007041858277471934

submission_type: basic

model_repo: ChaiML/nitral12b-dpos1-b06-pref10k

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6051160176921628, 'latency_mean': 1.652454388141632, 'latency_p50': 1.6523826122283936, 'latency_p90': 1.817934274673462}, {'batch_size': 3, 'throughput': 1.0864914369950458, 'latency_mean': 2.752654321193695, 'latency_p50': 2.760000705718994, 'latency_p90': 3.0428515195846555}, {'batch_size': 5, 'throughput': 1.3035452766135713, 'latency_mean': 3.825468808412552, 'latency_p50': 3.829261898994446, 'latency_p90': 4.224722766876221}, {'batch_size': 6, 'throughput': 1.3713452560283834, 'latency_mean': 4.35308585524559, 'latency_p50': 4.346091985702515, 'latency_p90': 4.913851857185364}, {'batch_size': 8, 'throughput': 1.4279378179718776, 'latency_mean': 5.5571911895275115, 'latency_p50': 5.503837704658508, 'latency_p90': 6.300564861297607}, {'batch_size': 10, 'throughput': 1.471578157848972, 'latency_mean': 6.740707876682282, 'latency_p50': 6.703210353851318, 'latency_p90': 7.626561713218689}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-nitral12b-dpos1-_95096_v5

is_internal_developer: False

language_model: ChaiML/nitral12b-dpos1-b06-pref10k

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-06-22

win_ratio: 0.48676421311292306

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 chaiml-nitral12b-dpos1-95096-v5-mkmlizer
Waiting for job on chaiml-nitral12b-dpos1-95096-v5-mkmlizer to finish
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║                                                                     ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║                                                                     ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║                                                                     ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║                                                                     ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ║                                                                     ║
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: Downloaded to shared memory in 41.018s
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: Checking if ChaiML/nitral12b-dpos1-b06-pref10k already exists in ChaiML
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn3ql8mqz, device:0
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: quantized model in 31.383s
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: Processed model ChaiML/nitral12b-dpos1-b06-pref10k in 72.402s
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nitral12b-dpos1-95096-v5
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nitral12b-dpos1-95096-v5/config.json
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nitral12b-dpos1-95096-v5/special_tokens_map.json
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nitral12b-dpos1-95096-v5/tokenizer_config.json
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nitral12b-dpos1-95096-v5/flywheel_model.0.safetensors
chaiml-nitral12b-dpos1-95096-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.18it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.88it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.84it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 38.70it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.98it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.43it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.61it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 45.20it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 37.04it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.44it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.35it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.16it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.23it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.35it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.34it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.58it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.01it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.40it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 41.38it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 45.24it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 38.38it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:06, 37.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.79it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.63it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.46it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.44it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.99it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.55it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.76it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.58it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.58it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 38.91it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.00it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 39.47it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 39.67it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 40.20it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.96it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.63it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 41.31it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.29it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.20it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.85it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.89it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.28it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.28it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.29it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 32.54it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.21it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 38.96it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.49it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.23it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 33.83it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.31it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.39it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 41.46it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 22.48it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 23.65it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 25.82it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 30.07it/s]
Loading 0:  89%|████████▉ | 323/363 [00:08<00:01, 30.49it/s]
Loading 0:  90%|█████████ | 328/363 [00:09<00:01, 34.28it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 34.36it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 37.73it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 38.34it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 39.44it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 41.28it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 33.69it/s]
                                                            
Job chaiml-nitral12b-dpos1-95096-v5-mkmlizer completed after 94.08s with status: succeeded
Stopping job with name chaiml-nitral12b-dpos1-95096-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nitral12b-dpos1-95096-v5
Waiting for inference service chaiml-nitral12b-dpos1-95096-v5 to be ready
Inference service chaiml-nitral12b-dpos1-95096-v5 ready after 110.59579658508301s
Pipeline stage MKMLDeployer completed in 111.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.254234552383423s
Received healthy response to inference request in 1.7049880027770996s
Received healthy response to inference request in 1.483933925628662s
Received healthy response to inference request in 1.6121532917022705s
Received healthy response to inference request in 1.523505687713623s
5 requests
0 failed requests
5th percentile: 1.4918482780456543
10th percentile: 1.4997626304626466
20th percentile: 1.5155913352966308
30th percentile: 1.5412352085113525
40th percentile: 1.5766942501068115
50th percentile: 1.6121532917022705
60th percentile: 1.649287176132202
70th percentile: 1.6864210605621337
80th percentile: 1.8148373126983643
90th percentile: 2.0345359325408934
95th percentile: 2.144385242462158
99th percentile: 2.23226469039917
mean time: 1.7157630920410156
Pipeline stage StressChecker completed in 10.27s
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 0.76s
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 0.68s
Shutdown handler de-registered
chaiml-nitral12b-dpos1-_95096_v5 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 5397.73s
Shutdown handler de-registered
chaiml-nitral12b-dpos1-_95096_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-nitral12b-dpos1-_95096_v5 status is now torndown due to DeploymentManager action