cgato-nemo-12b-humanize_88285

developer_uid: cgato

submission_id: cgato-nemo-12b-humanize_88285_v1

model_name: cgato-nemo-12b-humanize_88285_v1

model_group: cgato/Nemo-12b-Humanize-

status: torndown

timestamp: 2025-07-04T14:19:31+00:00

num_battles: 9566

num_wins: 4419

celo_rating: 1263.9

family_friendly_score: 0.5184

family_friendly_standard_error: 0.007066278228317931

submission_type: basic

model_repo: cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO

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': 0.6002702468658446, 'latency_mean': 1.665810877084732, 'latency_p50': 1.6728469133377075, 'latency_p90': 1.844676923751831}, {'batch_size': 3, 'throughput': 1.0786677131968352, 'latency_mean': 2.7769282591342925, 'latency_p50': 2.7779914140701294, 'latency_p90': 3.023110294342041}, {'batch_size': 5, 'throughput': 1.3155048962364628, 'latency_mean': 3.787542270421982, 'latency_p50': 3.7633821964263916, 'latency_p90': 4.22986536026001}, {'batch_size': 6, 'throughput': 1.3679037455877703, 'latency_mean': 4.366932755708694, 'latency_p50': 4.394495010375977, 'latency_p90': 4.943253850936889}, {'batch_size': 8, 'throughput': 1.4278257235772205, 'latency_mean': 5.563930380344391, 'latency_p50': 5.62054705619812, 'latency_p90': 6.2554994344711305}, {'batch_size': 10, 'throughput': 1.4655414651410037, 'latency_mean': 6.773416628837586, 'latency_p50': 6.739261627197266, 'latency_p90': 7.631358814239502}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-humanize_88285_v1

ineligible_reason: num_battles<10000

is_internal_developer: False

language_model: cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-07-04

win_ratio: 0.4619485678444491

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 cgato-nemo-12b-humanize-88285-v1-mkmlizer
Waiting for job on cgato-nemo-12b-humanize-88285-v1-mkmlizer to finish
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-88285-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-humanize-88285-v1-mkmlizer: Downloaded to shared memory in 36.986s
cgato-nemo-12b-humanize-88285-v1-mkmlizer: Checking if cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO already exists in ChaiML
cgato-nemo-12b-humanize-88285-v1-mkmlizer: Creating repo ChaiML/Nemo-12b-Humanize-SFT-v0.2.5-KTO and uploading /tmp/tmpq0bl8u82 to it
cgato-nemo-12b-humanize-88285-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:03<00:18,  3.73s/it]
 33%|███▎      | 2/6 [00:07<00:14,  3.65s/it]
 50%|█████     | 3/6 [00:13<00:14,  4.72s/it]
 67%|██████▋   | 4/6 [00:17<00:09,  4.61s/it]
 83%|████████▎ | 5/6 [00:21<00:04,  4.29s/it]
100%|██████████| 6/6 [00:22<00:00,  3.27s/it]
100%|██████████| 6/6 [00:22<00:00,  3.80s/it]
cgato-nemo-12b-humanize-88285-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq0bl8u82, device:0
cgato-nemo-12b-humanize-88285-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-humanize-88285-v1-mkmlizer: quantized model in 30.883s
cgato-nemo-12b-humanize-88285-v1-mkmlizer: Processed model cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO in 116.301s
cgato-nemo-12b-humanize-88285-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-humanize-88285-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-humanize-88285-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-humanize-88285-v1/nvidia
cgato-nemo-12b-humanize-88285-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-88285-v1/nvidia/special_tokens_map.json
cgato-nemo-12b-humanize-88285-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-88285-v1/nvidia/config.json
cgato-nemo-12b-humanize-88285-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-88285-v1/nvidia/tokenizer_config.json
cgato-nemo-12b-humanize-88285-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-88285-v1/nvidia/tokenizer.json
cgato-nemo-12b-humanize-88285-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-humanize-88285-v1/nvidia/flywheel_model.0.safetensors
cgato-nemo-12b-humanize-88285-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.46it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 43.60it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.11it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 42.32it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 43.65it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.39it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 43.01it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 41.94it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 41.68it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 43.28it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:07, 40.77it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 27.36it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.25it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 34.70it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 36.37it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.39it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.76it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 38.87it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 38.68it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 40.39it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 34.52it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.89it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.03it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.58it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 39.26it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 40.67it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 26.07it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.22it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.64it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.87it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.42it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.02it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.84it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.28it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 41.65it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 42.66it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 42.06it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 41.16it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 45.06it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.08it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 48.65it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:04, 29.82it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.87it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 37.05it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.94it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.05it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.11it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.52it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 42.78it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 42.87it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.05it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.82it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 43.39it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.49it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 44.96it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 24.28it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 25.22it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 27.84it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.66it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.88it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 37.62it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 43.77it/s]
Loading 0:  94%|█████████▍| 343/363 [00:09<00:00, 44.79it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 38.63it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 46.33it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 44.10it/s]
                                                            
Job cgato-nemo-12b-humanize-88285-v1-mkmlizer completed after 146.23s with status: succeeded
Stopping job with name cgato-nemo-12b-humanize-88285-v1-mkmlizer
Pipeline stage MKMLizer completed in 147.00s
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 cgato-nemo-12b-humanize-88285-v1
Waiting for inference service cgato-nemo-12b-humanize-88285-v1 to be ready
Inference service cgato-nemo-12b-humanize-88285-v1 ready after 221.02587366104126s
Pipeline stage MKMLDeployer completed in 221.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8187716007232666s
Received healthy response to inference request in 1.636859655380249s
Received healthy response to inference request in 1.9064247608184814s
Received healthy response to inference request in 1.5020778179168701s
Received healthy response to inference request in 1.520644187927246s
5 requests
0 failed requests
5th percentile: 1.5057910919189452
10th percentile: 1.5095043659210206
20th percentile: 1.516930913925171
30th percentile: 1.5438872814178466
40th percentile: 1.5903734683990478
50th percentile: 1.636859655380249
60th percentile: 1.744685697555542
70th percentile: 1.8525117397308348
80th percentile: 2.0888941287994385
90th percentile: 2.4538328647613525
95th percentile: 2.6363022327423096
99th percentile: 2.782277727127075
mean time: 1.8769556045532227
Pipeline stage StressChecker completed in 10.89s
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 0.80s
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 0.72s
Shutdown handler de-registered
cgato-nemo-12b-humanize_88285_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cgato-nemo-12b-humanize-88285-v1-profiler
Waiting for inference service cgato-nemo-12b-humanize-88285-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3285.15s
Shutdown handler de-registered
cgato-nemo-12b-humanize_88285_v1 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-humanize_88285_v1 status is now torndown due to DeploymentManager action