developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_59411_v4
model_name: chaiml-llama-8b-nis-800_59411_v4
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-06T23:53:32+00:00
num_battles: 8776
num_wins: 4468
celo_rating: 1295.61
family_friendly_score: 0.5304
family_friendly_standard_error: 0.007057986115033097
submission_type: basic
model_repo: ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 1
reward_model: default
display_name: chaiml-llama-8b-nis-800_59411_v4
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-06
win_ratio: 0.5091157702825889
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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-llama-8b-nis-800-59411-v4-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-59411-v4-mkmlizer to finish
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: Downloaded to shared memory in 23.179s
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc already exists in ChaiML
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpmn2q82i4, device:0
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: quantized model in 19.980s
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc in 43.159s
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v4/nvidia
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v4/nvidia/config.json
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v4/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v4/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-59411-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 37.77it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 55.74it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 45.99it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:06, 41.81it/s] Loading 0: 10%|█ | 30/291 [00:00<00:05, 46.43it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:05, 45.35it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 45.18it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:05, 46.06it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:06, 35.44it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:05, 43.15it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:05, 43.18it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:05, 42.75it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 44.38it/s] Loading 0: 26%|██▋ | 77/291 [00:01<00:06, 35.33it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:07, 27.28it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 28.28it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 34.36it/s] Loading 0: 34%|███▎ | 98/291 [00:02<00:05, 36.39it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 38.38it/s] Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 39.82it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:05, 33.83it/s] Loading 0: 42%|████▏ | 121/291 [00:03<00:03, 42.70it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:03, 41.18it/s] Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 40.97it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 45.93it/s] Loading 0: 49%|████▉ | 144/291 [00:03<00:03, 45.94it/s] Loading 0: 51%|█████ | 149/291 [00:03<00:03, 38.43it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 46.16it/s] Loading 0: 56%|█████▌ | 163/291 [00:04<00:02, 42.83it/s] Loading 0: 58%|█████▊ | 168/291 [00:04<00:02, 42.60it/s] Loading 0: 60%|█████▉ | 174/291 [00:04<00:02, 46.66it/s] Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 46.80it/s] Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 46.11it/s] Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 26.72it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 29.90it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:02, 38.63it/s] Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 38.31it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:01, 39.36it/s] Loading 0: 75%|███████▌ | 219/291 [00:05<00:01, 42.87it/s] Loading 0: 77%|███████▋ | 224/291 [00:05<00:01, 44.06it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 45.54it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 42.88it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 42.36it/s] Loading 0: 85%|████████▍ | 246/291 [00:06<00:00, 46.25it/s] Loading 0: 86%|████████▋ | 251/291 [00:06<00:00, 45.67it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 45.90it/s] Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 41.95it/s] Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 41.84it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 47.70it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 44.13it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 41.62it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 30.72it/s]
Job chaiml-llama-8b-nis-800-59411-v4-mkmlizer completed after 64.3s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-59411-v4-mkmlizer
Pipeline stage MKMLizer completed in 64.83s
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-llama-8b-nis-800-59411-v4
Waiting for inference service chaiml-llama-8b-nis-800-59411-v4 to be ready
Inference service chaiml-llama-8b-nis-800-59411-v4 ready after 200.74941873550415s
Pipeline stage MKMLDeployer completed in 201.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2706475257873535s
Received healthy response to inference request in 5.185013771057129s
Received healthy response to inference request in 3.683964967727661s
Received healthy response to inference request in 4.016423463821411s
Received healthy response to inference request in 4.369316816329956s
5 requests
0 failed requests
5th percentile: 2.553311014175415
10th percentile: 2.8359745025634764
20th percentile: 3.4013014793395997
30th percentile: 3.750456666946411
40th percentile: 3.883440065383911
50th percentile: 4.016423463821411
60th percentile: 4.157580804824829
70th percentile: 4.298738145828247
80th percentile: 4.5324562072753904
90th percentile: 4.85873498916626
95th percentile: 5.0218743801116945
99th percentile: 5.152385892868042
mean time: 3.905073308944702
Pipeline stage StressChecker completed in 21.56s
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 0.73s
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 0.79s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_59411_v4 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 9464.51s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_59411_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_59411_v4 status is now torndown due to DeploymentManager action