developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_62683_v1
model_name: chaiml-llama-8b-nis-800_62683_v1
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-05T22:47:21+00:00
num_battles: 8281
num_wins: 4256
celo_rating: 1294.62
family_friendly_score: 0.5352
family_friendly_standard_error: 0.007053523374881521
submission_type: basic
model_repo: ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_bestep_572acc
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_62683_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_bestep_572acc
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-05
win_ratio: 0.5139475908706678
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-800-62683-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-62683-v1-mkmlizer to finish
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: Downloaded to shared memory in 28.028s
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_bestep_572acc already exists in ChaiML
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp887vzg7n, device:0
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: quantized model in 18.717s
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_bestep_572acc in 46.745s
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-62683-v1/nvidia
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-62683-v1/nvidia/config.json
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-62683-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-62683-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-62683-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-62683-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-62683-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 33.48it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 46.52it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 57.56it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:04, 52.64it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:05, 50.74it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:05, 43.64it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 51.87it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:04, 49.34it/s] Loading 0: 21%|██ | 61/291 [00:01<00:04, 49.62it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:04, 46.33it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 54.06it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 48.89it/s] Loading 0: 30%|███ | 88/291 [00:02<00:06, 32.00it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 35.95it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 36.85it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 38.85it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 45.40it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 43.65it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 43.41it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 49.83it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 48.29it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:03, 49.59it/s] Loading 0: 51%|█████ | 149/291 [00:03<00:03, 46.10it/s] Loading 0: 54%|█████▍ | 158/291 [00:03<00:02, 49.10it/s] Loading 0: 57%|█████▋ | 167/291 [00:03<00:02, 49.66it/s] Loading 0: 61%|██████ | 177/291 [00:03<00:02, 55.05it/s] Loading 0: 63%|██████▎ | 183/291 [00:03<00:01, 54.85it/s] Loading 0: 65%|██████▍ | 189/291 [00:04<00:02, 36.38it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:02, 37.99it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:01, 45.38it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:01, 44.41it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 44.95it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 50.72it/s] Loading 0: 78%|███████▊ | 226/291 [00:04<00:01, 48.48it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 49.43it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 52.02it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 46.81it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 43.88it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 49.23it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 44.85it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 43.69it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 49.71it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 47.29it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 46.51it/s] Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 34.23it/s]
Job chaiml-llama-8b-nis-800-62683-v1-mkmlizer completed after 74.13s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-62683-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-800-62683-v1
Waiting for inference service chaiml-llama-8b-nis-800-62683-v1 to be ready
Inference service chaiml-llama-8b-nis-800-62683-v1 ready after 221.02532052993774s
Pipeline stage MKMLDeployer completed in 221.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.339680433273315s
Received healthy response to inference request in 1.7766952514648438s
Received healthy response to inference request in 7.526731729507446s
Received healthy response to inference request in 2.686490297317505s
Received healthy response to inference request in 3.6582448482513428s
5 requests
0 failed requests
5th percentile: 1.958654260635376
10th percentile: 2.1406132698059084
20th percentile: 2.5045312881469726
30th percentile: 2.8808412075042726
40th percentile: 3.2695430278778077
50th percentile: 3.6582448482513428
60th percentile: 4.330819082260132
70th percentile: 5.00339331626892
80th percentile: 5.777090692520142
90th percentile: 6.651911211013794
95th percentile: 7.08932147026062
99th percentile: 7.439249677658081
mean time: 4.19756851196289
%s, retrying in %s seconds...
Received healthy response to inference request in 3.6549339294433594s
Received healthy response to inference request in 3.3936245441436768s
Received healthy response to inference request in 2.50327205657959s
Received healthy response to inference request in 3.569375514984131s
Received healthy response to inference request in 2.5907647609710693s
5 requests
0 failed requests
5th percentile: 2.5207705974578856
10th percentile: 2.5382691383361817
20th percentile: 2.5732662200927736
30th percentile: 2.7513367176055907
40th percentile: 3.072480630874634
50th percentile: 3.3936245441436768
60th percentile: 3.463924932479858
70th percentile: 3.53422532081604
80th percentile: 3.5864871978759765
90th percentile: 3.620710563659668
95th percentile: 3.6378222465515138
99th percentile: 3.65151159286499
mean time: 3.1423941612243653
Pipeline stage StressChecker completed in 39.71s
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 0.71s
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 0.69s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_62683_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 5803.65s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_62683_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_62683_v1 status is now torndown due to DeploymentManager action