developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-ft-_30580_v2
model_name: chaiml-llama-8b-nis-ft-_30580_v2
model_group: ChaiML/llama_8b_nis_ft_n
status: torndown
timestamp: 2025-07-04T07:57:39+00:00
num_battles: 9854
num_wins: 4934
celo_rating: 1285.21
family_friendly_score: 0.5334
family_friendly_standard_error: 0.007055273772150873
submission_type: basic
model_repo: ChaiML/llama_8b_nis_ft_new1m_512seq_v625
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-ft-_30580_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_ft_new1m_512seq_v625
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-04
win_ratio: 0.5007103714227725
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-ft-30580-v2-mkmlizer
Waiting for job on chaiml-llama-8b-nis-ft-30580-v2-mkmlizer to finish
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: Downloaded to shared memory in 22.801s
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: Checking if ChaiML/llama_8b_nis_ft_new1m_512seq_v625 already exists in ChaiML
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmps5euzfsj, device:0
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: quantized model in 19.061s
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: Processed model ChaiML/llama_8b_nis_ft_new1m_512seq_v625 in 41.863s
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-30580-v2/nvidia
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-30580-v2/nvidia/config.json
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-30580-v2/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-30580-v2/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-30580-v2/nvidia/tokenizer.json
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-30580-v2/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-ft-30580-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.53it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 56.23it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 49.11it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:05, 50.30it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 45.79it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 54.28it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:04, 50.56it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 51.40it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 52.07it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 47.76it/s] Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 47.00it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 52.87it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 48.73it/s] Loading 0: 30%|███ | 88/291 [00:01<00:06, 32.60it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 37.07it/s] Loading 0: 34%|███▍ | 99/291 [00:02<00:05, 38.30it/s] Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 33.47it/s] Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 40.59it/s] Loading 0: 40%|███▉ | 116/291 [00:02<00:04, 40.66it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:04, 39.26it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 48.26it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 46.41it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:03, 48.01it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 50.96it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 48.60it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 48.17it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 51.07it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 47.89it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 52.49it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 53.54it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 32.78it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 34.40it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 38.99it/s] Loading 0: 71%|███████ | 207/291 [00:04<00:02, 41.34it/s] Loading 0: 73%|███████▎ | 212/291 [00:04<00:02, 37.54it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 45.75it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 43.32it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 43.80it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 49.53it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 45.20it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 45.01it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 50.97it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 47.70it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 46.09it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 51.70it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 49.05it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 44.58it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 36.43it/s]
Job chaiml-llama-8b-nis-ft-30580-v2-mkmlizer completed after 94.6s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-ft-30580-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.22s
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 chaiml-llama-8b-nis-ft-30580-v2
Waiting for inference service chaiml-llama-8b-nis-ft-30580-v2 to be ready
Inference service chaiml-llama-8b-nis-ft-30580-v2 ready after 211.06421899795532s
Pipeline stage MKMLDeployer completed in 211.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.272797346115112s
Received healthy response to inference request in 2.4994497299194336s
Received healthy response to inference request in 1.9368259906768799s
Received healthy response to inference request in 5.653077125549316s
Received healthy response to inference request in 2.9078962802886963s
5 requests
0 failed requests
5th percentile: 2.0493507385253906
10th percentile: 2.1618754863739014
20th percentile: 2.386924982070923
30th percentile: 2.5811390399932863
40th percentile: 2.7445176601409913
50th percentile: 2.9078962802886963
60th percentile: 3.8538567066192626
70th percentile: 4.799817132949829
80th percentile: 5.348853302001953
90th percentile: 5.500965213775634
95th percentile: 5.577021169662475
99th percentile: 5.637865934371948
mean time: 3.654009294509888
Pipeline stage StressChecker completed in 19.81s
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 0.67s
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-llama-8b-nis-ft-_30580_v2 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 0.10s
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 chaiml-llama-8b-nis-ft-30580-v2-profiler
Waiting for inference service chaiml-llama-8b-nis-ft-30580-v2-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 10376.43s
Shutdown handler de-registered
chaiml-llama-8b-nis-ft-_30580_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-ft-_30580_v2 status is now torndown due to DeploymentManager action