chaiml-llama-8b-nis-160_12983

developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-160_12983_v1
model_name: chaiml-llama-8b-nis-160_12983_v1
model_group: ChaiML/llama_8b_nis_160k
status: torndown
timestamp: 2025-07-05T19:22:36+00:00
num_battles: 10804
num_wins: 5455
celo_rating: 1292.56
family_friendly_score: 0.5284
family_friendly_standard_error: 0.007059652116074842
submission_type: basic
model_repo: ChaiML/llama_8b_nis_160ksamp_512seq_mer_bestep_merged
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-160_12983_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_160ksamp_512seq_mer_bestep_merged
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-05
win_ratio: 0.5049055905220289
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-160-12983-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-160-12983-v1-mkmlizer to finish
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: Downloaded to shared memory in 26.220s
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_160ksamp_512seq_mer_bestep_merged already exists in ChaiML
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpbwydfh61, device:0
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: quantized model in 19.149s
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_160ksamp_512seq_mer_bestep_merged in 45.370s
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-160-12983-v1/nvidia
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-160-12983-v1/nvidia/config.json
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-160-12983-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-160-12983-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-160-12983-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-160-12983-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-160-12983-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 39.15it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 53.26it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:05, 54.13it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 44.72it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 51.65it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.54it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 44.59it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 50.52it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 46.96it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 46.02it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.86it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.29it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 47.04it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.66it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 33.08it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 40.44it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.57it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.46it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 46.78it/s]
Loading 0:  40%|████      | 117/291 [00:02<00:03, 47.13it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:04, 39.89it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 47.79it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 44.94it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 44.44it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 49.85it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 45.92it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 45.40it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 50.96it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 46.79it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 49.97it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 51.22it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 33.05it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 34.26it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 38.61it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 38.79it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.05it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 45.73it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 43.67it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 43.62it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 49.11it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 43.95it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 43.60it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 49.06it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 46.05it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 44.70it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 48.33it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 46.98it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 38.41it/s]
Loading 0:  99%|█████████▉| 288/291 [00:06<00:00, 29.13it/s]
                                                            
Job chaiml-llama-8b-nis-160-12983-v1-mkmlizer completed after 63.89s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-160-12983-v1-mkmlizer
Pipeline stage MKMLizer completed in 64.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-160-12983-v1
Waiting for inference service chaiml-llama-8b-nis-160-12983-v1 to be ready
Inference service chaiml-llama-8b-nis-160-12983-v1 ready after 220.90392231941223s
Pipeline stage MKMLDeployer completed in 221.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.439746141433716s
Received healthy response to inference request in 3.5678627490997314s
Received healthy response to inference request in 6.860089302062988s
Received healthy response to inference request in 4.015641450881958s
Received healthy response to inference request in 6.084813594818115s
5 requests
0 failed requests
5th percentile: 3.6574184894561768
10th percentile: 3.746974229812622
20th percentile: 3.9260857105255127
30th percentile: 4.30046238899231
40th percentile: 4.870104265213013
50th percentile: 5.439746141433716
60th percentile: 5.697773122787476
70th percentile: 5.955800104141235
80th percentile: 6.23986873626709
90th percentile: 6.549979019165039
95th percentile: 6.705034160614013
99th percentile: 6.829078273773193
mean time: 5.193630647659302
%s, retrying in %s seconds...
Received healthy response to inference request in 4.7787885665893555s
Received healthy response to inference request in 3.3767714500427246s
Received healthy response to inference request in 3.9748716354370117s
Received healthy response to inference request in 3.2932660579681396s
Received healthy response to inference request in 3.981093168258667s
5 requests
0 failed requests
5th percentile: 3.3099671363830567
10th percentile: 3.326668214797974
20th percentile: 3.3600703716278075
30th percentile: 3.496391487121582
40th percentile: 3.735631561279297
50th percentile: 3.9748716354370117
60th percentile: 3.977360248565674
70th percentile: 3.979848861694336
80th percentile: 4.140632247924805
90th percentile: 4.45971040725708
95th percentile: 4.619249486923217
99th percentile: 4.7468807506561275
mean time: 3.8809581756591798
Pipeline stage StressChecker completed in 49.28s
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 0.92s
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
chaiml-llama-8b-nis-160_12983_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 7020.57s
Shutdown handler de-registered
chaiml-llama-8b-nis-160_12983_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-160_12983_v1 status is now torndown due to DeploymentManager action