chaiml-llama-8b-nis-800_35125

developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_35125_v2
model_name: chaiml-llama-8b-nis-800_35125_v2
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-07T17:37:23+00:00
num_battles: 9521
num_wins: 4869
celo_rating: 1297.79
family_friendly_score: 0.5292
family_friendly_standard_error: 0.007058999362515909
submission_type: basic
model_repo: ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565
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_35125_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-07
win_ratio: 0.5113958617792249
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-800-35125-v2-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-35125-v2-mkmlizer to finish
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: Downloaded to shared memory in 33.254s
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565 already exists in ChaiML
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp5lhr837a, device:0
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: quantized model in 35.751s
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565 in 69.007s
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v2/nvidia
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v2/nvidia/config.json
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v2/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v2/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v2/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-35125-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:13, 20.92it/s]
Loading 0:   3%|▎         | 10/291 [00:00<00:09, 30.59it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:10, 25.36it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:09, 29.64it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:10, 26.62it/s]
Loading 0:  10%|▉         | 28/291 [00:01<00:09, 28.33it/s]
Loading 0:  11%|█         | 32/291 [00:01<00:11, 23.33it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:09, 26.13it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:11, 22.04it/s]
Loading 0:  16%|█▌        | 46/291 [00:01<00:09, 25.62it/s]
Loading 0:  17%|█▋        | 50/291 [00:02<00:10, 22.07it/s]
Loading 0:  19%|█▉        | 55/291 [00:02<00:09, 25.78it/s]
Loading 0:  20%|██        | 59/291 [00:02<00:09, 24.09it/s]
Loading 0:  22%|██▏       | 64/291 [00:02<00:08, 25.65it/s]
Loading 0:  23%|██▎       | 68/291 [00:02<00:09, 22.84it/s]
Loading 0:  25%|██▌       | 73/291 [00:02<00:08, 26.08it/s]
Loading 0:  26%|██▋       | 77/291 [00:03<00:08, 24.13it/s]
Loading 0:  28%|██▊       | 82/291 [00:03<00:07, 27.53it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:11, 18.35it/s]
Loading 0:  30%|███       | 88/291 [00:03<00:10, 19.47it/s]
Loading 0:  31%|███▏      | 91/291 [00:03<00:09, 21.11it/s]
Loading 0:  33%|███▎      | 95/291 [00:04<00:09, 21.06it/s]
Loading 0:  34%|███▍      | 100/291 [00:04<00:07, 25.36it/s]
Loading 0:  36%|███▌      | 104/291 [00:04<00:07, 23.95it/s]
Loading 0:  37%|███▋      | 109/291 [00:04<00:06, 26.74it/s]
Loading 0:  39%|███▉      | 113/291 [00:04<00:07, 24.32it/s]
Loading 0:  41%|████      | 118/291 [00:04<00:06, 27.98it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:06, 25.56it/s]
Loading 0:  44%|████▎     | 127/291 [00:05<00:05, 29.36it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:06, 26.57it/s]
Loading 0:  47%|████▋     | 136/291 [00:05<00:05, 29.96it/s]
Loading 0:  48%|████▊     | 140/291 [00:05<00:05, 25.74it/s]
Loading 0:  50%|████▉     | 145/291 [00:05<00:04, 29.23it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:05, 26.11it/s]
Loading 0:  53%|█████▎    | 154/291 [00:06<00:04, 29.15it/s]
Loading 0:  54%|█████▍    | 158/291 [00:06<00:05, 25.23it/s]
Loading 0:  56%|█████▌    | 163/291 [00:06<00:04, 28.69it/s]
Loading 0:  57%|█████▋    | 167/291 [00:06<00:04, 25.52it/s]
Loading 0:  59%|█████▉    | 172/291 [00:06<00:04, 29.30it/s]
Loading 0:  61%|██████    | 177/291 [00:06<00:04, 28.30it/s]
Loading 0:  62%|██████▏   | 181/291 [00:07<00:04, 26.17it/s]
Loading 0:  64%|██████▍   | 186/291 [00:07<00:03, 30.26it/s]
Loading 0:  65%|██████▌   | 190/291 [00:07<00:05, 18.88it/s]
Loading 0:  67%|██████▋   | 194/291 [00:07<00:04, 20.05it/s]
Loading 0:  68%|██████▊   | 199/291 [00:07<00:03, 24.43it/s]
Loading 0:  70%|██████▉   | 203/291 [00:08<00:03, 23.79it/s]
Loading 0:  71%|███████▏  | 208/291 [00:08<00:02, 28.40it/s]
Loading 0:  73%|███████▎  | 212/291 [00:08<00:03, 24.70it/s]
Loading 0:  75%|███████▍  | 217/291 [00:08<00:02, 28.16it/s]
Loading 0:  76%|███████▌  | 221/291 [00:08<00:02, 25.90it/s]
Loading 0:  78%|███████▊  | 226/291 [00:08<00:02, 29.38it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:02, 26.80it/s]
Loading 0:  81%|████████  | 235/291 [00:09<00:01, 30.66it/s]
Loading 0:  82%|████████▏ | 239/291 [00:09<00:01, 27.52it/s]
Loading 0:  84%|████████▍ | 244/291 [00:09<00:01, 31.00it/s]
Loading 0:  85%|████████▌ | 248/291 [00:09<00:01, 25.83it/s]
Loading 0:  87%|████████▋ | 253/291 [00:09<00:01, 30.40it/s]
Loading 0:  88%|████████▊ | 257/291 [00:09<00:01, 28.13it/s]
Loading 0:  90%|█████████ | 262/291 [00:10<00:00, 32.23it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 29.12it/s]
Loading 0:  93%|█████████▎| 271/291 [00:10<00:00, 32.19it/s]
Loading 0:  95%|█████████▍| 275/291 [00:10<00:00, 29.20it/s]
Loading 0:  96%|█████████▌| 280/291 [00:10<00:00, 32.27it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 29.24it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00, 18.68it/s]
                                                            
Job chaiml-llama-8b-nis-800-35125-v2-mkmlizer completed after 106.41s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-35125-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.91s
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-800-35125-v2
Waiting for inference service chaiml-llama-8b-nis-800-35125-v2 to be ready
Inference service chaiml-llama-8b-nis-800-35125-v2 ready after 191.4367437362671s
Pipeline stage MKMLDeployer completed in 192.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7880008220672607s
Received healthy response to inference request in 4.688835382461548s
Received healthy response to inference request in 2.381500720977783s
Received healthy response to inference request in 3.6989104747772217s
Received healthy response to inference request in 5.746121644973755s
5 requests
0 failed requests
5th percentile: 2.644982671737671
10th percentile: 2.9084646224975588
20th percentile: 3.435428524017334
30th percentile: 3.7167285442352296
40th percentile: 3.752364683151245
50th percentile: 3.7880008220672607
60th percentile: 4.148334646224976
70th percentile: 4.50866847038269
80th percentile: 4.900292634963989
90th percentile: 5.323207139968872
95th percentile: 5.5346643924713135
99th percentile: 5.703830194473267
mean time: 4.060673809051513
Pipeline stage StressChecker completed in 21.99s
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 0.61s
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 0.62s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_35125_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 0.09s
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-800-35125-v2-profiler
Waiting for inference service chaiml-llama-8b-nis-800-35125-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
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 7972.74s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_35125_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_35125_v2 status is now torndown due to DeploymentManager action