chaiml-llama-8b-nis-800_13902

developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_13902_v1
model_name: chaiml-llama-8b-nis-800_13902_v1
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-06T09:03:29+00:00
num_battles: 11785
num_wins: 5829
celo_rating: 1284.78
family_friendly_score: 0.5314
family_friendly_standard_error: 0.0070571104568371325
submission_type: basic
model_repo: ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_lin_bestep_672acc
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_13902_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_lin_bestep_672acc
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-06
win_ratio: 0.49461179465422145
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-800-13902-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-13902-v1-mkmlizer to finish
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: Downloaded to shared memory in 30.314s
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_lin_bestep_672acc already exists in ChaiML
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp4o1f6n24, device:0
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: quantized model in 23.610s
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_200mpret_lin_bestep_672acc in 53.925s
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-13902-v1/nvidia
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-13902-v1/nvidia/config.json
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-13902-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-13902-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-13902-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-13902-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-13902-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 27.03it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 43.81it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 43.14it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 42.62it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:06, 43.54it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:07, 34.19it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:05, 42.11it/s]
Loading 0:  15%|█▌        | 44/291 [00:01<00:06, 41.16it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:05, 40.55it/s]
Loading 0:  19%|█▊        | 54/291 [00:01<00:05, 41.04it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:06, 33.57it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:05, 40.28it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:05, 39.87it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:05, 40.24it/s]
Loading 0:  28%|██▊       | 81/291 [00:02<00:05, 41.64it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:08, 23.40it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:06, 30.20it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 32.46it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 34.39it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 36.71it/s]
Loading 0:  39%|███▉      | 113/291 [00:03<00:05, 30.44it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 37.10it/s]
Loading 0:  43%|████▎     | 125/291 [00:03<00:04, 38.01it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 38.45it/s]
Loading 0:  46%|████▋     | 135/291 [00:03<00:03, 39.71it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:04, 32.41it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:03, 38.64it/s]
Loading 0:  52%|█████▏    | 152/291 [00:04<00:03, 38.96it/s]
Loading 0:  54%|█████▍    | 157/291 [00:04<00:03, 39.25it/s]
Loading 0:  56%|█████▌    | 162/291 [00:04<00:03, 39.57it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 31.24it/s]
Loading 0:  59%|█████▉    | 172/291 [00:04<00:03, 35.04it/s]
Loading 0:  61%|██████    | 177/291 [00:04<00:03, 36.24it/s]
Loading 0:  62%|██████▏   | 181/291 [00:04<00:03, 33.56it/s]
Loading 0:  64%|██████▍   | 187/291 [00:05<00:03, 26.78it/s]
Loading 0:  66%|██████▌   | 191/291 [00:05<00:03, 27.95it/s]
Loading 0:  67%|██████▋   | 195/291 [00:05<00:03, 28.12it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 33.27it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 33.08it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:02, 36.15it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 35.96it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 38.23it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 36.24it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 36.74it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 33.79it/s]
Loading 0:  81%|████████▏ | 237/291 [00:06<00:01, 39.10it/s]
Loading 0:  83%|████████▎ | 242/291 [00:06<00:01, 38.77it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:01, 39.89it/s]
Loading 0:  87%|████████▋ | 252/291 [00:06<00:00, 41.12it/s]
Loading 0:  88%|████████▊ | 257/291 [00:07<00:01, 32.99it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 40.01it/s]
Loading 0:  92%|█████████▏| 269/291 [00:07<00:00, 39.82it/s]
Loading 0:  94%|█████████▍| 274/291 [00:07<00:00, 39.56it/s]
Loading 0:  96%|█████████▌| 279/291 [00:07<00:00, 40.13it/s]
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 34.06it/s]
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00, 23.68it/s]
                                                            
Job chaiml-llama-8b-nis-800-13902-v1-mkmlizer completed after 84.42s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-13902-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.18s
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-800-13902-v1
Waiting for inference service chaiml-llama-8b-nis-800-13902-v1 to be ready
Inference service chaiml-llama-8b-nis-800-13902-v1 ready after 221.3056125640869s
Pipeline stage MKMLDeployer completed in 221.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.243268013000488s
Received healthy response to inference request in 3.137108325958252s
Received healthy response to inference request in 5.251734495162964s
Received healthy response to inference request in 2.628803014755249s
Received healthy response to inference request in 4.244232654571533s
5 requests
0 failed requests
5th percentile: 2.7304640769958497
10th percentile: 2.8321251392364504
20th percentile: 3.0354472637176513
30th percentile: 3.358340263366699
40th percentile: 3.8008041381835938
50th percentile: 4.243268013000488
60th percentile: 4.243653869628906
70th percentile: 4.244039726257324
80th percentile: 4.4457330226898195
90th percentile: 4.848733758926391
95th percentile: 5.050234127044678
99th percentile: 5.211434421539306
mean time: 3.9010293006896974
Pipeline stage StressChecker completed in 21.33s
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 0.78s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_13902_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
%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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3659.66s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_13902_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_13902_v1 status is now torndown due to DeploymentManager action