developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_59411_v3
model_name: chaiml-llama-8b-nis-800_59411_v3
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-06T19:28:11+00:00
num_battles: 8146
num_wins: 4077
celo_rating: 1290.41
family_friendly_score: 0.5324
family_friendly_standard_error: 0.007056206346189147
submission_type: basic
model_repo: ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc
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_59411_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-06
win_ratio: 0.5004910385465259
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-800-59411-v3-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-59411-v3-mkmlizer to finish
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: Downloaded to shared memory in 27.544s
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc already exists in ChaiML
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpbmc_58zw, device:0
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: quantized model in 25.302s
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc in 52.846s
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v3/nvidia
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v3/nvidia/config.json
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v3/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v3/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v3/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v3/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-59411-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.65it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 43.73it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 41.75it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 40.62it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 42.10it/s] Loading 0: 11%|█ | 32/291 [00:00<00:08, 30.73it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:07, 34.68it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:07, 31.54it/s] Loading 0: 16%|█▌ | 46/291 [00:01<00:06, 35.70it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:07, 33.22it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:05, 40.80it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:05, 40.05it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:05, 39.78it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:05, 41.22it/s] Loading 0: 26%|██▋ | 77/291 [00:02<00:06, 34.24it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:07, 27.21it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 27.25it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:06, 32.49it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 32.32it/s] Loading 0: 35%|███▌ | 102/291 [00:02<00:05, 35.01it/s] Loading 0: 36%|███▋ | 106/291 [00:03<00:05, 34.24it/s] Loading 0: 38%|███▊ | 111/291 [00:03<00:04, 36.15it/s] Loading 0: 40%|███▉ | 115/291 [00:03<00:05, 33.62it/s] Loading 0: 41%|████ | 120/291 [00:03<00:04, 35.28it/s] Loading 0: 43%|████▎ | 124/291 [00:03<00:04, 33.99it/s] Loading 0: 44%|████▍ | 129/291 [00:03<00:04, 35.87it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 33.16it/s] Loading 0: 47%|████▋ | 137/291 [00:03<00:04, 34.65it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 31.66it/s] Loading 0: 50%|████▉ | 145/291 [00:04<00:04, 33.45it/s] Loading 0: 51%|█████ | 149/291 [00:04<00:04, 28.99it/s] Loading 0: 53%|█████▎ | 154/291 [00:04<00:04, 33.34it/s] Loading 0: 54%|█████▍ | 158/291 [00:04<00:04, 30.57it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.87it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 35.27it/s] Loading 0: 59%|█████▉ | 173/291 [00:05<00:03, 35.05it/s] Loading 0: 62%|██████▏ | 179/291 [00:05<00:02, 38.51it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:03, 35.11it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:04, 22.23it/s] Loading 0: 65%|██████▌ | 190/291 [00:05<00:04, 22.06it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:04, 23.02it/s] Loading 0: 68%|██████▊ | 199/291 [00:06<00:03, 28.12it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:03, 26.54it/s] Loading 0: 71%|███████▏ | 208/291 [00:06<00:02, 31.03it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:02, 29.13it/s] Loading 0: 75%|███████▍ | 217/291 [00:06<00:02, 33.75it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:02, 31.41it/s] Loading 0: 78%|███████▊ | 226/291 [00:06<00:01, 35.08it/s] Loading 0: 79%|███████▉ | 230/291 [00:07<00:01, 31.23it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:01, 35.33it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 31.52it/s] Loading 0: 84%|████████▍ | 244/291 [00:07<00:01, 35.77it/s] Loading 0: 85%|████████▌ | 248/291 [00:07<00:01, 32.82it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 39.52it/s] Loading 0: 89%|████████▉ | 260/291 [00:07<00:00, 38.01it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 34.73it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 32.95it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.57it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 33.71it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 33.21it/s] Loading 0: 98%|█████████▊| 285/291 [00:08<00:00, 33.51it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 22.17it/s]
Job chaiml-llama-8b-nis-800-59411-v3-mkmlizer completed after 95.3s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-59411-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-800-59411-v3
Waiting for inference service chaiml-llama-8b-nis-800-59411-v3 to be ready
Inference service chaiml-llama-8b-nis-800-59411-v3 ready after 190.75271940231323s
Pipeline stage MKMLDeployer completed in 191.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.604278802871704s
Received healthy response to inference request in 2.984722137451172s
Received healthy response to inference request in 4.496669292449951s
Received healthy response to inference request in 3.8638126850128174s
Received healthy response to inference request in 4.244344472885132s
5 requests
0 failed requests
5th percentile: 3.160540246963501
10th percentile: 3.33635835647583
20th percentile: 3.6879945755004884
30th percentile: 3.93991904258728
40th percentile: 4.092131757736206
50th percentile: 4.244344472885132
60th percentile: 4.34527440071106
70th percentile: 4.446204328536988
80th percentile: 4.918191194534302
90th percentile: 5.761234998703003
95th percentile: 6.1827569007873535
99th percentile: 6.519974422454834
mean time: 4.4387654781341555
Pipeline stage StressChecker completed in 23.94s
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 0.68s
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-800_59411_v3 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 7218.17s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_59411_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_59411_v3 status is now torndown due to DeploymentManager action