developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_35125_v3
model_name: chaiml-llama-8b-nis-800_35125_v3
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-07T21:12:45+00:00
num_battles: 7341
num_wins: 3753
celo_rating: 1297.66
family_friendly_score: 0.5258
family_friendly_standard_error: 0.007061647966303617
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_v3
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: 0.5112382509194933
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-v3-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-35125-v3-mkmlizer to finish
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: Downloaded to shared memory in 25.685s
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565 already exists in ChaiML
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpwzc1anco, device:0
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: quantized model in 22.493s
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565 in 48.179s
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v3/nvidia
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v3/nvidia/config.json
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v3/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v3/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v3/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v3/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-35125-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:09, 30.71it/s] Loading 0: 3%|▎ | 10/291 [00:00<00:07, 39.07it/s] Loading 0: 5%|▌ | 15/291 [00:00<00:07, 36.82it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:07, 37.21it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:07, 33.81it/s] Loading 0: 10%|█ | 30/291 [00:00<00:06, 41.92it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:06, 39.98it/s] Loading 0: 14%|█▎ | 40/291 [00:01<00:06, 38.99it/s] Loading 0: 15%|█▌ | 44/291 [00:01<00:06, 38.17it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:06, 38.07it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:06, 36.45it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 38.89it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 37.23it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:05, 39.40it/s] Loading 0: 24%|██▍ | 70/291 [00:01<00:05, 37.34it/s] Loading 0: 26%|██▌ | 75/291 [00:01<00:05, 39.76it/s] Loading 0: 27%|██▋ | 80/291 [00:02<00:05, 39.98it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 25.63it/s] Loading 0: 31%|███ | 89/291 [00:02<00:07, 27.46it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:06, 28.46it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 27.26it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:06, 29.40it/s] Loading 0: 36%|███▌ | 105/291 [00:03<00:06, 28.09it/s] Loading 0: 37%|███▋ | 109/291 [00:03<00:05, 30.48it/s] Loading 0: 39%|███▉ | 113/291 [00:03<00:06, 28.82it/s] Loading 0: 41%|████ | 118/291 [00:03<00:05, 32.04it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:05, 29.92it/s] Loading 0: 44%|████▍ | 129/291 [00:03<00:04, 37.60it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 35.99it/s] Loading 0: 47%|████▋ | 138/291 [00:04<00:04, 37.75it/s] Loading 0: 49%|████▉ | 142/291 [00:04<00:04, 36.28it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:03, 38.60it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:03, 35.82it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 37.80it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 36.17it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 38.73it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 36.85it/s] Loading 0: 59%|█████▉ | 173/291 [00:04<00:03, 36.69it/s] Loading 0: 62%|██████▏ | 179/291 [00:05<00:02, 41.46it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 40.06it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 21.68it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:04, 24.17it/s] Loading 0: 68%|██████▊ | 199/291 [00:05<00:03, 28.00it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:03, 27.10it/s] Loading 0: 71%|███████▏ | 208/291 [00:06<00:02, 30.96it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:02, 29.34it/s] Loading 0: 75%|███████▍ | 217/291 [00:06<00:02, 33.34it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:02, 30.88it/s] Loading 0: 78%|███████▊ | 226/291 [00:06<00:01, 34.53it/s] Loading 0: 79%|███████▉ | 230/291 [00:06<00:01, 31.28it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:01, 35.17it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 31.33it/s] Loading 0: 84%|████████▍ | 244/291 [00:07<00:01, 34.88it/s] Loading 0: 85%|████████▌ | 248/291 [00:07<00:01, 31.66it/s] Loading 0: 87%|████████▋ | 253/291 [00:07<00:01, 35.08it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:01, 32.10it/s] Loading 0: 90%|█████████ | 262/291 [00:07<00:00, 35.53it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 32.08it/s] Loading 0: 93%|█████████▎| 271/291 [00:08<00:00, 35.58it/s] Loading 0: 95%|█████████▍| 275/291 [00:08<00:00, 32.10it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 35.96it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 34.41it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 22.91it/s]
Job chaiml-llama-8b-nis-800-35125-v3-mkmlizer completed after 96.48s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-35125-v3-mkmlizer
Pipeline stage MKMLizer completed in 96.97s
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-800-35125-v3
Waiting for inference service chaiml-llama-8b-nis-800-35125-v3 to be ready
Inference service chaiml-llama-8b-nis-800-35125-v3 ready after 180.9801788330078s
Pipeline stage MKMLDeployer completed in 181.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.4540650844573975s
Received healthy response to inference request in 4.891010046005249s
Received healthy response to inference request in 3.7422032356262207s
Received healthy response to inference request in 4.500123739242554s
Received healthy response to inference request in 3.9575414657592773s
5 requests
0 failed requests
5th percentile: 3.785270881652832
10th percentile: 3.8283385276794433
20th percentile: 3.914473819732666
30th percentile: 4.056846189498901
40th percentile: 4.25545563697815
50th percentile: 4.4540650844573975
60th percentile: 4.47248854637146
70th percentile: 4.490912008285522
80th percentile: 4.578301000595093
90th percentile: 4.734655523300171
95th percentile: 4.81283278465271
99th percentile: 4.875374593734741
mean time: 4.30898871421814
Pipeline stage StressChecker completed in 23.03s
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 0.83s
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 0.71s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_35125_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Received signal 15, running shutdown handler
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 6590.06s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_35125_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_35125_v3 status is now torndown due to DeploymentManager action