chaiml-nis-8b-v1-llama3_84691

developer_uid: NischayDnk

submission_id: chaiml-nis-8b-v1-llama3_84691_v4

model_name: chaiml-nis-8b-v1-llama3_84691_v4

model_group: ChaiML/nis-8b-v1-llama3-

status: torndown

timestamp: 2025-09-29T20:34:33+00:00

num_battles: 5371

num_wins: 2650

family_friendly_score: 0.5226

family_friendly_standard_error: 0.007063840881560116

submission_type: basic

model_repo: ChaiML/nis-8b-v1-llama3-prod-ftosmodelsdata50k1404_merged

model_architecture: LlamaForSequenceClassification

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3159881729603714, 'latency_mean': 3.1645484268665314, 'latency_p50': 3.158424496650696, 'latency_p90': 3.24357008934021}, {'batch_size': 2, 'throughput': 0.31638177735390355, 'latency_mean': 6.308870428800583, 'latency_p50': 6.301184296607971, 'latency_p90': 6.428841757774353}, {'batch_size': 5, 'throughput': 0.3096189781280636, 'latency_mean': 16.014057141542434, 'latency_p50': 16.117875576019287, 'latency_p90': 16.44435112476349}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-nis-8b-v1-llama3_84691_v4

is_internal_developer: False

language_model: ChaiML/nis-8b-v1-llama3-prod-ftosmodelsdata50k1404_merged

model_size: 8B

ranking_group: single

throughput_3p7s: 0.32

us_pacific_date: 2025-09-29

win_ratio: 0.493390430087507

generation_params: {'temperature': 0.55, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['\n'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

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-nis-8b-v1-llama3-84691-v4-mkmlizer
Waiting for job on chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer to finish
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║                                                                     ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║                                                                     ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║                                                                     ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║                                                                     ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ║                                                                     ║
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-smallbase-nis-mu_14714_v2: HTTPConnectionPool(host='chaiml-smallbase-nis-mu-14714-v2-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: Downloaded to shared memory in 17.158s
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: Checking if ChaiML/nis-8b-v1-llama3-prod-ftosmodelsdata50k1404_merged already exists in ChaiML
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpx281e261, device:0
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission rirv938-grpo-20250926-c_37256_v2: HTTPConnectionPool(host='rirv938-grpo-20250926-c-37256-v2-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: quantized model in 16.562s
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: Processed model ChaiML/nis-8b-v1-llama3-prod-ftosmodelsdata50k1404_merged in 33.721s
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-84691-v4/nvidia
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-84691-v4/nvidia/special_tokens_map.json
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-84691-v4/nvidia/config.json
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-84691-v4/nvidia/tokenizer_config.json
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-84691-v4/nvidia/tokenizer.json
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-84691-v4/nvidia/flywheel_model.0.safetensors
chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.58it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 49.09it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.94it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 53.43it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 52.96it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 53.67it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 54.57it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 54.84it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:03, 56.28it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:04, 46.31it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:04, 45.95it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 46.05it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:03, 50.02it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:03, 53.15it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 52.30it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:02, 53.95it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:02, 54.46it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:02, 55.59it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:02, 56.03it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 56.05it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:01, 60.78it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 62.30it/s]
Loading 0:  66%|██████▌   | 191/291 [00:03<00:02, 43.23it/s]
Loading 0:  68%|██████▊   | 197/291 [00:03<00:02, 45.99it/s]
Loading 0:  70%|██████▉   | 203/291 [00:03<00:02, 43.62it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 46.00it/s]
Loading 0:  76%|███████▌  | 221/291 [00:04<00:01, 48.24it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 50.97it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:00, 53.21it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 54.40it/s]
Loading 0:  88%|████████▊ | 257/291 [00:04<00:00, 55.45it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 56.09it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 56.69it/s]
Loading 0:  97%|█████████▋| 282/291 [00:05<00:00, 55.10it/s]
Loading 0:  99%|█████████▉| 288/291 [00:05<00:00, 44.29it/s]
                                                            
Job chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer completed after 93.79s with status: succeeded
Stopping job with name chaiml-nis-8b-v1-llama3-84691-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.61s
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-nis-8b-v1-llama3-84691-v4
Waiting for inference service chaiml-nis-8b-v1-llama3-84691-v4 to be ready
Inference service chaiml-nis-8b-v1-llama3-84691-v4 ready after 30.14156723022461s
Pipeline stage MKMLDeployer completed in 30.57s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission chaiml-jace-lightwood-s_43552_v2: HTTPConnectionPool(host='chaiml-jace-lightwood-s-43552-v2-predictor.creator-studio.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.7623744010925293s
Received healthy response to inference request in 2.7883358001708984s
Received healthy response to inference request in 1.6083672046661377s
Received healthy response to inference request in 4.6880059242248535s
5 requests
1 failed requests
5th percentile: 1.84436092376709
10th percentile: 2.080354642868042
20th percentile: 2.552342081069946
30th percentile: 2.983143520355225
40th percentile: 3.372758960723877
50th percentile: 3.7623744010925293
60th percentile: 4.132627010345459
70th percentile: 4.502879619598389
80th percentile: 7.778583621978763
90th percentile: 13.959739017486573
95th percentile: 17.050316715240477
99th percentile: 19.522778873443603
mean time: 6.59759554862976
%s, retrying in %s seconds...
Received healthy response to inference request in 2.7377099990844727s
Received healthy response to inference request in 2.6389520168304443s
Received healthy response to inference request in 3.6079142093658447s
Received healthy response to inference request in 2.657660722732544s
Received healthy response to inference request in 2.709836006164551s
5 requests
0 failed requests
5th percentile: 2.6426937580108643
10th percentile: 2.646435499191284
20th percentile: 2.653918981552124
30th percentile: 2.6680957794189455
40th percentile: 2.688965892791748
50th percentile: 2.709836006164551
60th percentile: 2.7209856033325197
70th percentile: 2.732135200500488
80th percentile: 2.9117508411407473
90th percentile: 3.259832525253296
95th percentile: 3.43387336730957
99th percentile: 3.5731060409545896
mean time: 2.8704145908355714
Pipeline stage StressChecker completed in 50.17s
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 0.62s
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 0.74s
Shutdown handler de-registered
chaiml-nis-8b-v1-llama3_84691_v4 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nis-8b-v1-llama3-84691-v4-profiler
Waiting for inference service chaiml-nis-8b-v1-llama3-84691-v4-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2712.66s
Shutdown handler de-registered
chaiml-nis-8b-v1-llama3_84691_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-8b-v1-llama3_84691_v4 status is now torndown due to DeploymentManager action