developer_uid: NischayDnk
submission_id: chaiml-llama3-200m-v2-t_76584_v1
model_name: chaiml-llama3-200m-v2-t_76584_v1
model_group: ChaiML/llama3-200m-v2-tr
status: torndown
timestamp: 2025-07-09T05:11:17+00:00
num_battles: 5694
num_wins: 2906
celo_rating: 1302.15
family_friendly_score: 0.5318
family_friendly_standard_error: 0.0070567522274768875
submission_type: basic
model_repo: ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725
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-llama3-200m-v2-t_76584_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-08
win_ratio: 0.5103617843343871
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-llama3-200m-v2-t-76584-v1-mkmlizer
Waiting for job on chaiml-llama3-200m-v2-t-76584-v1-mkmlizer to finish
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ belonging to: ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: Downloaded to shared memory in 27.461s
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: Checking if ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725 already exists in ChaiML
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpfqe9y3gs, device:0
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: quantized model in 19.165s
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: Processed model ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725 in 46.626s
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v1/nvidia
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v1/nvidia/config.json
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v1/nvidia/special_tokens_map.json
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v1/nvidia/tokenizer_config.json
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v1/nvidia/tokenizer.json
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama3-200m-v2-t-76584-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:09, 30.59it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 50.98it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.55it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:05, 47.05it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 53.72it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 49.29it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:04, 49.66it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:05, 45.85it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 48.04it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:04, 49.15it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 54.76it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 50.36it/s] Loading 0: 30%|███ | 88/291 [00:01<00:05, 36.37it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 39.72it/s] Loading 0: 34%|███▍ | 99/291 [00:02<00:04, 40.97it/s] Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 36.00it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 44.22it/s] Loading 0: 41%|████ | 118/291 [00:02<00:04, 41.66it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:04, 40.47it/s] Loading 0: 44%|████▍ | 129/291 [00:02<00:03, 44.51it/s] Loading 0: 46%|████▌ | 134/291 [00:03<00:03, 44.11it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 44.38it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 42.11it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 42.55it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 48.72it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 45.36it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 44.65it/s] Loading 0: 60%|█████▉ | 174/291 [00:03<00:02, 48.37it/s] Loading 0: 62%|██████▏ | 180/291 [00:03<00:02, 49.08it/s] Loading 0: 64%|██████▍ | 186/291 [00:04<00:02, 44.41it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 30.64it/s] Loading 0: 67%|██████▋ | 195/291 [00:04<00:03, 30.93it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 37.67it/s] Loading 0: 71%|███████ | 207/291 [00:04<00:02, 39.47it/s] Loading 0: 73%|███████▎ | 212/291 [00:05<00:02, 33.57it/s] Loading 0: 75%|███████▌ | 219/291 [00:05<00:01, 41.07it/s] Loading 0: 77%|███████▋ | 224/291 [00:05<00:01, 41.46it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 43.46it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 40.81it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 42.48it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 49.13it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 45.65it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 46.07it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 45.98it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 53.36it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 49.56it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 43.21it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 37.76it/s]
Job chaiml-llama3-200m-v2-t-76584-v1-mkmlizer completed after 74.44s with status: succeeded
Stopping job with name chaiml-llama3-200m-v2-t-76584-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama3-200m-v2-t-76584-v1
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v1 to be ready
Inference service chaiml-llama3-200m-v2-t-76584-v1 ready after 200.72886967658997s
Pipeline stage MKMLDeployer completed in 201.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.313363790512085s
Received healthy response to inference request in 4.890382528305054s
Received healthy response to inference request in 3.1035194396972656s
Received healthy response to inference request in 3.5208451747894287s
Received healthy response to inference request in 2.882467746734619s
5 requests
0 failed requests
5th percentile: 2.9266780853271483
10th percentile: 2.9708884239196776
20th percentile: 3.0593091011047364
30th percentile: 3.1454883098602293
40th percentile: 3.229426050186157
50th percentile: 3.313363790512085
60th percentile: 3.3963563442230225
70th percentile: 3.47934889793396
80th percentile: 3.794752645492554
90th percentile: 4.342567586898804
95th percentile: 4.616475057601928
99th percentile: 4.835601034164429
mean time: 3.5421157360076903
Pipeline stage StressChecker completed in 18.93s
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 0.65s
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 0.67s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_76584_v1 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 0.11s
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-llama3-200m-v2-t-76584-v1-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4768.68s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_76584_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama3-200m-v2-t_76584_v1 status is now torndown due to DeploymentManager action