developer_uid: richhx
submission_id: chaiml-anthropic-40k-2_11629_v13
model_name: chaiml-anthropic-40k-2_11629_v13
model_group: ChaiML/anthropic_40k_249
status: torndown
timestamp: 2025-06-24T22:01:38+00:00
num_battles: 7330
num_wins: 3704
celo_rating: 1290.49
family_friendly_score: 0.489
family_friendly_standard_error: 0.007069356406349874
submission_type: basic
model_repo: ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6353725087053945, 'latency_mean': 1.5736988079547882, 'latency_p50': 1.5829185247421265, 'latency_p90': 1.7463509798049928}, {'batch_size': 3, 'throughput': 1.1864960007106014, 'latency_mean': 2.520799980163574, 'latency_p50': 2.530975818634033, 'latency_p90': 2.812241506576538}, {'batch_size': 5, 'throughput': 1.4643412311424504, 'latency_mean': 3.39971853852272, 'latency_p50': 3.4428082704544067, 'latency_p90': 3.817238759994507}, {'batch_size': 6, 'throughput': 1.563844306094191, 'latency_mean': 3.8137495744228365, 'latency_p50': 3.8114529848098755, 'latency_p90': 4.324048924446106}, {'batch_size': 8, 'throughput': 1.6471273913432658, 'latency_mean': 4.830037187337876, 'latency_p50': 4.819082617759705, 'latency_p90': 5.363847732543945}, {'batch_size': 10, 'throughput': 1.6885402802000755, 'latency_mean': 5.869203649759292, 'latency_p50': 5.849262237548828, 'latency_p90': 6.557378625869751}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-anthropic-40k-2_11629_v13
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.55
us_pacific_date: 2025-06-24
win_ratio: 0.5053206002728513
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', 'You:', '<|end_of_text|>', '<|eot_id|>'], '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': '### Response:\n{bot_name}:', 'truncate_by_message': False}
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-anthropic-40k-2-11629-v13-mkmlizer
Waiting for job on chaiml-anthropic-40k-2-11629-v13-mkmlizer to finish
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ║                                                                     ║
chaiml-anthropic-40k-2-11629-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-40k-2-11629-v13-mkmlizer: Downloaded to shared memory in 91.239s
chaiml-anthropic-40k-2-11629-v13-mkmlizer: Checking if ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged already exists in ChaiML
chaiml-anthropic-40k-2-11629-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6nibgyv5, device:0
chaiml-anthropic-40k-2-11629-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-40k-2-11629-v13-mkmlizer: quantized model in 36.626s
chaiml-anthropic-40k-2-11629-v13-mkmlizer: Processed model ChaiML/anthropic_40k_2496_bo8_85w_b4_l1_merged in 127.865s
chaiml-anthropic-40k-2-11629-v13-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-40k-2-11629-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-40k-2-11629-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v13
chaiml-anthropic-40k-2-11629-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v13/config.json
chaiml-anthropic-40k-2-11629-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v13/special_tokens_map.json
chaiml-anthropic-40k-2-11629-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v13/tokenizer_config.json
chaiml-anthropic-40k-2-11629-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-40k-2-11629-v13/tokenizer.json
Job chaiml-anthropic-40k-2-11629-v13-mkmlizer completed after 155.15s with status: succeeded
Stopping job with name chaiml-anthropic-40k-2-11629-v13-mkmlizer
Pipeline stage MKMLizer completed in 155.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-40k-2-11629-v13
Waiting for inference service chaiml-anthropic-40k-2-11629-v13 to be ready
Inference service chaiml-anthropic-40k-2-11629-v13 ready after 130.5248429775238s
Pipeline stage MKMLDeployer completed in 131.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.344897747039795s
Received healthy response to inference request in 1.6572506427764893s
Received healthy response to inference request in 1.5794501304626465s
Received healthy response to inference request in 1.767719030380249s
Received healthy response to inference request in 1.6714327335357666s
5 requests
0 failed requests
5th percentile: 1.595010232925415
10th percentile: 1.6105703353881835
20th percentile: 1.6416905403137207
30th percentile: 1.6600870609283447
40th percentile: 1.6657598972320558
50th percentile: 1.6714327335357666
60th percentile: 1.7099472522735595
70th percentile: 1.7484617710113526
80th percentile: 1.8831547737121583
90th percentile: 2.1140262603759767
95th percentile: 2.229462003707886
99th percentile: 2.321810598373413
mean time: 1.8041500568389892
Pipeline stage StressChecker completed in 10.55s
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 0.74s
Shutdown handler de-registered
chaiml-anthropic-40k-2_11629_v13 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-anthropic-40k-2-11629-v13-profiler
Waiting for inference service chaiml-anthropic-40k-2-11629-v13-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 2846.93s
Shutdown handler de-registered
chaiml-anthropic-40k-2_11629_v13 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now protected due to ABTestQueueItem
chaiml-anthropic-40k-2_11629_v13 status is now torndown due to DeploymentManager action