chaiml-llama3-8b-exp2-c_82557

developer_uid: NischayDnk

submission_id: chaiml-llama3-8b-exp2-c_82557_v1

model_name: chaiml-llama3-8b-exp2-c_82557_v1

model_group: ChaiML/llama3-8b-exp2-cl

status: torndown

timestamp: 2025-03-19T15:48:07+00:00

num_battles: 9553

num_wins: 4331

celo_rating: 1243.53

family_friendly_score: 0.5902000000000001

family_friendly_standard_error: 0.006955055139968338

submission_type: basic

model_repo: ChaiML/llama3-8b-exp2-cls-bce-delete-seq512-acc87

model_architecture: LlamaForSequenceClassification

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.21876778690289322, 'latency_mean': 4.570986398458481, 'latency_p50': 4.568754315376282, 'latency_p90': 4.662979364395142}, {'batch_size': 2, 'throughput': 0.21691331068167966, 'latency_mean': 9.201761660575867, 'latency_p50': 9.183668613433838, 'latency_p90': 9.362713813781738}, {'batch_size': 5, 'throughput': 0.21367625139498536, 'latency_mean': 23.205116314888002, 'latency_p50': 23.381158590316772, 'latency_p90': 23.808064675331117}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-llama3-8b-exp2-c_82557_v1

is_internal_developer: False

language_model: ChaiML/llama3-8b-exp2-cls-bce-delete-seq512-acc87

model_size: 8B

ranking_group: single

us_pacific_date: 2025-03-19

win_ratio: 0.45336543494190307

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': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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-llama3-8b-exp2-c-82557-v1-mkmlizer
Waiting for job on chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer to finish
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║       /___/                                                         ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: Downloaded to shared memory in 28.773s
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmph4zum51b, device:0
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-llama3-8b-exp2-c_80038_v1: HTTPConnectionPool(host='chaiml-llama3-8b-exp2-c-80038-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: quantized model in 86.577s
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: Processed model ChaiML/llama3-8b-exp2-cls-bce-delete-seq512-acc87 in 115.350s
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama3-8b-exp2-c-82557-v1
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama3-8b-exp2-c-82557-v1/special_tokens_map.json
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama3-8b-exp2-c-82557-v1/config.json
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama3-8b-exp2-c-82557-v1/tokenizer_config.json
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama3-8b-exp2-c-82557-v1/tokenizer.json
chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama3-8b-exp2-c-82557-v1/flywheel_model.0.safetensors
Job chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer completed after 144.94s with status: succeeded
Stopping job with name chaiml-llama3-8b-exp2-c-82557-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.42s
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-llama3-8b-exp2-c-82557-v1
Waiting for inference service chaiml-llama3-8b-exp2-c-82557-v1 to be ready
Inference service chaiml-llama3-8b-exp2-c-82557-v1 ready after 90.38071250915527s
Pipeline stage MKMLDeployer completed in 90.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2423739433288574s
Received healthy response to inference request in 5.201092481613159s
Received healthy response to inference request in 3.9684665203094482s
Received healthy response to inference request in 2.792908191680908s
Received healthy response to inference request in 3.7198896408081055s
5 requests
0 failed requests
5th percentile: 2.882801342010498
10th percentile: 2.972694492340088
20th percentile: 3.1524807929992678
30th percentile: 3.337877082824707
40th percentile: 3.528883361816406
50th percentile: 3.7198896408081055
60th percentile: 3.8193203926086428
70th percentile: 3.9187511444091796
80th percentile: 4.214991712570191
90th percentile: 4.708042097091675
95th percentile: 4.954567289352417
99th percentile: 5.151787443161011
mean time: 3.784946155548096
%s, retrying in %s seconds...
Received healthy response to inference request in 2.10058331489563s
Received healthy response to inference request in 2.2537670135498047s
Received healthy response to inference request in 4.230238437652588s
Received healthy response to inference request in 2.467939853668213s
Received healthy response to inference request in 2.8680033683776855s
5 requests
0 failed requests
5th percentile: 2.131220054626465
10th percentile: 2.1618567943572997
20th percentile: 2.2231302738189695
30th percentile: 2.296601581573486
40th percentile: 2.3822707176208495
50th percentile: 2.467939853668213
60th percentile: 2.6279652595520018
70th percentile: 2.787990665435791
80th percentile: 3.1404503822326664
90th percentile: 3.685344409942627
95th percentile: 3.957791423797607
99th percentile: 4.1757490348815915
mean time: 2.784106397628784
Pipeline stage StressChecker completed in 35.51s
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 0.75s
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-llama3-8b-exp2-c_82557_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5605.04s
Shutdown handler de-registered
chaiml-llama3-8b-exp2-c_82557_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama3-8b-exp2-c_82557_v1 status is now torndown due to DeploymentManager action