chaiml-llama-8b-multihe_54063

developer_uid: rirv938
submission_id: chaiml-llama-8b-multihe_54063_v1
model_name: chaiml-llama-8b-multihe_54063_v1
model_group: ChaiML/llama_8b_multihea
status: torndown
timestamp: 2025-02-27T18:12:40+00:00
num_battles: 6285
num_wins: 3337
celo_rating: 1300.51
family_friendly_score: 0.5198
family_friendly_standard_error: 0.007065521353728966
submission_type: basic
model_repo: ChaiML/llama_8b_multihead_204m_preference
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: chaiml-llama-8b-multihe_54063_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_multihead_204m_preference
model_size: 8B
ranking_group: single
us_pacific_date: 2025-02-27
win_ratio: 0.5309466984884647
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': 256, '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': 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-llama-8b-multihe-54063-v1-mkmlizer
Waiting for job on chaiml-llama-8b-multihe-54063-v1-mkmlizer to finish
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-multihe-54063-v1-mkmlizer: Downloaded to shared memory in 35.608s
chaiml-llama-8b-multihe-54063-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpmtl5zko0, device:0
chaiml-llama-8b-multihe-54063-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission nischaydnk-exp27-ftexp1_72507_v1: HTTPConnectionPool(host='nischaydnk-exp27-ftexp1-72507-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama-8b-multihe-54063-v1-mkmlizer: quantized model in 88.051s
chaiml-llama-8b-multihe-54063-v1-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_preference in 123.659s
chaiml-llama-8b-multihe-54063-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multihe-54063-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multihe-54063-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v1
chaiml-llama-8b-multihe-54063-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v1/config.json
chaiml-llama-8b-multihe-54063-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v1/special_tokens_map.json
chaiml-llama-8b-multihe-54063-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v1/tokenizer_config.json
chaiml-llama-8b-multihe-54063-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v1/tokenizer.json
chaiml-llama-8b-multihe-54063-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v1/flywheel_model.0.safetensors
Job chaiml-llama-8b-multihe-54063-v1-mkmlizer completed after 155.31s with status: succeeded
Stopping job with name chaiml-llama-8b-multihe-54063-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.02s
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-multihe-54063-v1
Waiting for inference service chaiml-llama-8b-multihe-54063-v1 to be ready
Failed to get response for submission nischaydnk-exp27-ftexp1_72507_v2: HTTPConnectionPool(host='nischaydnk-exp27-ftexp1-72507-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v1: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v1: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp27-ftexp1_72507_v1: HTTPConnectionPool(host='nischaydnk-exp27-ftexp1-72507-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp27-ftexp1_72507_v1: HTTPConnectionPool(host='nischaydnk-exp27-ftexp1-72507-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama-8b-multihe-54063-v1 ready after 291.36878514289856s
Pipeline stage MKMLDeployer completed in 291.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9449663162231445s
Received healthy response to inference request in 5.0327818393707275s
Received healthy response to inference request in 5.314119577407837s
Received healthy response to inference request in 3.1759426593780518s
Received healthy response to inference request in 3.923565149307251s
5 requests
0 failed requests
5th percentile: 3.3254671573638914
10th percentile: 3.4749916553497315
20th percentile: 3.7740406513214113
30th percentile: 3.9278453826904296
40th percentile: 3.9364058494567873
50th percentile: 3.9449663162231445
60th percentile: 4.380092525482178
70th percentile: 4.815218734741211
80th percentile: 5.089049386978149
90th percentile: 5.2015844821929935
95th percentile: 5.257852029800415
99th percentile: 5.302866067886352
mean time: 4.278275108337402
%s, retrying in %s seconds...
Received healthy response to inference request in 2.929335117340088s
Received healthy response to inference request in 2.439735174179077s
Received healthy response to inference request in 4.403951644897461s
Received healthy response to inference request in 1.9523367881774902s
Received healthy response to inference request in 3.32582426071167s
5 requests
0 failed requests
5th percentile: 2.0498164653778077
10th percentile: 2.147296142578125
20th percentile: 2.3422554969787597
30th percentile: 2.537655162811279
40th percentile: 2.7334951400756835
50th percentile: 2.929335117340088
60th percentile: 3.087930774688721
70th percentile: 3.2465264320373532
80th percentile: 3.5414497375488283
90th percentile: 3.9727006912231446
95th percentile: 4.188326168060303
99th percentile: 4.360826549530029
mean time: 3.0102365970611573
Pipeline stage StressChecker completed in 38.81s
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 0.66s
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 0.66s
Shutdown handler de-registered
chaiml-llama-8b-multihe_54063_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihe-54063-v1-profiler
Waiting for inference service chaiml-llama-8b-multihe-54063-v1-profiler to be ready
Inference service chaiml-llama-8b-multihe-54063-v1-profiler ready after 301.1077995300293s
Pipeline stage MKMLProfilerDeployer completed in 301.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult426af0efedce440ff73186b65b299a23-deploxgthh:/code/chaiverse_profiler_1740680781 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult426af0efedce440ff73186b65b299a23-deploxgthh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1740680781 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1740680781/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihe-54063-v1-profiler is running
Tearing down inference service chaiml-llama-8b-multihe-54063-v1-profiler
Service chaiml-llama-8b-multihe-54063-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.46s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihe-54063-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.80s
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-llama-8b-multihe-54063-v1-profiler
Waiting for inference service chaiml-llama-8b-multihe-54063-v1-profiler to be ready
Inference service chaiml-llama-8b-multihe-54063-v1-profiler ready after 120.48276448249817s
Pipeline stage MKMLProfilerDeployer completed in 120.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult426af0efedce440ff73186b65b299a23-deplo9p5zd:/code/chaiverse_profiler_1740684227 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult426af0efedce440ff73186b65b299a23-deplo9p5zd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1740684227 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1740684227/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihe-54063-v1-profiler is running
Tearing down inference service chaiml-llama-8b-multihe-54063-v1-profiler
Service chaiml-llama-8b-multihe-54063-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.00s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihe-54063-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.29s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihe-54063-v1-profiler
Waiting for inference service chaiml-llama-8b-multihe-54063-v1-profiler to be ready
Inference service chaiml-llama-8b-multihe-54063-v1-profiler ready after 90.36729407310486s
Pipeline stage MKMLProfilerDeployer completed in 90.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult426af0efedce440ff73186b65b299a23-deplolvr4v:/code/chaiverse_profiler_1740687829 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult426af0efedce440ff73186b65b299a23-deplolvr4v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1740687829 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1740687829/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihe-54063-v1-profiler is running
Tearing down inference service chaiml-llama-8b-multihe-54063-v1-profiler
Service chaiml-llama-8b-multihe-54063-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.41s
Shutdown handler de-registered
chaiml-llama-8b-multihe_54063_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multihe_54063_v1 status is now torndown due to DeploymentManager action
ChatRequest
Bot Name
Generation Params
Prompt Formatter
ChatMessage 1
Sender
Message
User Message