alexdaoud-trainer-bagir-_3219

developer_uid: chai_backend_admin
submission_id: alexdaoud-trainer-bagir-_3219_v1
model_name: alexdaoud-trainer-bagir-_3219_v1
model_group: alexdaoud/trainer_bagir_
status: inactive
timestamp: 2024-12-13T00:37:07+00:00
num_battles: 13558
num_wins: 6901
celo_rating: 1263.77
family_friendly_score: 0.5796
family_friendly_standard_error: 0.006980885903665809
submission_type: basic
model_repo: alexdaoud/trainer_bagir_2024-12-11-checkpoint-24
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: alexdaoud-trainer-bagir-_3219_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: alexdaoud/trainer_bagir_2024-12-11-checkpoint-24
model_size: 8B
ranking_group: single
us_pacific_date: 2024-12-12
win_ratio: 0.5089983773417909
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': 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 alexdaoud-trainer-bagir-3219-v1-mkmlizer
Waiting for job on alexdaoud-trainer-bagir-3219-v1-mkmlizer to finish
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║     _____            __           __                                ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║       /___/                                                         ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  https://mk1.ai                                                     ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  belonging to:                                                      ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  Chai Research Corp.                                                ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-3219-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexdaoud-trainer-bagir-3219-v1-mkmlizer: Downloaded to shared memory in 30.824s
alexdaoud-trainer-bagir-3219-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpzl_1i9d4, device:0
alexdaoud-trainer-bagir-3219-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
alexdaoud-trainer-bagir-3219-v1-mkmlizer: quantized model in 85.806s
alexdaoud-trainer-bagir-3219-v1-mkmlizer: Processed model alexdaoud/trainer_bagir_2024-12-11-checkpoint-24 in 116.630s
alexdaoud-trainer-bagir-3219-v1-mkmlizer: creating bucket guanaco-mkml-models
alexdaoud-trainer-bagir-3219-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexdaoud-trainer-bagir-3219-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexdaoud-trainer-bagir-3219-v1
alexdaoud-trainer-bagir-3219-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-3219-v1/config.json
alexdaoud-trainer-bagir-3219-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-3219-v1/special_tokens_map.json
alexdaoud-trainer-bagir-3219-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-3219-v1/tokenizer_config.json
alexdaoud-trainer-bagir-3219-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-3219-v1/tokenizer.json
Job alexdaoud-trainer-bagir-3219-v1-mkmlizer completed after 149.71s with status: succeeded
Stopping job with name alexdaoud-trainer-bagir-3219-v1-mkmlizer
Pipeline stage MKMLizer completed in 150.24s
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 alexdaoud-trainer-bagir-3219-v1
Waiting for inference service alexdaoud-trainer-bagir-3219-v1 to be ready
Inference service alexdaoud-trainer-bagir-3219-v1 ready after 191.1860752105713s
Pipeline stage MKMLDeployer completed in 191.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.934136867523193s
Received healthy response to inference request in 3.1035966873168945s
Received healthy response to inference request in 3.1596171855926514s
Received healthy response to inference request in 2.5104992389678955s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 4.924349784851074s
5 requests
0 failed requests
5th percentile: 2.629118728637695
10th percentile: 2.747738218307495
20th percentile: 2.984977197647095
30th percentile: 3.114800786972046
40th percentile: 3.1372089862823485
50th percentile: 3.1596171855926514
60th percentile: 3.8655102252960205
70th percentile: 4.57140326499939
80th percentile: 5.126307201385498
90th percentile: 5.530222034454345
95th percentile: 5.732179450988769
99th percentile: 5.893745384216309
mean time: 3.926439952850342
%s, retrying in %s seconds...
Received healthy response to inference request in 3.5029592514038086s
Received healthy response to inference request in 2.2207322120666504s
Received healthy response to inference request in 3.5334088802337646s
Received healthy response to inference request in 2.3119637966156006s
Received healthy response to inference request in 3.9742980003356934s
5 requests
0 failed requests
5th percentile: 2.2389785289764403
10th percentile: 2.2572248458862303
20th percentile: 2.2937174797058106
30th percentile: 2.5501628875732423
40th percentile: 3.0265610694885257
50th percentile: 3.5029592514038086
60th percentile: 3.515139102935791
70th percentile: 3.5273189544677734
80th percentile: 3.6215867042541503
90th percentile: 3.797942352294922
95th percentile: 3.8861201763153077
99th percentile: 3.9566624355316162
mean time: 3.1086724281311033
Pipeline stage StressChecker completed in 37.81s
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 2.46s
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 2.23s
Shutdown handler de-registered
alexdaoud-trainer-bagir-_3219_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 0.12s
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 alexdaoud-trainer-bagir-3219-v1-profiler
Waiting for inference service alexdaoud-trainer-bagir-3219-v1-profiler to be ready
Inference service alexdaoud-trainer-bagir-3219-v1-profiler ready after 200.48700833320618s
Pipeline stage MKMLProfilerDeployer completed in 201.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplottfvr:/code/chaiverse_profiler_1734050846 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplottfvr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734050846 && 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_1734050846/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplottfvr:/code/chaiverse_profiler_1734053614 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplottfvr:/code/chaiverse_profiler_1734053615 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplottfvr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734053615 && 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_1734053615/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-3219-v1-profiler is running
Tearing down inference service alexdaoud-trainer-bagir-3219-v1-profiler
Service alexdaoud-trainer-bagir-3219-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-3219-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.42s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexdaoud-trainer-bagir-3219-v1-profiler
Waiting for inference service alexdaoud-trainer-bagir-3219-v1-profiler to be ready
Inference service alexdaoud-trainer-bagir-3219-v1-profiler ready after 140.3464286327362s
Pipeline stage MKMLProfilerDeployer completed in 140.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplo6hjnb:/code/chaiverse_profiler_1734054415 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplo6hjnb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734054415 && 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_1734054415/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplo6hjnb:/code/chaiverse_profiler_1734057191 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplo6hjnb:/code/chaiverse_profiler_1734057192 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplo6hjnb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734057192 && 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_1734057192/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-3219-v1-profiler is running
Tearing down inference service alexdaoud-trainer-bagir-3219-v1-profiler
Service alexdaoud-trainer-bagir-3219-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.19s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-3219-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.31s
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 alexdaoud-trainer-bagir-3219-v1-profiler
Waiting for inference service alexdaoud-trainer-bagir-3219-v1-profiler to be ready
Inference service alexdaoud-trainer-bagir-3219-v1-profiler ready after 60.15073251724243s
Pipeline stage MKMLProfilerDeployer completed in 60.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplojv6s4:/code/chaiverse_profiler_1734057957 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplojv6s4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734057957 && 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_1734057957/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplojv6s4:/code/chaiverse_profiler_1734060734 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplojv6s4:/code/chaiverse_profiler_1734060734 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-ba63ea401b23c5dd3349b83385ec376e4a-deplojv6s4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734060734 && 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_1734060734/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-3219-v1-profiler is running
Tearing down inference service alexdaoud-trainer-bagir-3219-v1-profiler
Service alexdaoud-trainer-bagir-3219-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.33s
Shutdown handler de-registered
alexdaoud-trainer-bagir-_3219_v1 status is now inactive due to auto deactivation removed underperforming models