submission_id: zonemercy-virgo-edit-v4-1e5_v4
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1246.36
display_name: 0919v1-2
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: zonemercy/Virgo-Edit-v4-1e5
latencies: [{'batch_size': 1, 'throughput': 0.616181252130264, 'latency_mean': 1.6228349637985229, 'latency_p50': 1.6273539066314697, 'latency_p90': 1.7940728425979615}, {'batch_size': 3, 'throughput': 1.0795270443208294, 'latency_mean': 2.7689327359199525, 'latency_p50': 2.7590993642807007, 'latency_p90': 3.1212170362472533}, {'batch_size': 5, 'throughput': 1.2150485380691909, 'latency_mean': 4.094506981372834, 'latency_p50': 4.102929711341858, 'latency_p90': 4.695793581008911}, {'batch_size': 6, 'throughput': 1.2367325140617522, 'latency_mean': 4.833636136054992, 'latency_p50': 4.813598394393921, 'latency_p90': 5.494533109664917}, {'batch_size': 8, 'throughput': 1.2043626272428232, 'latency_mean': 6.611300699710846, 'latency_p50': 6.6037068367004395, 'latency_p90': 7.514123916625977}, {'batch_size': 10, 'throughput': 1.191624470146956, 'latency_mean': 8.350603787899017, 'latency_p50': 8.36189329624176, 'latency_p90': 9.424781250953673}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Virgo-Edit-v4-
model_name: 0919v1-2
model_num_parameters: 12772070400.0
model_repo: zonemercy/Virgo-Edit-v4-1e5
model_size: 13B
num_battles: 14596
num_wins: 7257
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.19
timestamp: 2024-09-19T14:17:10+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.49719101123595505
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 zonemercy-virgo-edit-v4-1e5-v4-mkmlizer
Waiting for job on zonemercy-virgo-edit-v4-1e5-v4-mkmlizer to finish
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ _____ __ __ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ /___/ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ https://mk1.ai ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ belonging to: ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ Chai Research Corp. ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ║ ║
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: Downloaded to shared memory in 75.350s
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqx7ed263, device:0
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: quantized model in 40.680s
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: Processed model zonemercy/Virgo-Edit-v4-1e5 in 116.030s
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-virgo-edit-v4-1e5-v4
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v4-1e5-v4/config.json
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v4-1e5-v4/special_tokens_map.json
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v4-1e5-v4/tokenizer_config.json
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v4-1e5-v4/tokenizer.json
zonemercy-virgo-edit-v4-1e5-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-virgo-edit-v4-1e5-v4/flywheel_model.0.safetensors
Job zonemercy-virgo-edit-v4-1e5-v4-mkmlizer completed after 146.23s with status: succeeded
Stopping job with name zonemercy-virgo-edit-v4-1e5-v4-mkmlizer
Pipeline stage MKMLizer completed in 147.88s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-virgo-edit-v4-1e5-v4
Waiting for inference service zonemercy-virgo-edit-v4-1e5-v4 to be ready
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
Inference service zonemercy-virgo-edit-v4-1e5-v4 ready after 271.91709423065186s
Pipeline stage MKMLDeployer completed in 272.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.997140645980835s
Received healthy response to inference request in 2.056926727294922s
Received healthy response to inference request in 1.8320870399475098s
Received healthy response to inference request in 1.767385721206665s
Received healthy response to inference request in 1.936187744140625s
5 requests
0 failed requests
5th percentile: 1.780325984954834
10th percentile: 1.7932662487030029
20th percentile: 1.8191467761993407
30th percentile: 1.8529071807861328
40th percentile: 1.894547462463379
50th percentile: 1.936187744140625
60th percentile: 1.960568904876709
70th percentile: 1.984950065612793
80th percentile: 2.009097862243652
90th percentile: 2.033012294769287
95th percentile: 2.0449695110321047
99th percentile: 2.0545352840423585
mean time: 1.9179455757141113
Pipeline stage StressChecker completed in 10.39s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.94s
Shutdown handler de-registered
zonemercy-virgo-edit-v4-1e5_v4 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 0.13s
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 zonemercy-virgo-edit-v4-1e5-v4-profiler
Waiting for inference service zonemercy-virgo-edit-v4-1e5-v4-profiler to be ready
Inference service zonemercy-virgo-edit-v4-1e5-v4-profiler ready after 200.45343732833862s
Pipeline stage MKMLProfilerDeployer completed in 200.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-virgo-edit6b2aac0489b7ac502a82b054d7b5b0f4-deplo4vxzm:/code/chaiverse_profiler_1726756130 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-virgo-edit6b2aac0489b7ac502a82b054d7b5b0f4-deplo4vxzm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726756130 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726756130/summary.json'
kubectl exec -it zonemercy-virgo-edit6b2aac0489b7ac502a82b054d7b5b0f4-deplo4vxzm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726756130/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1177.49s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-virgo-edit-v4-1e5-v4-profiler is running
Tearing down inference service zonemercy-virgo-edit-v4-1e5-v4-profiler
Service zonemercy-virgo-edit-v4-1e5-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.12s
Shutdown handler de-registered
zonemercy-virgo-edit-v4-1e5_v4 status is now inactive due to auto deactivation removed underperforming models
zonemercy-virgo-edit-v4-1e5_v4 status is now torndown due to DeploymentManager action