submission_id: cycy233-l3-bp-v6-c2_v1
developer_uid: shiroe40
alignment_samples: 13467
alignment_score: -0.5649177461062312
best_of: 16
celo_rating: 1248.41
display_name: auto
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/L3-bp-v6-c2
latencies: [{'batch_size': 1, 'throughput': 0.9103939049686501, 'latency_mean': 1.0983316969871522, 'latency_p50': 1.0882246494293213, 'latency_p90': 1.2301892518997193}, {'batch_size': 4, 'throughput': 1.7743028066454525, 'latency_mean': 2.2466555988788603, 'latency_p50': 2.2409284114837646, 'latency_p90': 2.520865035057068}, {'batch_size': 5, 'throughput': 1.8717791785893478, 'latency_mean': 2.658571048974991, 'latency_p50': 2.6563538312911987, 'latency_p90': 2.9991030216217043}, {'batch_size': 8, 'throughput': 1.9833187462316602, 'latency_mean': 4.0045657885074615, 'latency_p50': 3.989296317100525, 'latency_p90': 4.500141716003418}, {'batch_size': 10, 'throughput': 2.0231347356332474, 'latency_mean': 4.8937017333507535, 'latency_p50': 4.9443405866622925, 'latency_p90': 5.61640920639038}, {'batch_size': 12, 'throughput': 2.030253055435844, 'latency_mean': 5.831160287857056, 'latency_p50': 5.889148712158203, 'latency_p90': 6.704883861541748}, {'batch_size': 15, 'throughput': 2.0046468734116316, 'latency_mean': 7.3454375648498536, 'latency_p50': 7.482760310173035, 'latency_p90': 8.193301153182983}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-bp-v6-c2
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-bp-v6-c2
model_size: 8B
num_battles: 13467
num_wins: 6853
propriety_score: 0.7181146025878004
propriety_total_count: 1082.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.98
timestamp: 2024-09-05T03:16:46+00:00
us_pacific_date: 2024-09-04
win_ratio: 0.5088735427340907
Download Preference Data
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 cycy233-l3-bp-v6-c2-v1-mkmlizer
Waiting for job on cycy233-l3-bp-v6-c2-v1-mkmlizer to finish
cycy233-l3-bp-v6-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v6-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
cycy233-l3-bp-v6-c2-v1-mkmlizer: Downloaded to shared memory in 33.986s
cycy233-l3-bp-v6-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjbq2lo5v, device:0
cycy233-l3-bp-v6-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bp-v6-c2-v1-mkmlizer: quantized model in 26.033s
cycy233-l3-bp-v6-c2-v1-mkmlizer: Processed model cycy233/L3-bp-v6-c2 in 60.019s
cycy233-l3-bp-v6-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bp-v6-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bp-v6-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bp-v6-c2-v1
cycy233-l3-bp-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c2-v1/special_tokens_map.json
cycy233-l3-bp-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c2-v1/config.json
cycy233-l3-bp-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c2-v1/tokenizer_config.json
cycy233-l3-bp-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bp-v6-c2-v1/tokenizer.json
Job cycy233-l3-bp-v6-c2-v1-mkmlizer completed after 85.62s with status: succeeded
Stopping job with name cycy233-l3-bp-v6-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.57s
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 cycy233-l3-bp-v6-c2-v1
Waiting for inference service cycy233-l3-bp-v6-c2-v1 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
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 cycy233-l3-bp-v6-c2-v1 ready after 150.90226197242737s
Pipeline stage MKMLDeployer completed in 151.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9654779434204102s
Received healthy response to inference request in 1.753394365310669s
Received healthy response to inference request in 2.930957317352295s
Received healthy response to inference request in 1.8565483093261719s
Received healthy response to inference request in 1.7227354049682617s
5 requests
0 failed requests
5th percentile: 1.728867197036743
10th percentile: 1.7349989891052247
20th percentile: 1.7472625732421876
30th percentile: 1.7740251541137695
40th percentile: 1.8152867317199708
50th percentile: 1.8565483093261719
60th percentile: 1.900120162963867
70th percentile: 1.9436920166015625
80th percentile: 2.1585738182067873
90th percentile: 2.544765567779541
95th percentile: 2.737861442565918
99th percentile: 2.8923381423950194
mean time: 2.0458226680755613
Pipeline stage StressChecker completed in 11.26s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 8.69s
Shutdown handler de-registered
cycy233-l3-bp-v6-c2_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-bp-v6-c2-v1-profiler
Waiting for inference service cycy233-l3-bp-v6-c2-v1-profiler to be ready
Inference service cycy233-l3-bp-v6-c2-v1-profiler ready after 150.35828566551208s
Pipeline stage MKMLProfilerDeployer completed in 150.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-bp-v6-c2-v1-profiler-predictor-00001-deploymentjkm7f:/code/chaiverse_profiler_1725506656 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bp-v6-c2-v1-profiler-predictor-00001-deploymentjkm7f --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725506656 && python profiles.py profile --best_of_n 16 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725506656/summary.json'
kubectl exec -it cycy233-l3-bp-v6-c2-v1-profiler-predictor-00001-deploymentjkm7f --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725506656/summary.json'
Pipeline stage MKMLProfilerRunner completed in 843.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-bp-v6-c2-v1-profiler is running
Tearing down inference service cycy233-l3-bp-v6-c2-v1-profiler
Service cycy233-l3-bp-v6-c2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.56s
Shutdown handler de-registered
cycy233-l3-bp-v6-c2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics