submission_id: trace2333-fd5wfixed-2e5-_4620_v1
developer_uid: Trace2333
alignment_samples: 13230
alignment_score: 0.5920143542129085
best_of: 8
celo_rating: 1237.4
display_name: trace2333-mistral-trial6_v7
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Trace2333/fd5wfixed_2e5_10035s
latencies: [{'batch_size': 1, 'throughput': 0.9772056907621527, 'latency_mean': 1.0232669305801392, 'latency_p50': 1.0236220359802246, 'latency_p90': 1.1451822519302368}, {'batch_size': 5, 'throughput': 2.546311779149167, 'latency_mean': 1.9527677750587464, 'latency_p50': 1.9527400732040405, 'latency_p90': 2.1742205142974855}, {'batch_size': 10, 'throughput': 3.02214628094895, 'latency_mean': 3.2794783985614777, 'latency_p50': 3.2837798595428467, 'latency_p90': 3.696110391616821}, {'batch_size': 15, 'throughput': 3.1866019618092696, 'latency_mean': 4.648767993450165, 'latency_p50': 4.642852544784546, 'latency_p90': 5.276835894584655}, {'batch_size': 20, 'throughput': 3.2370078294449267, 'latency_mean': 6.068626927137375, 'latency_p50': 6.096522092819214, 'latency_p90': 6.879174757003784}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/fd5wfixed_2e5_
model_name: trace2333-mistral-trial6_v7
model_num_parameters: 8030261248.0
model_repo: Trace2333/fd5wfixed_2e5_10035s
model_size: 8B
num_battles: 13230
num_wins: 6543
propriety_score: 0.7295373665480427
propriety_total_count: 1124.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 3.12
timestamp: 2024-09-07T11:35:51+00:00
us_pacific_date: 2024-09-07
win_ratio: 0.49455782312925173
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 trace2333-fd5wfixed-2e5-4620-v1-mkmlizer
Waiting for job on trace2333-fd5wfixed-2e5-4620-v1-mkmlizer to finish
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ _____ __ __ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ /___/ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ Version: 0.10.1 ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ belonging to: ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ║ ║
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: Downloaded to shared memory in 64.205s
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8naq0dw0, device:0
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: quantized model in 28.880s
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: Processed model Trace2333/fd5wfixed_2e5_10035s in 93.086s
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd5wfixed-2e5-4620-v1
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd5wfixed-2e5-4620-v1/config.json
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd5wfixed-2e5-4620-v1/special_tokens_map.json
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd5wfixed-2e5-4620-v1/tokenizer_config.json
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd5wfixed-2e5-4620-v1/tokenizer.json
trace2333-fd5wfixed-2e5-4620-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd5wfixed-2e5-4620-v1/flywheel_model.0.safetensors
Job trace2333-fd5wfixed-2e5-4620-v1-mkmlizer completed after 230.09s with status: succeeded
Stopping job with name trace2333-fd5wfixed-2e5-4620-v1-mkmlizer
Pipeline stage MKMLizer completed in 231.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-fd5wfixed-2e5-4620-v1
Waiting for inference service trace2333-fd5wfixed-2e5-4620-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
Inference service trace2333-fd5wfixed-2e5-4620-v1 ready after 140.9237198829651s
Pipeline stage MKMLDeployer completed in 141.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.047342300415039s
Received healthy response to inference request in 1.8395955562591553s
Received healthy response to inference request in 1.4936375617980957s
Received healthy response to inference request in 1.5466225147247314s
Received healthy response to inference request in 1.8850200176239014s
5 requests
0 failed requests
5th percentile: 1.5042345523834229
10th percentile: 1.51483154296875
20th percentile: 1.5360255241394043
30th percentile: 1.6052171230316161
40th percentile: 1.7224063396453857
50th percentile: 1.8395955562591553
60th percentile: 1.8577653408050536
70th percentile: 1.8759351253509522
80th percentile: 1.9174844741821289
90th percentile: 1.982413387298584
95th percentile: 2.0148778438568113
99th percentile: 2.0408494091033935
mean time: 1.7624435901641846
Pipeline stage StressChecker completed in 9.78s
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 5.07s
Shutdown handler de-registered
trace2333-fd5wfixed-2e5-_4620_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-fd5wfixed-2e5-4620-v1-profiler
Waiting for inference service trace2333-fd5wfixed-2e5-4620-v1-profiler to be ready
Inference service trace2333-fd5wfixed-2e5-4620-v1-profiler ready after 140.32391929626465s
Pipeline stage MKMLProfilerDeployer completed in 141.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-fd5wfixed-f4e418dbcc9367d5dbaf3f047a43955a-deplowhnt8:/code/chaiverse_profiler_1725709521 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-fd5wfixed-f4e418dbcc9367d5dbaf3f047a43955a-deplowhnt8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725709521 && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725709521/summary.json'
kubectl exec -it trace2333-fd5wfixed-f4e418dbcc9367d5dbaf3f047a43955a-deplowhnt8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725709521/summary.json'
Pipeline stage MKMLProfilerRunner completed in 481.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-fd5wfixed-2e5-4620-v1-profiler is running
Tearing down inference service trace2333-fd5wfixed-2e5-4620-v1-profiler
Service trace2333-fd5wfixed-2e5-4620-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.91s
Shutdown handler de-registered
trace2333-fd5wfixed-2e5-_4620_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics