submission_id: trace2333-mistral-trial3_v1
developer_uid: Trace2333
alignment_samples: 11945
alignment_score: -0.8756155967355788
best_of: 8
celo_rating: 1243.73
display_name: trace2333-mistral-trial3_v1
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': 0.9, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Trace2333/mistral_trial3
latencies: [{'batch_size': 1, 'throughput': 0.6896962299135733, 'latency_mean': 1.449828909635544, 'latency_p50': 1.4443439245224, 'latency_p90': 1.6083349704742431}, {'batch_size': 3, 'throughput': 1.2965185416124336, 'latency_mean': 2.31106981754303, 'latency_p50': 2.3076701164245605, 'latency_p90': 2.575659465789795}, {'batch_size': 5, 'throughput': 1.5338895499788192, 'latency_mean': 3.2456958079338074, 'latency_p50': 3.2399702072143555, 'latency_p90': 3.6623866319656373}, {'batch_size': 6, 'throughput': 1.5523999303521134, 'latency_mean': 3.8380896401405336, 'latency_p50': 3.856291174888611, 'latency_p90': 4.332860231399536}, {'batch_size': 8, 'throughput': 1.5683780056394472, 'latency_mean': 5.078086681365967, 'latency_p50': 5.120054006576538, 'latency_p90': 5.753134870529175}, {'batch_size': 10, 'throughput': 1.4835269176776869, 'latency_mean': 6.706975209712982, 'latency_p50': 6.7273043394088745, 'latency_p90': 7.6859657049179075}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial3
model_name: trace2333-mistral-trial3_v1
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial3
model_size: 13B
num_battles: 11945
num_wins: 6049
propriety_score: 0.7553191489361702
propriety_total_count: 1034.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.56
timestamp: 2024-09-05T11:08:08+00:00
us_pacific_date: 2024-09-05
win_ratio: 0.5064043532858937
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-mistral-trial3-v1-mkmlizer
Waiting for job on trace2333-mistral-trial3-v1-mkmlizer to finish
trace2333-mistral-trial3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial3-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial3-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial3-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial3-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial3-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial3-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial3-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial3-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
trace2333-mistral-trial3-v1-mkmlizer: Downloaded to shared memory in 51.562s
trace2333-mistral-trial3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps4_6shp9, device:0
trace2333-mistral-trial3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial3-v1-mkmlizer: quantized model in 35.842s
trace2333-mistral-trial3-v1-mkmlizer: Processed model Trace2333/mistral_trial3 in 87.405s
trace2333-mistral-trial3-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial3-v1
trace2333-mistral-trial3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trial3-v1/tokenizer_config.json
trace2333-mistral-trial3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial3-v1/tokenizer.json
trace2333-mistral-trial3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial3-v1/flywheel_model.0.safetensors
trace2333-mistral-trial3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 48.85it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 63.90it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 71.31it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 71.66it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 73.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 73.07it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:15, 19.91it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:11, 26.16it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.22it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 40.87it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 48.03it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 53.65it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 60.78it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 67.10it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 69.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 21.33it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 27.68it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.12it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:04, 39.71it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:03, 46.74it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 52.19it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 59.03it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 65.59it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 69.76it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:06, 21.02it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 27.12it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.14it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 43.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 48.74it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 55.37it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 62.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 68.35it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:00, 68.36it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 20.81it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.89it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.80it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.54it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 47.31it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 54.57it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 58.87it/s]
                                                            

Job trace2333-mistral-trial3-v1-mkmlizer completed after 106.18s with status: succeeded
Stopping job with name trace2333-mistral-trial3-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial3-v1
Waiting for inference service trace2333-mistral-trial3-v1 to be ready
Inference service trace2333-mistral-trial3-v1 ready after 140.89016795158386s
Pipeline stage MKMLDeployer completed in 141.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6475324630737305s
Received healthy response to inference request in 1.7239527702331543s
Received healthy response to inference request in 2.1986396312713623s
Received healthy response to inference request in 1.6713802814483643s
Received healthy response to inference request in 1.8588135242462158s
5 requests
0 failed requests
5th percentile: 1.6818947792053223
10th percentile: 1.6924092769622803
20th percentile: 1.7134382724761963
30th percentile: 1.7509249210357667
40th percentile: 1.8048692226409913
50th percentile: 1.8588135242462158
60th percentile: 1.9947439670562743
70th percentile: 2.130674409866333
80th percentile: 2.488418197631836
90th percentile: 3.0679753303527835
95th percentile: 3.3577538967132567
99th percentile: 3.5895767498016355
mean time: 2.2200637340545653
Pipeline stage StressChecker completed in 12.18s
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 6.11s
Shutdown handler de-registered
trace2333-mistral-trial3_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trial3-v1-profiler
Waiting for inference service trace2333-mistral-trial3-v1-profiler to be ready
Inference service trace2333-mistral-trial3-v1-profiler ready after 150.40074253082275s
Pipeline stage MKMLProfilerDeployer completed in 150.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial3-v1-profiler-predictor-00001-deplo469vc:/code/chaiverse_profiler_1725534948 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial3-v1-profiler-predictor-00001-deplo469vc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725534948 && 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_1725534948/summary.json'
kubectl exec -it trace2333-mistral-trial3-v1-profiler-predictor-00001-deplo469vc --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725534948/summary.json'
Pipeline stage MKMLProfilerRunner completed in 971.60s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial3-v1-profiler is running
Tearing down inference service trace2333-mistral-trial3-v1-profiler
Service trace2333-mistral-trial3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.76s
Shutdown handler de-registered
trace2333-mistral-trial3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics