submission_id: trace2333-mistral-trial2_v1
developer_uid: Trace2333
alignment_samples: 11943
alignment_score: -0.3825336622576747
best_of: 8
celo_rating: 1243.92
display_name: trace2333-mistral-trial2_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': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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_trial2
latencies: [{'batch_size': 1, 'throughput': 0.6904116901739746, 'latency_mean': 1.448337435722351, 'latency_p50': 1.4566776752471924, 'latency_p90': 1.6120919227600097}, {'batch_size': 3, 'throughput': 1.3238391696366472, 'latency_mean': 2.2608130311965944, 'latency_p50': 2.2697041034698486, 'latency_p90': 2.5141143560409547}, {'batch_size': 5, 'throughput': 1.5459594996703658, 'latency_mean': 3.214732141494751, 'latency_p50': 3.20922315120697, 'latency_p90': 3.6223906755447386}, {'batch_size': 6, 'throughput': 1.5904910967147845, 'latency_mean': 3.7516858088970184, 'latency_p50': 3.7712888717651367, 'latency_p90': 4.176148295402527}, {'batch_size': 8, 'throughput': 1.5883413981827708, 'latency_mean': 5.005676721334457, 'latency_p50': 5.050478219985962, 'latency_p90': 5.651588058471679}, {'batch_size': 10, 'throughput': 1.5290200570362615, 'latency_mean': 6.496292276382446, 'latency_p50': 6.49753999710083, 'latency_p90': 7.3910136222839355}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial2
model_name: trace2333-mistral-trial2_v1
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial2
model_size: 13B
num_battles: 11943
num_wins: 6001
propriety_score: 0.7210884353741497
propriety_total_count: 1029.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.6
timestamp: 2024-09-05T03:26:36+00:00
us_pacific_date: 2024-09-04
win_ratio: 0.5024700661475341
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-trial2-v1-mkmlizer
Waiting for job on trace2333-mistral-trial2-v1-mkmlizer to finish
trace2333-mistral-trial2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial2-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial2-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial2-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial2-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial2-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial2-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial2-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial2-v1-mkmlizer: Downloaded to shared memory in 49.263s
trace2333-mistral-trial2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4rc5q33b, device:0
trace2333-mistral-trial2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-mistral-trial2-v1-mkmlizer: quantized model in 36.480s
trace2333-mistral-trial2-v1-mkmlizer: Processed model Trace2333/mistral_trial2 in 85.743s
trace2333-mistral-trial2-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial2-v1
trace2333-mistral-trial2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial2-v1/config.json
trace2333-mistral-trial2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial2-v1/special_tokens_map.json
trace2333-mistral-trial2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial2-v1/flywheel_model.0.safetensors
trace2333-mistral-trial2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.39it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 61.99it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 69.63it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 69.32it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 67.17it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 68.74it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:15, 19.78it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.84it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.19it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 40.77it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 45.91it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 49.07it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 53.28it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 59.91it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 65.75it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:10, 20.16it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 26.18it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.09it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:04, 39.63it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 43.71it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 49.37it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 54.12it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 58.79it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 60.33it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.22it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 26.21it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 31.90it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 38.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 44.70it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 51.36it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 56.81it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 58.94it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 64.46it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.36it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 25.77it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 32.27it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.52it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 44.77it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 49.70it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 56.04it/s]
                                                            

Job trace2333-mistral-trial2-v1-mkmlizer completed after 106.02s with status: succeeded
Stopping job with name trace2333-mistral-trial2-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.74s
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 trace2333-mistral-trial2-v1
Waiting for inference service trace2333-mistral-trial2-v1 to be ready
admin requested tearing down of nousresearch-meta-llama_4939_v19
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=%s
Shutdown handler de-registered
Inference service trace2333-mistral-trial2-v1 ready after 150.76700973510742s
Pipeline stage MKMLDeployer completed in 151.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6716341972351074s
Received healthy response to inference request in 1.434325933456421s
Received healthy response to inference request in 2.0886194705963135s
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
Received healthy response to inference request in 2.2778704166412354s
Received healthy response to inference request in 1.170478105545044s
5 requests
0 failed requests
5th percentile: 1.2232476711273192
10th percentile: 1.2760172367095948
20th percentile: 1.3815563678741456
30th percentile: 1.5651846408843995
40th percentile: 1.8269020557403566
50th percentile: 2.0886194705963135
60th percentile: 2.1643198490142823
70th percentile: 2.240020227432251
80th percentile: 2.3566231727600098
90th percentile: 2.5141286849975586
95th percentile: 2.592881441116333
99th percentile: 2.6558836460113526
mean time: 1.9285856246948243
Pipeline stage StressChecker completed in 10.46s
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 8.47s
Shutdown handler de-registered
trace2333-mistral-trial2_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trial2-v1-profiler
Waiting for inference service trace2333-mistral-trial2-v1-profiler to be ready
Inference service trace2333-mistral-trial2-v1-profiler ready after 140.360995054245s
Pipeline stage MKMLProfilerDeployer completed in 140.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial2-v1-profiler-predictor-00001-deplozxc85:/code/chaiverse_profiler_1725507249 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial2-v1-profiler-predictor-00001-deplozxc85 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725507249 && 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_1725507249/summary.json'
kubectl exec -it trace2333-mistral-trial2-v1-profiler-predictor-00001-deplozxc85 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725507249/summary.json'
Pipeline stage MKMLProfilerRunner completed in 957.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial2-v1-profiler is running
Tearing down inference service trace2333-mistral-trial2-v1-profiler
Service trace2333-mistral-trial2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.82s
Shutdown handler de-registered
trace2333-mistral-trial2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics