submission_id: trace2333-mistral-trial6_v4
developer_uid: Trace2333
alignment_samples: 12694
alignment_score: -0.19649614548746608
best_of: 8
celo_rating: 1254.65
display_name: trace2333-mistral-trial6_v4
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', '</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_trial6
latencies: [{'batch_size': 1, 'throughput': 0.6981860824769747, 'latency_mean': 1.4321943986415864, 'latency_p50': 1.4189603328704834, 'latency_p90': 1.5990623235702515}, {'batch_size': 3, 'throughput': 1.3428560518370949, 'latency_mean': 2.227911977767944, 'latency_p50': 2.2168368101119995, 'latency_p90': 2.5135214567184447}, {'batch_size': 5, 'throughput': 1.5738169491135952, 'latency_mean': 3.1593749809265135, 'latency_p50': 3.186428189277649, 'latency_p90': 3.511012387275696}, {'batch_size': 6, 'throughput': 1.626252383838948, 'latency_mean': 3.665831959247589, 'latency_p50': 3.6943775415420532, 'latency_p90': 4.129699158668518}, {'batch_size': 8, 'throughput': 1.5940607609449275, 'latency_mean': 4.9935013973712925, 'latency_p50': 5.009069085121155, 'latency_p90': 5.642131996154785}, {'batch_size': 10, 'throughput': 1.5541353749145796, 'latency_mean': 6.400211254358291, 'latency_p50': 6.404184699058533, 'latency_p90': 7.340887331962586}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial6
model_name: trace2333-mistral-trial6_v4
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial6
model_size: 13B
num_battles: 12694
num_wins: 6568
propriety_score: 0.738404452690167
propriety_total_count: 1078.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.64
timestamp: 2024-09-06T16:42:19+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5174097999054672
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-trial6-v4-mkmlizer
Waiting for job on trace2333-mistral-trial6-v4-mkmlizer to finish
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
Failed to get response for submission trace2333-mistral-align-_8132_v2: ('http://trace2333-mistral-align-8132-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission trace2333-mistral-align-_8132_v2: ('http://trace2333-mistral-align-8132-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
trace2333-mistral-trial6-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v4-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial6-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial6-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial6-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial6-v4-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial6-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial6-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial6-v4-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial6-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial6-v4-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial6-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v4-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial6-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial6-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial6-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission trace2333-mistral-align-_8132_v2: ('http://trace2333-mistral-align-8132-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
trace2333-mistral-trial6-v4-mkmlizer: Downloaded to shared memory in 28.904s
trace2333-mistral-trial6-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7rov4az8, device:0
trace2333-mistral-trial6-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial6-v4-mkmlizer: quantized model in 36.367s
trace2333-mistral-trial6-v4-mkmlizer: Processed model Trace2333/mistral_trial6 in 65.271s
trace2333-mistral-trial6-v4-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v4
trace2333-mistral-trial6-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v4/config.json
trace2333-mistral-trial6-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v4/special_tokens_map.json
trace2333-mistral-trial6-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v4/tokenizer.json
trace2333-mistral-trial6-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v4/flywheel_model.0.safetensors
trace2333-mistral-trial6-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 49.74it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 83.74it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:03, 83.81it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:03, 84.13it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 92.22it/s]
Loading 0:  19%|█▊        | 68/363 [00:01<00:12, 24.23it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:10, 28.70it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 36.83it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.16it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 48.25it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 52.64it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:04, 59.69it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:03, 65.05it/s]
Loading 0:  38%|███▊      | 139/363 [00:02<00:03, 68.22it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:10, 20.78it/s]
Loading 0:  42%|████▏     | 153/363 [00:03<00:08, 24.26it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:07, 28.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 36.32it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 43.31it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 53.36it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 58.02it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 63.34it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 65.48it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:07, 19.83it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.47it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 31.44it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 37.60it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 42.53it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 49.06it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 55.51it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 58.93it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 64.52it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.70it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.14it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.03it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.65it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 47.43it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 52.96it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 57.22it/s]
                                                            

Job trace2333-mistral-trial6-v4-mkmlizer completed after 84.08s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v4-mkmlizer
Pipeline stage MKMLizer completed in 85.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial6-v4
Waiting for inference service trace2333-mistral-trial6-v4 to be ready
Retrying (%r) after connection broken by '%r': %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
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 trace2333-mistral-trial6-v4 ready after 212.12212228775024s
Pipeline stage MKMLDeployer completed in 212.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.550504207611084s
Received healthy response to inference request in 1.9360013008117676s
Received healthy response to inference request in 2.069317579269409s
Received healthy response to inference request in 1.8405911922454834s
Received healthy response to inference request in 1.9917566776275635s
5 requests
0 failed requests
5th percentile: 1.8596732139587402
10th percentile: 1.878755235671997
20th percentile: 1.9169192790985108
30th percentile: 1.9471523761749268
40th percentile: 1.9694545269012451
50th percentile: 1.9917566776275635
60th percentile: 2.0227810382843017
70th percentile: 2.05380539894104
80th percentile: 2.165554904937744
90th percentile: 2.3580295562744142
95th percentile: 2.454266881942749
99th percentile: 2.531256742477417
mean time: 2.0776341915130616
Pipeline stage StressChecker completed in 11.16s
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 5.21s
Shutdown handler de-registered
trace2333-mistral-trial6_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trial6-v4-profiler
Waiting for inference service trace2333-mistral-trial6-v4-profiler to be ready
Inference service trace2333-mistral-trial6-v4-profiler ready after 150.4709391593933s
Pipeline stage MKMLProfilerDeployer completed in 150.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial6-v4-profiler-predictor-00001-deplo56r7k:/code/chaiverse_profiler_1725641457 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial6-v4-profiler-predictor-00001-deplo56r7k --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725641457 && 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_1725641457/summary.json'
kubectl exec -it trace2333-mistral-trial6-v4-profiler-predictor-00001-deplo56r7k --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725641457/summary.json'
Pipeline stage MKMLProfilerRunner completed in 945.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v4-profiler is running
Tearing down inference service trace2333-mistral-trial6-v4-profiler
Service trace2333-mistral-trial6-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.83s
Shutdown handler de-registered
trace2333-mistral-trial6_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics