trace2333-mistral-trail11

submission_id: trace2333-mistral-trail11_v1

developer_uid: Trace2333

best_of: 8

celo_rating: 1230.28

display_name: trace2333-mistral-trail11_v1

family_friendly_score: 0.0

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/mistral_trail11

latencies: [{'batch_size': 1, 'throughput': 0.6956250056762137, 'latency_mean': 1.4374959409236907, 'latency_p50': 1.4316385984420776, 'latency_p90': 1.5905717134475708}, {'batch_size': 3, 'throughput': 1.3190874871998584, 'latency_mean': 2.265435138940811, 'latency_p50': 2.2513598203659058, 'latency_p90': 2.5360119104385377}, {'batch_size': 5, 'throughput': 1.5639278278216846, 'latency_mean': 3.1831467163562777, 'latency_p50': 3.170362949371338, 'latency_p90': 3.583970832824707}, {'batch_size': 6, 'throughput': 1.5964464687674413, 'latency_mean': 3.738384635448456, 'latency_p50': 3.761726498603821, 'latency_p90': 4.19273612499237}, {'batch_size': 8, 'throughput': 1.5913291609764364, 'latency_mean': 4.997027246952057, 'latency_p50': 4.9829185009002686, 'latency_p90': 5.7513188123703}, {'batch_size': 10, 'throughput': 1.5136667032954196, 'latency_mean': 6.562461552619934, 'latency_p50': 6.646388292312622, 'latency_p90': 7.415664172172546}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Trace2333/mistral_trail1

model_name: trace2333-mistral-trail11_v1

model_num_parameters: 12772070400.0

model_repo: Trace2333/mistral_trail11

model_size: 13B

num_battles: 9978

num_wins: 4794

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.6

timestamp: 2024-09-12T02:56:18+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.48045700541190617

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-trail11-v1-mkmlizer
Waiting for job on trace2333-mistral-trail11-v1-mkmlizer to finish
trace2333-mistral-trail11-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trail11-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trail11-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trail11-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trail11-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trail11-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trail11-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail11-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trail11-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trail11-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trail11-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail11-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trail11-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trail11-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail11-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trail11-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trail11-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trail11-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail11-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trail11-v1-mkmlizer: Downloaded to shared memory in 46.515s
trace2333-mistral-trail11-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0wu44qb1, device:0
trace2333-mistral-trail11-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trail11-v1-mkmlizer: quantized model in 36.849s
trace2333-mistral-trail11-v1-mkmlizer: Processed model Trace2333/mistral_trail11 in 83.364s
trace2333-mistral-trail11-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trail11-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trail11-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trail11-v1
trace2333-mistral-trail11-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trail11-v1/config.json
trace2333-mistral-trail11-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trail11-v1/special_tokens_map.json
trace2333-mistral-trail11-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trail11-v1/tokenizer_config.json
trace2333-mistral-trail11-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trail11-v1/tokenizer.json
trace2333-mistral-trail11-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trail11-v1/flywheel_model.0.safetensors
trace2333-mistral-trail11-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 45.72it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:06, 56.04it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:05, 60.39it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 67.90it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 72.19it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 69.47it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:15, 19.31it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.18it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.04it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 40.04it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 44.19it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 51.62it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 56.42it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:04, 56.98it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 62.40it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 20.00it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 24.93it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.36it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 38.77it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 45.52it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 50.83it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 53.96it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 58.30it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 63.76it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.36it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.53it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.04it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 39.58it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 45.86it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 52.38it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 57.66it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 60.77it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 65.47it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.28it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.00it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 31.77it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.15it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 44.21it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 51.65it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 57.68it/s]
                                                            
Job trace2333-mistral-trail11-v1-mkmlizer completed after 105.53s with status: succeeded
Stopping job with name trace2333-mistral-trail11-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.57s
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 trace2333-mistral-trail11-v1
Waiting for inference service trace2333-mistral-trail11-v1 to be ready
Inference service trace2333-mistral-trail11-v1 ready after 170.40427827835083s
Pipeline stage MKMLDeployer completed in 170.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 15.457670211791992s
Received healthy response to inference request in 2.892667293548584s
Received healthy response to inference request in 1.9258286952972412s
Received healthy response to inference request in 2.359278440475464s
Received healthy response to inference request in 1.9278039932250977s
5 requests
0 failed requests
5th percentile: 1.9262237548828125
10th percentile: 1.9266188144683838
20th percentile: 1.9274089336395264
30th percentile: 2.014098882675171
40th percentile: 2.1866886615753174
50th percentile: 2.359278440475464
60th percentile: 2.572633981704712
70th percentile: 2.78598952293396
80th percentile: 5.405667877197268
90th percentile: 10.43166904449463
95th percentile: 12.94466962814331
99th percentile: 14.955070095062256
mean time: 4.912649726867675
Pipeline stage StressChecker completed in 25.17s
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 8.61s
Shutdown handler de-registered
trace2333-mistral-trail11_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 0.12s
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-trail11-v1-profiler
Waiting for inference service trace2333-mistral-trail11-v1-profiler to be ready
Inference service trace2333-mistral-trail11-v1-profiler ready after 170.51791834831238s
Pipeline stage MKMLProfilerDeployer completed in 172.30s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-tr6e3f4d8d49f51af6823f5373d37b03b5-deplo7n4z5:/code/chaiverse_profiler_1726110321 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-tr6e3f4d8d49f51af6823f5373d37b03b5-deplo7n4z5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726110321 && 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_1726110321/summary.json'
kubectl exec -it trace2333-mistral-tr6e3f4d8d49f51af6823f5373d37b03b5-deplo7n4z5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726110321/summary.json'
Pipeline stage MKMLProfilerRunner completed in 957.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trail11-v1-profiler is running
Tearing down inference service trace2333-mistral-trail11-v1-profiler
Service trace2333-mistral-trail11-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
trace2333-mistral-trail11_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trail11_v1 status is now torndown due to DeploymentManager action