trace2333-mistral-align-_8132

developer_uid: Trace2333

submission_id: trace2333-mistral-align-_8132_v6

model_name: trace2333-mistral-align-_8132_v6

model_group: Trace2333/mistral_align_

status: torndown

timestamp: 2024-09-07T03:53:50+00:00

num_battles: 12863

num_wins: 6958

celo_rating: 1253.25

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/mistral_align_namo_1448

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6887210312072579, 'latency_mean': 1.451879357099533, 'latency_p50': 1.4341351985931396, 'latency_p90': 1.6236056089401245}, {'batch_size': 3, 'throughput': 1.303021615954806, 'latency_mean': 2.293401389122009, 'latency_p50': 2.3179426193237305, 'latency_p90': 2.5528985500335692}, {'batch_size': 5, 'throughput': 1.539013716498496, 'latency_mean': 3.230256563425064, 'latency_p50': 3.261520028114319, 'latency_p90': 3.605654740333557}, {'batch_size': 6, 'throughput': 1.5854061370505397, 'latency_mean': 3.7604226088523864, 'latency_p50': 3.7847965955734253, 'latency_p90': 4.236521577835083}, {'batch_size': 8, 'throughput': 1.5868177673284578, 'latency_mean': 5.023491431474685, 'latency_p50': 5.055796265602112, 'latency_p90': 5.634241604804993}, {'batch_size': 10, 'throughput': 1.5321326387472303, 'latency_mean': 6.481670389175415, 'latency_p50': 6.482420325279236, 'latency_p90': 7.406701636314392}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: trace2333-mistral-align-_8132_v6

is_internal_developer: False

language_model: Trace2333/mistral_align_namo_1448

model_size: 13B

ranking_group: single

throughput_3p7s: 1.59

us_pacific_date: 2024-09-06

win_ratio: 0.5409313534945192

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}

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}

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-align-8132-v6-mkmlizer
Waiting for job on trace2333-mistral-align-8132-v6-mkmlizer to finish
trace2333-mistral-align-8132-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-align-8132-v6-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-align-8132-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-align-8132-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-align-8132-v6-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-align-8132-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-align-8132-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-align-8132-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-align-8132-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-align-8132-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-align-8132-v6-mkmlizer: Downloaded to shared memory in 43.916s
trace2333-mistral-align-8132-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8ws1x6ok, device:0
trace2333-mistral-align-8132-v6-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-mistral-align-8132-v6-mkmlizer: quantized model in 36.426s
trace2333-mistral-align-8132-v6-mkmlizer: Processed model Trace2333/mistral_align_namo_1448 in 80.343s
trace2333-mistral-align-8132-v6-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-align-8132-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-align-8132-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-align-8132-v6
trace2333-mistral-align-8132-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v6/special_tokens_map.json
trace2333-mistral-align-8132-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v6/config.json
trace2333-mistral-align-8132-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v6/tokenizer_config.json
trace2333-mistral-align-8132-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v6/tokenizer.json
trace2333-mistral-align-8132-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:08, 43.48it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 63.56it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 68.87it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 70.48it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 75.22it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 71.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:16, 18.19it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.69it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.94it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 35.74it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:05, 45.25it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 50.92it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 53.66it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 61.05it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 67.59it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:10, 20.94it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:07, 27.18it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.08it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:04, 39.66it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:03, 46.70it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 53.82it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 61.20it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 63.80it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 62.79it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.78it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 26.11it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.81it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 39.85it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 46.70it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 54.02it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 61.05it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 64.81it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 66.04it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 21.54it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.81it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.91it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 45.31it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 51.63it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 57.19it/s]
                                                            
Job trace2333-mistral-align-8132-v6-mkmlizer completed after 106.73s with status: succeeded
Stopping job with name trace2333-mistral-align-8132-v6-mkmlizer
Pipeline stage MKMLizer completed in 107.74s
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-align-8132-v6
Waiting for inference service trace2333-mistral-align-8132-v6 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-mistral-align-8132-v6 ready after 190.71777987480164s
Pipeline stage MKMLDeployer completed in 191.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.460400342941284s
Received healthy response to inference request in 2.0364112854003906s
Received healthy response to inference request in 2.0757038593292236s
Received healthy response to inference request in 1.829563856124878s
Received healthy response to inference request in 1.6767926216125488s
5 requests
0 failed requests
5th percentile: 1.7073468685150146
10th percentile: 1.7379011154174804
20th percentile: 1.7990096092224122
30th percentile: 1.8709333419799805
40th percentile: 1.9536723136901855
50th percentile: 2.0364112854003906
60th percentile: 2.052128314971924
70th percentile: 2.067845344543457
80th percentile: 2.152643156051636
90th percentile: 2.30652174949646
95th percentile: 2.383461046218872
99th percentile: 2.445012483596802
mean time: 2.015774393081665
Pipeline stage StressChecker completed in 10.80s
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 5.05s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v6 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-align-8132-v6-profiler
Waiting for inference service trace2333-mistral-align-8132-v6-profiler to be ready
Inference service trace2333-mistral-align-8132-v6-profiler ready after 150.35521411895752s
Pipeline stage MKMLProfilerDeployer completed in 150.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-alfb0d352cb93dd548a02ac08414ea52c9-deplor6gc8:/code/chaiverse_profiler_1725681740 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-alfb0d352cb93dd548a02ac08414ea52c9-deplor6gc8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725681740 && 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_1725681740/summary.json'
kubectl exec -it trace2333-mistral-alfb0d352cb93dd548a02ac08414ea52c9-deplor6gc8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725681740/summary.json'
Pipeline stage MKMLProfilerRunner completed in 963.34s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-align-8132-v6-profiler is running
Tearing down inference service trace2333-mistral-align-8132-v6-profiler
Service trace2333-mistral-align-8132-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.73s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v6 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-align-_8132_v6 status is now torndown due to DeploymentManager action