trace2333-mistral-align-_8132

developer_uid: Trace2333

submission_id: trace2333-mistral-align-_8132_v7

model_name: trace2333-mistral-align-_8132_v7

model_group: Trace2333/mistral_align_

status: torndown

timestamp: 2024-09-07T05:33:14+00:00

num_battles: 11222

num_wins: 5817

celo_rating: 1254.95

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': 0.698919941263286, 'latency_mean': 1.4306890618801118, 'latency_p50': 1.431679129600525, 'latency_p90': 1.5973151922225952}, {'batch_size': 3, 'throughput': 1.3178610587131647, 'latency_mean': 2.2674101042747496, 'latency_p50': 2.264872670173645, 'latency_p90': 2.4825931072235106}, {'batch_size': 5, 'throughput': 1.566135235041807, 'latency_mean': 3.169746096134186, 'latency_p50': 3.1737024784088135, 'latency_p90': 3.5437446355819704}, {'batch_size': 6, 'throughput': 1.6275540781664124, 'latency_mean': 3.658710113763809, 'latency_p50': 3.7068052291870117, 'latency_p90': 4.099413537979126}, {'batch_size': 8, 'throughput': 1.6057175818618394, 'latency_mean': 4.9633654582500455, 'latency_p50': 4.984787106513977, 'latency_p90': 5.616945409774781}, {'batch_size': 10, 'throughput': 1.560080239369783, 'latency_mean': 6.388229593038559, 'latency_p50': 6.393986463546753, 'latency_p90': 7.240326738357544}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: trace2333-mistral-align-_8132_v7

is_internal_developer: False

language_model: Trace2333/mistral_align_namo_1448

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2024-09-06

win_ratio: 0.5183567991445375

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-v7-mkmlizer
Waiting for job on trace2333-mistral-align-8132-v7-mkmlizer to finish
trace2333-mistral-align-8132-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-align-8132-v7-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-align-8132-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-align-8132-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-align-8132-v7-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-align-8132-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-align-8132-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-align-8132-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-align-8132-v7-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-align-8132-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-align-8132-v7-mkmlizer: Downloaded to shared memory in 32.259s
trace2333-mistral-align-8132-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7oxryjv3, device:0
trace2333-mistral-align-8132-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission neversleep-noromaid-v0_8068_v150: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42110->127.0.0.1:8080: read: connection reset by peer\n')
trace2333-mistral-align-8132-v7-mkmlizer: quantized model in 35.592s
trace2333-mistral-align-8132-v7-mkmlizer: Processed model Trace2333/mistral_align_namo_1448 in 67.851s
trace2333-mistral-align-8132-v7-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-align-8132-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-align-8132-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-align-8132-v7
trace2333-mistral-align-8132-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v7/config.json
trace2333-mistral-align-8132-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v7/special_tokens_map.json
trace2333-mistral-align-8132-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v7/tokenizer_config.json
trace2333-mistral-align-8132-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v7/tokenizer.json
trace2333-mistral-align-8132-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-align-8132-v7/flywheel_model.0.safetensors
trace2333-mistral-align-8132-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 44.57it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 78.00it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:04, 74.44it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:04, 78.21it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:04, 77.62it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:04, 75.86it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:14, 20.26it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:12, 23.74it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.69it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 35.25it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 43.97it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 52.00it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 58.61it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:04, 59.63it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 63.11it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 20.47it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 26.29it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.43it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 42.48it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 54.38it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:02, 58.64it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 63.95it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 67.21it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 69.77it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:06, 21.63it/s]
Loading 0:  64%|██████▍   | 234/363 [00:06<00:05, 24.52it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:04, 29.52it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 37.29it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 45.87it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:01, 56.00it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 58.64it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 60.80it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 66.54it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 21.01it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 31.51it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:00, 37.68it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 44.43it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 48.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:08<00:00, 55.43it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00,  4.44it/s]
                                                            
Job trace2333-mistral-align-8132-v7-mkmlizer completed after 95.37s with status: succeeded
Stopping job with name trace2333-mistral-align-8132-v7-mkmlizer
Pipeline stage MKMLizer completed in 96.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-align-8132-v7
Waiting for inference service trace2333-mistral-align-8132-v7 to be ready
Inference service trace2333-mistral-align-8132-v7 ready after 150.40548014640808s
Pipeline stage MKMLDeployer completed in 150.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.667208194732666s
Received healthy response to inference request in 2.0761680603027344s
Received healthy response to inference request in 1.911440372467041s
Received healthy response to inference request in 2.264674425125122s
Received healthy response to inference request in 1.800309658050537s
5 requests
0 failed requests
5th percentile: 1.822535800933838
10th percentile: 1.8447619438171388
20th percentile: 1.8892142295837402
30th percentile: 1.9443859100341796
40th percentile: 2.010276985168457
50th percentile: 2.0761680603027344
60th percentile: 2.1515706062316893
70th percentile: 2.2269731521606446
80th percentile: 2.345181179046631
90th percentile: 2.5061946868896485
95th percentile: 2.586701440811157
99th percentile: 2.651106843948364
mean time: 2.14396014213562
Pipeline stage StressChecker completed in 11.41s
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 4.69s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v7 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-align-8132-v7-profiler
Waiting for inference service trace2333-mistral-align-8132-v7-profiler to be ready
Inference service trace2333-mistral-align-8132-v7-profiler ready after 150.3884518146515s
Pipeline stage MKMLProfilerDeployer completed in 150.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-al6b634e043fdeb86aa7c23610d0a131ca-deplosz8w2:/code/chaiverse_profiler_1725687644 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-al6b634e043fdeb86aa7c23610d0a131ca-deplosz8w2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725687644 && 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_1725687644/summary.json'
kubectl exec -it trace2333-mistral-al6b634e043fdeb86aa7c23610d0a131ca-deplosz8w2 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725687644/summary.json'
Pipeline stage MKMLProfilerRunner completed in 946.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-align-8132-v7-profiler is running
Tearing down inference service trace2333-mistral-align-8132-v7-profiler
Service trace2333-mistral-align-8132-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v7 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-align-_8132_v7 status is now torndown due to DeploymentManager action