submission_id: trace2333-mistral-align-_8132_v3
developer_uid: Trace2333
alignment_samples: 12032
alignment_score: -0.06913207446447137
best_of: 8
celo_rating: 1256.58
display_name: trace2333-mistral-align-_8132_v3
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_align_namo_1448
latencies: [{'batch_size': 1, 'throughput': 0.6937078048832248, 'latency_mean': 1.4414356279373168, 'latency_p50': 1.4432095289230347, 'latency_p90': 1.5995412588119506}, {'batch_size': 3, 'throughput': 1.3252493505477088, 'latency_mean': 2.258074381351471, 'latency_p50': 2.2456746101379395, 'latency_p90': 2.48301842212677}, {'batch_size': 5, 'throughput': 1.550166898075938, 'latency_mean': 3.2068489599227905, 'latency_p50': 3.2157269716262817, 'latency_p90': 3.5920592308044434}, {'batch_size': 6, 'throughput': 1.5937800814755119, 'latency_mean': 3.7413528501987456, 'latency_p50': 3.780479669570923, 'latency_p90': 4.268610835075378}, {'batch_size': 8, 'throughput': 1.5984573024814637, 'latency_mean': 4.981389136314392, 'latency_p50': 4.973011255264282, 'latency_p90': 5.696141934394836}, {'batch_size': 10, 'throughput': 1.5347578334807817, 'latency_mean': 6.475692907571792, 'latency_p50': 6.486029744148254, 'latency_p90': 7.335342192649842}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_align_
model_name: trace2333-mistral-align-_8132_v3
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_align_namo_1448
model_size: 13B
num_battles: 12032
num_wins: 6246
propriety_score: 0.7589545014520813
propriety_total_count: 1033.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.6
timestamp: 2024-09-06T17:25:48+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5191156914893617
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-align-8132-v3-mkmlizer
Waiting for job on trace2333-mistral-align-8132-v3-mkmlizer to finish
trace2333-mistral-align-8132-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-align-8132-v3-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-align-8132-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-align-8132-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-align-8132-v3-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-align-8132-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-align-8132-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-align-8132-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-align-8132-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-align-8132-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-align-8132-v3-mkmlizer: Downloaded to shared memory in 29.455s
trace2333-mistral-align-8132-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp556yn1zj, device:0
trace2333-mistral-align-8132-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-align-8132-v3-mkmlizer: quantized model in 35.923s
trace2333-mistral-align-8132-v3-mkmlizer: Processed model Trace2333/mistral_align_namo_1448 in 65.379s
trace2333-mistral-align-8132-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-align-8132-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-align-8132-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-align-8132-v3
trace2333-mistral-align-8132-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v3/config.json
trace2333-mistral-align-8132-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v3/special_tokens_map.json
trace2333-mistral-align-8132-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v3/tokenizer_config.json
trace2333-mistral-align-8132-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-align-8132-v3/flywheel_model.0.safetensors
trace2333-mistral-align-8132-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.09it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 83.05it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:04, 78.22it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:04, 73.67it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:04, 76.94it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 78.23it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:14, 21.06it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:11, 24.90it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.44it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 39.59it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 46.07it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 52.57it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 56.81it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 62.78it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 63.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 20.17it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.79it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.66it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.05it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 48.89it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 55.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:02, 63.98it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:02, 65.32it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 67.51it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:06, 20.93it/s]
Loading 0:  64%|██████▍   | 234/363 [00:06<00:05, 24.08it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:04, 28.31it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 36.25it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 44.57it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 49.47it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 55.60it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 60.95it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 63.11it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.48it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 30.32it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:00, 37.70it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 43.09it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 48.89it/s]
Loading 0:  98%|█████████▊| 356/363 [00:08<00:00, 57.86it/s]
                                                            

Job trace2333-mistral-align-8132-v3-mkmlizer completed after 85.21s with status: succeeded
Stopping job with name trace2333-mistral-align-8132-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.13s
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-align-8132-v3
Waiting for inference service trace2333-mistral-align-8132-v3 to be ready
Inference service trace2333-mistral-align-8132-v3 ready after 150.85944271087646s
Pipeline stage MKMLDeployer completed in 152.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3587515354156494s
Received healthy response to inference request in 2.117159843444824s
Received healthy response to inference request in 1.5007576942443848s
Received healthy response to inference request in 1.7284400463104248s
Received healthy response to inference request in 1.695019245147705s
5 requests
0 failed requests
5th percentile: 1.539610004425049
10th percentile: 1.5784623146057128
20th percentile: 1.656166934967041
30th percentile: 1.7017034053802491
40th percentile: 1.715071725845337
50th percentile: 1.7284400463104248
60th percentile: 1.8839279651641845
70th percentile: 2.039415884017944
80th percentile: 2.1654781818389894
90th percentile: 2.2621148586273194
95th percentile: 2.310433197021484
99th percentile: 2.3490878677368165
mean time: 1.8800256729125977
Pipeline stage StressChecker completed in 11.65s
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 5.22s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-align-8132-v3-profiler
Waiting for inference service trace2333-mistral-align-8132-v3-profiler to be ready
Inference service trace2333-mistral-align-8132-v3-profiler ready after 150.38093161582947s
Pipeline stage MKMLProfilerDeployer completed in 150.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-alcac01455b6b9cb9dec751cf60d1a3ad8-deplogxx78:/code/chaiverse_profiler_1725644010 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-alcac01455b6b9cb9dec751cf60d1a3ad8-deplogxx78 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725644010 && 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_1725644010/summary.json'
kubectl exec -it trace2333-mistral-alcac01455b6b9cb9dec751cf60d1a3ad8-deplogxx78 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725644010/summary.json'
Pipeline stage MKMLProfilerRunner completed in 954.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-align-8132-v3-profiler is running
Tearing down inference service trace2333-mistral-align-8132-v3-profiler
Service trace2333-mistral-align-8132-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.95s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics