valentin87-duke-jack-dra_2042

submission_id: valentin87-duke-jack-dra_2042_v6

developer_uid: valentin87

alignment_samples: 10386

alignment_score: -0.02927600271070673

best_of: 8

celo_rating: 1222.48

display_name: valentin87-duke-jack-dra_2042_v6

formatter: {'memory_template': '', 'prompt_template': '', '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': 0.0, 'top_k': 100, '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: valentin87/Duke_Jack_Dragonbane

latencies: [{'batch_size': 1, 'throughput': 0.6920522251022, 'latency_mean': 1.444912955760956, 'latency_p50': 1.4557660818099976, 'latency_p90': 1.5976054430007935}, {'batch_size': 3, 'throughput': 1.3507103635463602, 'latency_mean': 2.216179171800613, 'latency_p50': 2.21024227142334, 'latency_p90': 2.457135248184204}, {'batch_size': 5, 'throughput': 1.5770806078940387, 'latency_mean': 3.153505607843399, 'latency_p50': 3.1854926347732544, 'latency_p90': 3.522849273681641}, {'batch_size': 6, 'throughput': 1.6409015993566223, 'latency_mean': 3.6382846319675446, 'latency_p50': 3.6528714895248413, 'latency_p90': 4.065975666046143}, {'batch_size': 8, 'throughput': 1.6182267741554859, 'latency_mean': 4.912253276109696, 'latency_p50': 4.969979166984558, 'latency_p90': 5.539707183837891}, {'batch_size': 10, 'throughput': 1.570560742241888, 'latency_mean': 6.3224694895744324, 'latency_p50': 6.348997592926025, 'latency_p90': 7.227829360961914}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: valentin87/Duke_Jack_Dra

model_name: valentin87-duke-jack-dra_2042_v6

model_num_parameters: 12772070400.0

model_repo: valentin87/Duke_Jack_Dragonbane

model_size: 13B

num_battles: 10386

num_wins: 4887

propriety_score: 0.7594799566630552

propriety_total_count: 923.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.65

timestamp: 2024-09-11T21:09:23+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.47053726169844023

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 valentin87-duke-jack-dra-2042-v6-mkmlizer
Waiting for job on valentin87-duke-jack-dra-2042-v6-mkmlizer to finish
valentin87-duke-jack-dra-2042-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║     _____            __           __                                ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║       /___/                                                         ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  Version: 0.10.1                                                    ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  https://mk1.ai                                                     ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  belonging to:                                                      ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  Chai Research Corp.                                                ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
valentin87-duke-jack-dra-2042-v6-mkmlizer: Downloaded to shared memory in 82.290s
valentin87-duke-jack-dra-2042-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg8he_2kt, device:0
valentin87-duke-jack-dra-2042-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
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
valentin87-duke-jack-dra-2042-v6-mkmlizer: quantized model in 48.195s
valentin87-duke-jack-dra-2042-v6-mkmlizer: Processed model valentin87/Duke_Jack_Dragonbane in 130.485s
valentin87-duke-jack-dra-2042-v6-mkmlizer: creating bucket guanaco-mkml-models
valentin87-duke-jack-dra-2042-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
valentin87-duke-jack-dra-2042-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v6
valentin87-duke-jack-dra-2042-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v6/config.json
valentin87-duke-jack-dra-2042-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v6/special_tokens_map.json
valentin87-duke-jack-dra-2042-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v6/flywheel_model.0.safetensors
valentin87-duke-jack-dra-2042-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:17, 21.05it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:30, 11.62it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:21, 16.54it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:21, 16.39it/s]
Loading 0:   4%|▍         | 14/363 [00:01<00:29, 11.63it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:19, 17.50it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 16.10it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:22, 14.77it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.10it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:20, 16.46it/s]
Loading 0:   9%|▉         | 33/363 [00:02<00:21, 15.04it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:17, 18.21it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:18, 17.83it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.46it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.41it/s]
Loading 0:  13%|█▎        | 49/363 [00:03<00:20, 15.67it/s]
Loading 0:  14%|█▍        | 51/363 [00:03<00:21, 14.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:18, 16.96it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:18, 16.60it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:17, 17.58it/s]
Loading 0:  17%|█▋        | 62/363 [00:04<00:26, 11.42it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:40,  7.40it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:28, 10.30it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:29,  9.84it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:42,  6.89it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:31,  9.18it/s]
Loading 0:  21%|██▏       | 78/363 [00:06<00:29,  9.81it/s]
Loading 0:  22%|██▏       | 80/363 [00:06<00:31,  9.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:06<00:44,  6.26it/s]
Loading 0:  24%|██▎       | 86/363 [00:07<00:30,  9.16it/s]
Loading 0:  25%|██▍       | 89/363 [00:07<00:30,  8.97it/s]
Loading 0:  25%|██▌       | 91/363 [00:07<00:40,  6.64it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:30,  8.93it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:27,  9.65it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:29,  9.04it/s]
Loading 0:  28%|██▊       | 100/363 [00:09<00:42,  6.25it/s]
Loading 0:  29%|██▉       | 105/363 [00:09<00:24, 10.37it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:22, 11.21it/s]
Loading 0:  30%|███       | 110/363 [00:09<00:19, 13.24it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:18, 13.90it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:18, 13.12it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:17, 13.97it/s]
Loading 0:  33%|███▎      | 118/363 [00:10<00:23, 10.39it/s]
Loading 0:  34%|███▍      | 123/363 [00:10<00:15, 15.68it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:15, 15.69it/s]
Loading 0:  35%|███▍      | 127/363 [00:10<00:20, 11.56it/s]
Loading 0:  36%|███▋      | 132/363 [00:10<00:14, 16.48it/s]
Loading 0:  37%|███▋      | 135/363 [00:11<00:15, 14.90it/s]
Loading 0:  38%|███▊      | 137/363 [00:11<00:16, 13.64it/s]
Loading 0:  39%|███▉      | 141/363 [00:11<00:13, 16.55it/s]
Loading 0:  39%|███▉      | 143/363 [00:11<00:13, 16.17it/s]
Loading 0:  40%|████      | 147/363 [00:11<00:10, 19.97it/s]
Loading 0:  41%|████▏     | 150/363 [00:11<00:09, 22.02it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:06, 32.10it/s]
Loading 0:  45%|████▍     | 163/363 [00:12<00:05, 34.54it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:05, 32.93it/s]
Loading 0:  48%|████▊     | 174/363 [00:12<00:04, 40.63it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:04, 40.97it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:04, 42.29it/s]
Loading 0:  52%|█████▏    | 189/363 [00:12<00:04, 42.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:04, 36.27it/s]
Loading 0:  56%|█████▌    | 202/363 [00:13<00:03, 44.37it/s]
Loading 0:  57%|█████▋    | 207/363 [00:13<00:03, 44.37it/s]
Loading 0:  58%|█████▊    | 212/363 [00:13<00:03, 37.87it/s]
Loading 0:  60%|██████    | 218/363 [00:13<00:03, 41.45it/s]
Loading 0:  61%|██████▏   | 223/363 [00:13<00:04, 30.66it/s]
Loading 0:  63%|██████▎   | 227/363 [00:13<00:04, 32.05it/s]
Loading 0:  64%|██████▎   | 231/363 [00:14<00:04, 30.49it/s]
Loading 0:  65%|██████▌   | 237/363 [00:14<00:03, 34.92it/s]
Loading 0:  66%|██████▋   | 241/363 [00:14<00:03, 35.19it/s]
Loading 0:  68%|██████▊   | 247/363 [00:14<00:02, 39.35it/s]
Loading 0:  69%|██████▉   | 252/363 [00:14<00:02, 40.66it/s]
Loading 0:  71%|███████   | 257/363 [00:14<00:03, 34.69it/s]
Loading 0:  73%|███████▎  | 264/363 [00:14<00:02, 41.79it/s]
Loading 0:  74%|███████▍  | 269/363 [00:14<00:02, 40.89it/s]
Loading 0:  75%|███████▌  | 274/363 [00:15<00:02, 40.27it/s]
Loading 0:  77%|███████▋  | 280/363 [00:15<00:02, 39.92it/s]
Loading 0:  79%|███████▊  | 285/363 [00:15<00:01, 40.02it/s]
Loading 0:  80%|████████  | 291/363 [00:15<00:01, 44.54it/s]
Loading 0:  82%|████████▏ | 296/363 [00:15<00:01, 43.43it/s]
Loading 0:  83%|████████▎ | 302/363 [00:15<00:01, 47.06it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:25,  2.23it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:16,  3.05it/s]
Loading 0:  88%|████████▊ | 320/363 [00:23<00:08,  4.90it/s]
Loading 0:  90%|████████▉ | 326/363 [00:23<00:05,  6.66it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:03,  8.46it/s]
Loading 0:  93%|█████████▎| 337/363 [00:24<00:02, 11.44it/s]
Loading 0:  94%|█████████▍| 342/363 [00:24<00:01, 14.10it/s]
Loading 0:  96%|█████████▌| 347/363 [00:24<00:00, 17.39it/s]
Loading 0:  97%|█████████▋| 352/363 [00:24<00:00, 21.30it/s]
Loading 0:  98%|█████████▊| 357/363 [00:24<00:00, 22.48it/s]
                                                            
Job valentin87-duke-jack-dra-2042-v6-mkmlizer completed after 150.3s with status: succeeded
Stopping job with name valentin87-duke-jack-dra-2042-v6-mkmlizer
Pipeline stage MKMLizer completed in 151.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-duke-jack-dra-2042-v6
Waiting for inference service valentin87-duke-jack-dra-2042-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service valentin87-duke-jack-dra-2042-v6 ready after 161.0440158843994s
Pipeline stage MKMLDeployer completed in 162.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6209025382995605s
Received healthy response to inference request in 1.629216194152832s
Received healthy response to inference request in 1.7716147899627686s
Received healthy response to inference request in 1.9805338382720947s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.5974140167236328s
5 requests
0 failed requests
5th percentile: 1.6037744522094726
10th percentile: 1.6101348876953125
20th percentile: 1.6228557586669923
30th percentile: 1.6576959133148192
40th percentile: 1.714655351638794
50th percentile: 1.7716147899627686
60th percentile: 1.855182409286499
70th percentile: 1.9387500286102295
80th percentile: 2.108607578277588
90th percentile: 2.364755058288574
95th percentile: 2.492828798294067
99th percentile: 2.5952877902984617
mean time: 1.9199362754821778
Pipeline stage StressChecker completed in 10.79s
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 3.96s
Shutdown handler de-registered
valentin87-duke-jack-dra_2042_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service valentin87-duke-jack-dra-2042-v6-profiler
Waiting for inference service valentin87-duke-jack-dra-2042-v6-profiler to be ready
Inference service valentin87-duke-jack-dra-2042-v6-profiler ready after 170.40781116485596s
Pipeline stage MKMLProfilerDeployer completed in 170.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-duke-jack36db00dac2c51689f0cdfc793b070e2f-deplomfp8l:/code/chaiverse_profiler_1726089510 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-duke-jack36db00dac2c51689f0cdfc793b070e2f-deplomfp8l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726089510 && 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_1726089510/summary.json'
kubectl exec -it valentin87-duke-jack36db00dac2c51689f0cdfc793b070e2f-deplomfp8l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726089510/summary.json'
Pipeline stage MKMLProfilerRunner completed in 944.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-duke-jack-dra-2042-v6-profiler is running
Tearing down inference service valentin87-duke-jack-dra-2042-v6-profiler
Service valentin87-duke-jack-dra-2042-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
valentin87-duke-jack-dra_2042_v6 status is now inactive due to auto deactivation removed underperforming models