valentin87-duke-jack-dra_2042

submission_id: valentin87-duke-jack-dra_2042_v2

developer_uid: valentin87

alignment_samples: 13152

alignment_score: 0.01125818084134621

best_of: 8

celo_rating: 1238.76

display_name: valentin87-duke-jack-dra_2042_v2

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': 0.6922152116214775, 'latency_mean': 1.4445471167564392, 'latency_p50': 1.4428776502609253, 'latency_p90': 1.6235849380493164}, {'batch_size': 3, 'throughput': 1.3326742422488145, 'latency_mean': 2.244494518041611, 'latency_p50': 2.2479504346847534, 'latency_p90': 2.5399597883224487}, {'batch_size': 5, 'throughput': 1.5730655991713598, 'latency_mean': 3.1582868933677672, 'latency_p50': 3.1471195220947266, 'latency_p90': 3.5926538228988645}, {'batch_size': 6, 'throughput': 1.5937621645463573, 'latency_mean': 3.730835896730423, 'latency_p50': 3.7654372453689575, 'latency_p90': 4.239360189437866}, {'batch_size': 8, 'throughput': 1.6010706286442293, 'latency_mean': 4.96870104432106, 'latency_p50': 4.987966299057007, 'latency_p90': 5.694528484344483}, {'batch_size': 10, 'throughput': 1.5504092828200813, 'latency_mean': 6.4158812165260315, 'latency_p50': 6.470276713371277, 'latency_p90': 7.338151621818542}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: valentin87/Duke_Jack_Dra

model_name: valentin87-duke-jack-dra_2042_v2

model_num_parameters: 12772070400.0

model_repo: valentin87/Duke_Jack_Dragonbane

model_size: 13B

num_battles: 13152

num_wins: 6546

propriety_score: 0.7458369851007888

propriety_total_count: 1141.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.61

timestamp: 2024-09-11T14:52:50+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.4977189781021898

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-v2-mkmlizer
Waiting for job on valentin87-duke-jack-dra-2042-v2-mkmlizer to finish
valentin87-duke-jack-dra-2042-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║     _____            __           __                                ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║       /___/                                                         ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  https://mk1.ai                                                     ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  belonging to:                                                      ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  Chai Research Corp.                                                ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
valentin87-duke-jack-dra-2042-v2-mkmlizer: Downloaded to shared memory in 58.754s
valentin87-duke-jack-dra-2042-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkv6o9loq, device:0
valentin87-duke-jack-dra-2042-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
valentin87-duke-jack-dra-2042-v2-mkmlizer: quantized model in 41.165s
valentin87-duke-jack-dra-2042-v2-mkmlizer: Processed model valentin87/Duke_Jack_Dragonbane in 99.919s
valentin87-duke-jack-dra-2042-v2-mkmlizer: creating bucket guanaco-mkml-models
valentin87-duke-jack-dra-2042-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
valentin87-duke-jack-dra-2042-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v2
valentin87-duke-jack-dra-2042-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v2/config.json
valentin87-duke-jack-dra-2042-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v2/special_tokens_map.json
valentin87-duke-jack-dra-2042-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v2/tokenizer_config.json
valentin87-duke-jack-dra-2042-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v2/tokenizer.json
valentin87-duke-jack-dra-2042-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v2/flywheel_model.0.safetensors
valentin87-duke-jack-dra-2042-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.41it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 29.65it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.29it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:10, 31.33it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 23.51it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.18it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.85it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.62it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.42it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:12, 24.90it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.11it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.78it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.91it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 31.27it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.38it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.29it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.57it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:11, 23.92it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.58it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.88it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.73it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.79it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.64it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:11, 22.23it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.87it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.26it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.81it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.81it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.49it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.56it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.83it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.01it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.77it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.52it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.73it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.01it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:06, 29.88it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 26.44it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 31.30it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:06, 27.70it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 26.31it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 23.15it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 29.46it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.41it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.01it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.59it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.91it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.19it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:05, 28.95it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.48it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.60it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.71it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 27.72it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 25.48it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 32.07it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.88it/s]
Loading 0:  70%|██████▉   | 254/363 [00:09<00:03, 32.83it/s]
Loading 0:  71%|███████   | 258/363 [00:09<00:03, 28.13it/s]
Loading 0:  72%|███████▏  | 262/363 [00:09<00:03, 30.21it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 20.93it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.62it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 26.74it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.54it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.69it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.25it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.75it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.07it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.87it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.06it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.04it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.55it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 30.72it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.81it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.08it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.20it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.66it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.99it/s]
Loading 0: 100%|█████████▉| 362/363 [00:19<00:00,  7.09it/s]
                                                            
Job valentin87-duke-jack-dra-2042-v2-mkmlizer completed after 125.75s with status: succeeded
Stopping job with name valentin87-duke-jack-dra-2042-v2-mkmlizer
Pipeline stage MKMLizer completed in 126.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-duke-jack-dra-2042-v2
Waiting for inference service valentin87-duke-jack-dra-2042-v2 to be ready
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://zonemercy-virgo-edit-v1-1e5-v10-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Inference service valentin87-duke-jack-dra-2042-v2 ready after 162.09171724319458s
Pipeline stage MKMLDeployer completed in 162.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3517799377441406s
Received healthy response to inference request in 1.726062536239624s
Received healthy response to inference request in 3.0008201599121094s
Received healthy response to inference request in 1.593566656112671s
Received healthy response to inference request in 1.7744286060333252s
5 requests
0 failed requests
5th percentile: 1.6200658321380614
10th percentile: 1.6465650081634522
20th percentile: 1.6995633602142335
30th percentile: 1.7357357501983643
40th percentile: 1.7550821781158448
50th percentile: 1.7744286060333252
60th percentile: 2.0053691387176515
70th percentile: 2.2363096714019775
80th percentile: 2.4815879821777345
90th percentile: 2.7412040710449217
95th percentile: 2.8710121154785155
99th percentile: 2.9748585510253904
mean time: 2.089331579208374
Pipeline stage StressChecker completed in 11.27s
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 5.43s
Shutdown handler de-registered
valentin87-duke-jack-dra_2042_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service valentin87-duke-jack-dra-2042-v2-profiler
Waiting for inference service valentin87-duke-jack-dra-2042-v2-profiler to be ready
Inference service valentin87-duke-jack-dra-2042-v2-profiler ready after 161.93062806129456s
Pipeline stage MKMLProfilerDeployer completed in 162.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-duke-jackf6507a36248ef23ed0aa8e7fa9e8f849-deplocgj9l:/code/chaiverse_profiler_1726066877 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-duke-jackf6507a36248ef23ed0aa8e7fa9e8f849-deplocgj9l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726066877 && 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_1726066877/summary.json'
kubectl exec -it valentin87-duke-jackf6507a36248ef23ed0aa8e7fa9e8f849-deplocgj9l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726066877/summary.json'
Pipeline stage MKMLProfilerRunner completed in 952.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-duke-jack-dra-2042-v2-profiler is running
Tearing down inference service valentin87-duke-jack-dra-2042-v2-profiler
Service valentin87-duke-jack-dra-2042-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.91s
Shutdown handler de-registered
valentin87-duke-jack-dra_2042_v2 status is now inactive due to auto deactivation removed underperforming models