submission_id: valentin87-duke-jack-dra_6112_v1
developer_uid: valentin87
alignment_samples: 11642
alignment_score: 1.0016774534172463
best_of: 8
celo_rating: 1202.98
display_name: valentin87-duke-jack-dra_6112_v1
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_r1
latencies: [{'batch_size': 1, 'throughput': 0.6949088126732134, 'latency_mean': 1.4389825105667113, 'latency_p50': 1.4377981424331665, 'latency_p90': 1.6113296031951905}, {'batch_size': 3, 'throughput': 1.3182963417688571, 'latency_mean': 2.272177460193634, 'latency_p50': 2.2745331525802612, 'latency_p90': 2.5398751974105833}, {'batch_size': 5, 'throughput': 1.5422871981507398, 'latency_mean': 3.2308881855010987, 'latency_p50': 3.2039915323257446, 'latency_p90': 3.667489218711853}, {'batch_size': 6, 'throughput': 1.6078334654275577, 'latency_mean': 3.7069615542888643, 'latency_p50': 3.6967933177948, 'latency_p90': 4.261169004440307}, {'batch_size': 8, 'throughput': 1.5813789587239333, 'latency_mean': 5.030166115760803, 'latency_p50': 5.085729241371155, 'latency_p90': 5.640614247322082}, {'batch_size': 10, 'throughput': 1.5315492332368317, 'latency_mean': 6.484892729520798, 'latency_p50': 6.516398787498474, 'latency_p90': 7.395871615409851}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: valentin87/Duke_Jack_Dra
model_name: valentin87-duke-jack-dra_6112_v1
model_num_parameters: 12772070400.0
model_repo: valentin87/Duke_Jack_Dragonbane_r1
model_size: 13B
num_battles: 11642
num_wins: 5140
propriety_score: 0.7320525783619818
propriety_total_count: 989.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.62
timestamp: 2024-09-11T21:00:34+00:00
us_pacific_date: 2024-09-11
win_ratio: 0.44150489606596804
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-6112-v1-mkmlizer
Waiting for job on valentin87-duke-jack-dra-6112-v1-mkmlizer to finish
valentin87-duke-jack-dra-6112-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ _____ __ __ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ /___/ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ Version: 0.10.1 ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ https://mk1.ai ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ The license key for the current software has been verified as ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ belonging to: ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ Chai Research Corp. ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ║ ║
valentin87-duke-jack-dra-6112-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
valentin87-duke-jack-dra-6112-v1-mkmlizer: Downloaded to shared memory in 49.628s
valentin87-duke-jack-dra-6112-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoam6igdf, device:0
valentin87-duke-jack-dra-6112-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
valentin87-duke-jack-dra-6112-v1-mkmlizer: quantized model in 36.158s
valentin87-duke-jack-dra-6112-v1-mkmlizer: Processed model valentin87/Duke_Jack_Dragonbane_r1 in 85.786s
valentin87-duke-jack-dra-6112-v1-mkmlizer: creating bucket guanaco-mkml-models
valentin87-duke-jack-dra-6112-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
valentin87-duke-jack-dra-6112-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/valentin87-duke-jack-dra-6112-v1
valentin87-duke-jack-dra-6112-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-6112-v1/config.json
valentin87-duke-jack-dra-6112-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-6112-v1/special_tokens_map.json
valentin87-duke-jack-dra-6112-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-6112-v1/tokenizer_config.json
valentin87-duke-jack-dra-6112-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-6112-v1/tokenizer.json
Failed to get response for submission chaiml-elo-alignment-run-3_v42: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39436->127.0.0.1:8080: read: connection reset by peer\n')
valentin87-duke-jack-dra-6112-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/valentin87-duke-jack-dra-6112-v1/flywheel_model.0.safetensors
valentin87-duke-jack-dra-6112-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.05it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 46.28it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 46.63it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:09, 35.31it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:07, 43.83it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:07, 43.94it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:07, 40.26it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.64it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:07, 42.96it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.30it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.26it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 37.79it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 39.64it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:07, 36.61it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 43.16it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 41.88it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 42.63it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 43.49it/s] Loading 0: 30%|███ | 110/363 [00:02<00:06, 41.06it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 42.02it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:06, 40.46it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 44.33it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 45.68it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 38.72it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.57it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.35it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.00it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.17it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 37.37it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 41.99it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.21it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 36.67it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 42.31it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 41.80it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 40.54it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 42.32it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 36.87it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 45.99it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 44.47it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.64it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 34.99it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 35.40it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 40.15it/s] Loading 0: 67%|██████▋ | 243/363 [00:06<00:02, 41.41it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 33.32it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 40.95it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 40.60it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 41.29it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 41.32it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 39.07it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:01, 42.62it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 42.02it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 40.62it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 42.19it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 41.38it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:22, 2.48it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.20it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.28it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:05, 6.94it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 8.80it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 13.41it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 16.83it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 20.04it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 26.19it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.54it/s]
Job valentin87-duke-jack-dra-6112-v1-mkmlizer completed after 106.55s with status: succeeded
Stopping job with name valentin87-duke-jack-dra-6112-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-duke-jack-dra-6112-v1
Waiting for inference service valentin87-duke-jack-dra-6112-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service valentin87-duke-jack-dra-6112-v1 ready after 161.8922040462494s
Pipeline stage MKMLDeployer completed in 162.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2131776809692383s
Received healthy response to inference request in 1.8523178100585938s
Received healthy response to inference request in 1.727973222732544s
Received healthy response to inference request in 1.5867340564727783s
Received healthy response to inference request in 2.7097930908203125s
5 requests
0 failed requests
5th percentile: 1.6149818897247314
10th percentile: 1.6432297229766846
20th percentile: 1.6997253894805908
30th percentile: 1.7528421401977539
40th percentile: 1.802579975128174
50th percentile: 1.8523178100585938
60th percentile: 2.195307922363281
70th percentile: 2.5382980346679687
80th percentile: 2.8104700088500976
90th percentile: 3.011823844909668
95th percentile: 3.112500762939453
99th percentile: 3.1930422973632813
mean time: 2.2179991722106935
Pipeline stage StressChecker completed in 13.31s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.38s
Shutdown handler de-registered
valentin87-duke-jack-dra_6112_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service valentin87-duke-jack-dra-6112-v1-profiler
Waiting for inference service valentin87-duke-jack-dra-6112-v1-profiler to be ready
Inference service valentin87-duke-jack-dra-6112-v1-profiler ready after 170.42708158493042s
Pipeline stage MKMLProfilerDeployer completed in 170.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-duke-jack9ab982e0269772f2870a70ee123bd19b-deplovfknn:/code/chaiverse_profiler_1726088941 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-duke-jack9ab982e0269772f2870a70ee123bd19b-deplovfknn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726088941 && 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_1726088941/summary.json'
kubectl exec -it valentin87-duke-jack9ab982e0269772f2870a70ee123bd19b-deplovfknn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726088941/summary.json'
Pipeline stage MKMLProfilerRunner completed in 958.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-duke-jack-dra-6112-v1-profiler is running
Tearing down inference service valentin87-duke-jack-dra-6112-v1-profiler
Service valentin87-duke-jack-dra-6112-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
valentin87-duke-jack-dra_6112_v1 status is now inactive due to auto deactivation removed underperforming models