rica40325-dpo0904

developer_uid: rica40325

submission_id: rica40325-dpo0904_v1

model_name: rica40325-dpo0904_v1

model_group: rica40325/dpo0904

status: torndown

timestamp: 2024-09-05T06:44:18+00:00

num_battles: 13212

num_wins: 5375

celo_rating: 1171.78

family_friendly_score: 0.0

submission_type: basic

model_repo: rica40325/dpo0904

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8916534766505932, 'latency_mean': 1.121422472000122, 'latency_p50': 1.1236674785614014, 'latency_p90': 1.25724139213562}, {'batch_size': 4, 'throughput': 1.7813601956231728, 'latency_mean': 2.229950214624405, 'latency_p50': 2.228931427001953, 'latency_p90': 2.52610867023468}, {'batch_size': 5, 'throughput': 1.8537487873443586, 'latency_mean': 2.681754792928696, 'latency_p50': 2.6970804929733276, 'latency_p90': 3.0072163105010983}, {'batch_size': 8, 'throughput': 1.9700690142093682, 'latency_mean': 4.044894660711289, 'latency_p50': 4.068016409873962, 'latency_p90': 4.561249232292175}, {'batch_size': 10, 'throughput': 1.9947544471293022, 'latency_mean': 4.9637329018116, 'latency_p50': 4.958483934402466, 'latency_p90': 5.655247712135314}, {'batch_size': 12, 'throughput': 1.9972146113430287, 'latency_mean': 5.920848928689956, 'latency_p50': 5.9869314432144165, 'latency_p90': 6.793820738792419}, {'batch_size': 15, 'throughput': 2.0036682385349307, 'latency_mean': 7.355240802764893, 'latency_p50': 7.459568977355957, 'latency_p90': 8.310866975784302}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-dpo0904_v1

is_internal_developer: False

language_model: rica40325/dpo0904

model_size: 8B

ranking_group: single

throughput_3p7s: 1.96

us_pacific_date: 2024-09-04

win_ratio: 0.40682712685437483

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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 rica40325-dpo0904-v1-mkmlizer
Waiting for job on rica40325-dpo0904-v1-mkmlizer to finish
rica40325-dpo0904-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-dpo0904-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-dpo0904-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-dpo0904-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-dpo0904-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-dpo0904-v1-mkmlizer: ║       /___/                                                         ║
rica40325-dpo0904-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0904-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-dpo0904-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-dpo0904-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-dpo0904-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0904-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-dpo0904-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-dpo0904-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0904-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-dpo0904-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-dpo0904-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-dpo0904-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0904-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-dpo0904-v1-mkmlizer: Downloaded to shared memory in 64.979s
rica40325-dpo0904-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnauuyfab, device:0
rica40325-dpo0904-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-dpo0904-v1-mkmlizer: quantized model in 30.250s
rica40325-dpo0904-v1-mkmlizer: Processed model rica40325/dpo0904 in 95.229s
rica40325-dpo0904-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-dpo0904-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-dpo0904-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-dpo0904-v1
rica40325-dpo0904-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-dpo0904-v1/config.json
rica40325-dpo0904-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-dpo0904-v1/special_tokens_map.json
rica40325-dpo0904-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-dpo0904-v1/tokenizer_config.json
rica40325-dpo0904-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-dpo0904-v1/flywheel_model.0.safetensors
rica40325-dpo0904-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.29it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 33.30it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 30.80it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:08, 32.92it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 30.70it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:08, 31.96it/s]
Loading 0:  11%|█▏        | 33/291 [00:01<00:11, 22.45it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:12, 20.66it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:11, 22.32it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 29.19it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 28.60it/s]
Loading 0:  20%|█▉        | 57/291 [00:02<00:07, 30.45it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 29.26it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:07, 31.72it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:07, 30.08it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:07, 29.87it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:07, 30.40it/s]
Loading 0:  28%|██▊       | 82/291 [00:03<00:09, 22.08it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:08, 23.08it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 27.58it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:07, 27.67it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 30.13it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 28.99it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 32.09it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 31.38it/s]
Loading 0:  40%|███▉      | 116/291 [00:04<00:05, 30.98it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 35.48it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:05, 32.52it/s]
Loading 0:  45%|████▌     | 132/291 [00:04<00:04, 35.51it/s]
Loading 0:  47%|████▋     | 136/291 [00:04<00:06, 23.70it/s]
Loading 0:  48%|████▊     | 140/291 [00:05<00:06, 22.99it/s]
Loading 0:  51%|█████     | 147/291 [00:05<00:04, 29.44it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 28.78it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 30.49it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 29.33it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 31.86it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 30.73it/s]
Loading 0:  60%|█████▉    | 174/291 [00:06<00:03, 32.54it/s]
Loading 0:  61%|██████    | 178/291 [00:06<00:03, 31.02it/s]
Loading 0:  63%|██████▎   | 183/291 [00:06<00:03, 34.89it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:04, 24.99it/s]
Loading 0:  65%|██████▌   | 190/291 [00:06<00:04, 24.06it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:04, 23.34it/s]
Loading 0:  69%|██████▉   | 201/291 [00:07<00:02, 30.13it/s]
Loading 0:  70%|███████   | 205/291 [00:07<00:02, 29.09it/s]
Loading 0:  72%|███████▏  | 210/291 [00:07<00:02, 31.94it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 30.30it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 32.44it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 30.92it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 30.77it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 30.45it/s]
Loading 0:  81%|████████  | 235/291 [00:08<00:02, 22.95it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 22.56it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 29.52it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 29.01it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 31.43it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 30.28it/s]
Loading 0:  91%|█████████ | 264/291 [00:09<00:00, 32.65it/s]
Loading 0:  92%|█████████▏| 268/291 [00:09<00:00, 30.88it/s]
Loading 0:  94%|█████████▍| 273/291 [00:09<00:00, 32.58it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 30.17it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 29.71it/s]
Loading 0:  98%|█████████▊| 285/291 [00:09<00:00, 31.97it/s]
Loading 0:  99%|█████████▉| 289/291 [00:15<00:00,  2.32it/s]
                                                            
Job rica40325-dpo0904-v1-mkmlizer completed after 115.16s with status: succeeded
Stopping job with name rica40325-dpo0904-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-dpo0904-v1
Waiting for inference service rica40325-dpo0904-v1 to be ready
Inference service rica40325-dpo0904-v1 ready after 140.8246204853058s
Pipeline stage MKMLDeployer completed in 141.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9277334213256836s
Received healthy response to inference request in 1.7556605339050293s
Received healthy response to inference request in 1.609919548034668s
Received healthy response to inference request in 1.3854544162750244s
Received healthy response to inference request in 2.303347587585449s
5 requests
0 failed requests
5th percentile: 1.4303474426269531
10th percentile: 1.4752404689788818
20th percentile: 1.5650265216827393
30th percentile: 1.6390677452087403
40th percentile: 1.6973641395568848
50th percentile: 1.7556605339050293
60th percentile: 1.824489688873291
70th percentile: 1.8933188438415527
80th percentile: 2.0028562545776367
90th percentile: 2.153101921081543
95th percentile: 2.228224754333496
99th percentile: 2.2883230209350587
mean time: 1.7964231014251708
Pipeline stage StressChecker completed in 9.73s
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 5.47s
Shutdown handler de-registered
rica40325-dpo0904_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-dpo0904-v1-profiler
Waiting for inference service rica40325-dpo0904-v1-profiler to be ready
Inference service rica40325-dpo0904-v1-profiler ready after 150.33788299560547s
Pipeline stage MKMLProfilerDeployer completed in 150.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-dpo0904-v1-profiler-predictor-00001-deployment-5xws6r:/code/chaiverse_profiler_1725519114 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-dpo0904-v1-profiler-predictor-00001-deployment-5xws6r --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725519114 && python profiles.py profile --best_of_n 16 --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_1725519114/summary.json'
kubectl exec -it rica40325-dpo0904-v1-profiler-predictor-00001-deployment-5xws6r --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725519114/summary.json'
Pipeline stage MKMLProfilerRunner completed in 852.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-dpo0904-v1-profiler is running
Tearing down inference service rica40325-dpo0904-v1-profiler
Service rica40325-dpo0904-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.55s
Shutdown handler de-registered
rica40325-dpo0904_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-dpo0904_v1 status is now torndown due to DeploymentManager action