submission_id: rinen0721-llama0911_v1
developer_uid: rinen0721
best_of: 16
celo_rating: 1216.03
display_name: rinen0721-llama0911_v1
family_friendly_score: 0.0
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': 0.0, '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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rinen0721/llama0911
latencies: [{'batch_size': 1, 'throughput': 0.9058676771774427, 'latency_mean': 1.103851535320282, 'latency_p50': 1.110918402671814, 'latency_p90': 1.228943157196045}, {'batch_size': 4, 'throughput': 1.8145394141882998, 'latency_mean': 2.1938546538352965, 'latency_p50': 2.18815279006958, 'latency_p90': 2.4525532722473145}, {'batch_size': 5, 'throughput': 1.8788522063711144, 'latency_mean': 2.6514797973632813, 'latency_p50': 2.6320995092391968, 'latency_p90': 2.9604772567749023}, {'batch_size': 8, 'throughput': 2.005074770901256, 'latency_mean': 3.9566921377182007, 'latency_p50': 3.930914282798767, 'latency_p90': 4.546098971366882}, {'batch_size': 10, 'throughput': 2.0590501823575535, 'latency_mean': 4.811527523994446, 'latency_p50': 4.841981053352356, 'latency_p90': 5.50054018497467}, {'batch_size': 12, 'throughput': 2.039713107765649, 'latency_mean': 5.800738557577133, 'latency_p50': 5.770959973335266, 'latency_p90': 6.7109929561614985}, {'batch_size': 15, 'throughput': 2.0309648951856203, 'latency_mean': 7.245573513507843, 'latency_p50': 7.3604536056518555, 'latency_p90': 8.12281653881073}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rinen0721/llama0911
model_name: rinen0721-llama0911_v1
model_num_parameters: 8030261248.0
model_repo: rinen0721/llama0911
model_size: 8B
num_battles: 13129
num_wins: 6068
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.0
timestamp: 2024-09-11T06:10:07+00:00
us_pacific_date: 2024-09-10
win_ratio: 0.46218295376647117
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 rinen0721-llama0911-v1-mkmlizer
Waiting for job on rinen0721-llama0911-v1-mkmlizer to finish
rinen0721-llama0911-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama0911-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama0911-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama0911-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama0911-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama0911-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama0911-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0911-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rinen0721-llama0911-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama0911-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama0911-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0911-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama0911-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama0911-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0911-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama0911-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama0911-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama0911-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0911-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama0911-v1-mkmlizer: Downloaded to shared memory in 34.984s
rinen0721-llama0911-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppq7v_als, device:0
rinen0721-llama0911-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama0911-v1-mkmlizer: quantized model in 25.687s
rinen0721-llama0911-v1-mkmlizer: Processed model rinen0721/llama0911 in 60.671s
rinen0721-llama0911-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama0911-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-llama0911-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-llama0911-v1
rinen0721-llama0911-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama0911-v1/config.json
rinen0721-llama0911-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama0911-v1/special_tokens_map.json
rinen0721-llama0911-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama0911-v1/tokenizer_config.json
rinen0721-llama0911-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama0911-v1/tokenizer.json
rinen0721-llama0911-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 53.49it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 84.33it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 78.26it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 80.84it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 78.11it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 82.84it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:02, 85.42it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:08, 25.16it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 28.86it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 39.39it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 45.35it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 51.73it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 60.13it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 65.01it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 68.61it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 79.93it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 78.34it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:01, 85.23it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 24.29it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 34.61it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 40.31it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 48.67it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 52.78it/s]
Loading 0:  88%|████████▊ | 256/291 [00:04<00:00, 65.07it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 66.21it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 71.76it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 73.63it/s]
                                                            

Job rinen0721-llama0911-v1-mkmlizer completed after 87.92s with status: succeeded
Stopping job with name rinen0721-llama0911-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.14s
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 rinen0721-llama0911-v1
Waiting for inference service rinen0721-llama0911-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rinen0721-llama0911-v1 ready after 161.1046769618988s
Pipeline stage MKMLDeployer completed in 162.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1496355533599854s
Received healthy response to inference request in 1.61346435546875s
Received healthy response to inference request in 1.9532485008239746s
Received healthy response to inference request in 1.5158395767211914s
Received healthy response to inference request in 1.5429680347442627s
5 requests
0 failed requests
5th percentile: 1.5212652683258057
10th percentile: 1.52669095993042
20th percentile: 1.5375423431396484
30th percentile: 1.55706729888916
40th percentile: 1.585265827178955
50th percentile: 1.61346435546875
60th percentile: 1.7493780136108399
70th percentile: 1.8852916717529296
80th percentile: 1.9925259113311768
90th percentile: 2.071080732345581
95th percentile: 2.110358142852783
99th percentile: 2.141780071258545
mean time: 1.755031204223633
Pipeline stage StressChecker completed in 9.49s
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 5.60s
Shutdown handler de-registered
rinen0721-llama0911_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 0.11s
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 rinen0721-llama0911-v1-profiler
Waiting for inference service rinen0721-llama0911-v1-profiler to be ready
Inference service rinen0721-llama0911-v1-profiler ready after 160.38534474372864s
Pipeline stage MKMLProfilerDeployer completed in 160.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rinen0721-llama0911-v1-profiler-predictor-00001-deploymentqmcdt:/code/chaiverse_profiler_1726035482 --namespace tenant-chaiml-guanaco
kubectl exec -it rinen0721-llama0911-v1-profiler-predictor-00001-deploymentqmcdt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726035482 && 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_1726035482/summary.json'
kubectl exec -it rinen0721-llama0911-v1-profiler-predictor-00001-deploymentqmcdt --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726035482/summary.json'
Pipeline stage MKMLProfilerRunner completed in 837.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rinen0721-llama0911-v1-profiler is running
Tearing down inference service rinen0721-llama0911-v1-profiler
Service rinen0721-llama0911-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.72s
Shutdown handler de-registered
rinen0721-llama0911_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-llama0911_v1 status is now torndown due to DeploymentManager action