rica40325-feedback-retry

developer_uid: rica40325

submission_id: rica40325-feedback-retry_v1

model_name: rica40325-feedback-retry_v1

model_group: rica40325/feedback_retry

status: torndown

timestamp: 2024-09-07T06:48:22+00:00

num_battles: 12201

num_wins: 6242

celo_rating: 1249.34

family_friendly_score: 0.0

submission_type: basic

model_repo: rica40325/feedback_retry

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.9119415556275932, 'latency_mean': 1.0965008628368378, 'latency_p50': 1.0901466608047485, 'latency_p90': 1.2291062593460083}, {'batch_size': 4, 'throughput': 1.818204690889935, 'latency_mean': 2.183892914056778, 'latency_p50': 2.1910877227783203, 'latency_p90': 2.4448729276657106}, {'batch_size': 5, 'throughput': 1.8965576534720263, 'latency_mean': 2.621624330282211, 'latency_p50': 2.6042264699935913, 'latency_p90': 2.9383231163024903}, {'batch_size': 8, 'throughput': 2.017273157277461, 'latency_mean': 3.9296420085430146, 'latency_p50': 3.939175248146057, 'latency_p90': 4.439392185211181}, {'batch_size': 10, 'throughput': 2.0500496492489266, 'latency_mean': 4.827016301155091, 'latency_p50': 4.804193377494812, 'latency_p90': 5.67978184223175}, {'batch_size': 12, 'throughput': 2.041101604790579, 'latency_mean': 5.7965815794467925, 'latency_p50': 5.803443908691406, 'latency_p90': 6.753988862037659}, {'batch_size': 15, 'throughput': 2.067808479448717, 'latency_mean': 7.0866993403434755, 'latency_p50': 7.227775573730469, 'latency_p90': 7.877237772941589}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-feedback-retry_v1

is_internal_developer: False

language_model: rica40325/feedback_retry

model_size: 8B

ranking_group: single

throughput_3p7s: 2.02

us_pacific_date: 2024-09-06

win_ratio: 0.5115974100483567

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-feedback-retry-v1-mkmlizer
Waiting for job on rica40325-feedback-retry-v1-mkmlizer to finish
rica40325-feedback-retry-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-retry-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-feedback-retry-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-feedback-retry-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-feedback-retry-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-feedback-retry-v1-mkmlizer: ║       /___/                                                         ║
rica40325-feedback-retry-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-feedback-retry-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-feedback-retry-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-feedback-retry-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-feedback-retry-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-feedback-retry-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-feedback-retry-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-feedback-retry-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-feedback-retry-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedback-retry-v1-mkmlizer: Downloaded to shared memory in 65.734s
rica40325-feedback-retry-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm152lqk8, device:0
rica40325-feedback-retry-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedback-retry-v1-mkmlizer: quantized model in 28.804s
rica40325-feedback-retry-v1-mkmlizer: Processed model rica40325/feedback_retry in 94.538s
rica40325-feedback-retry-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-retry-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-retry-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-retry-v1
rica40325-feedback-retry-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-retry-v1/config.json
rica40325-feedback-retry-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-retry-v1/special_tokens_map.json
rica40325-feedback-retry-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-retry-v1/tokenizer_config.json
rica40325-feedback-retry-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-retry-v1/tokenizer.json
rica40325-feedback-retry-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedback-retry-v1/flywheel_model.0.safetensors
rica40325-feedback-retry-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.75it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.35it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 33.90it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.98it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.14it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:07, 35.13it/s]
Loading 0:  11%|█▏        | 33/291 [00:01<00:09, 26.46it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 23.65it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.67it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.87it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.26it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 33.65it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 32.94it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.16it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.93it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.39it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.42it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.94it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 27.50it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.69it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.66it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.21it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 30.84it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.79it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.67it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.19it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.18it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.84it/s]
Loading 0:  45%|████▌     | 132/291 [00:04<00:04, 39.13it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 27.03it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 25.98it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 31.51it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.67it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 34.36it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 32.91it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.45it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.48it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.15it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.14it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 36.96it/s]
Loading 0:  64%|██████▍   | 187/291 [00:05<00:03, 27.12it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 27.90it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 26.50it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.78it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.61it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.04it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 31.18it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 33.48it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.56it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 33.32it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.62it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.74it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.50it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 32.24it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.03it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 35.32it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 33.09it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.29it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.03it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 34.79it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 33.35it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 32.56it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.61it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.23it/s]
                                                            
Job rica40325-feedback-retry-v1-mkmlizer completed after 116.79s with status: succeeded
Stopping job with name rica40325-feedback-retry-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-retry-v1
Waiting for inference service rica40325-feedback-retry-v1 to be ready
Inference service rica40325-feedback-retry-v1 ready after 150.81873989105225s
Pipeline stage MKMLDeployer completed in 151.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.09370756149292s
Received healthy response to inference request in 1.7786483764648438s
Received healthy response to inference request in 1.83674955368042s
Received healthy response to inference request in 2.3314459323883057s
Received healthy response to inference request in 2.043182373046875s
5 requests
0 failed requests
5th percentile: 1.790268611907959
10th percentile: 1.8018888473510741
20th percentile: 1.8251293182373047
30th percentile: 1.878036117553711
40th percentile: 1.960609245300293
50th percentile: 2.043182373046875
60th percentile: 2.063392448425293
70th percentile: 2.083602523803711
80th percentile: 2.141255235671997
90th percentile: 2.236350584030151
95th percentile: 2.2838982582092284
99th percentile: 2.32193639755249
mean time: 2.016746759414673
Pipeline stage StressChecker completed in 10.95s
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 5.55s
Shutdown handler de-registered
rica40325-feedback-retry_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 rica40325-feedback-retry-v1-profiler
Waiting for inference service rica40325-feedback-retry-v1-profiler to be ready
Inference service rica40325-feedback-retry-v1-profiler ready after 150.36371850967407s
Pipeline stage MKMLProfilerDeployer completed in 150.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-retry-v1-profiler-predictor-00001-deploqj4bx:/code/chaiverse_profiler_1725692186 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-retry-v1-profiler-predictor-00001-deploqj4bx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725692186 && 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_1725692186/summary.json'
kubectl exec -it rica40325-feedback-retry-v1-profiler-predictor-00001-deploqj4bx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725692186/summary.json'
Pipeline stage MKMLProfilerRunner completed in 833.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-retry-v1-profiler is running
Tearing down inference service rica40325-feedback-retry-v1-profiler
Service rica40325-feedback-retry-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
rica40325-feedback-retry_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-feedback-retry_v1 status is now torndown due to DeploymentManager action