rica40325-feedback-dpo-3

developer_uid: rica40325

submission_id: rica40325-feedback-dpo-3_v1

model_name: rica40325-feedback-dpo-3_v1

model_group: rica40325/feedback_dpo_3

status: torndown

timestamp: 2024-09-10T05:58:30+00:00

num_battles: 11391

num_wins: 4777

celo_rating: 1165.11

family_friendly_score: 0.0

submission_type: basic

model_repo: rica40325/feedback_dpo_3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.902065042627818, 'latency_mean': 1.1084728825092316, 'latency_p50': 1.1136852502822876, 'latency_p90': 1.2351430416107176}, {'batch_size': 4, 'throughput': 1.8139013072129833, 'latency_mean': 2.1916801702976225, 'latency_p50': 2.1794809103012085, 'latency_p90': 2.4637901544570924}, {'batch_size': 5, 'throughput': 1.8901422589025647, 'latency_mean': 2.6295800960063933, 'latency_p50': 2.622322916984558, 'latency_p90': 2.926296925544739}, {'batch_size': 8, 'throughput': 2.038399407524855, 'latency_mean': 3.8968724513053896, 'latency_p50': 3.8806627988815308, 'latency_p90': 4.349859404563904}, {'batch_size': 10, 'throughput': 2.0323493963023638, 'latency_mean': 4.876366269588471, 'latency_p50': 4.860754132270813, 'latency_p90': 5.85842649936676}, {'batch_size': 12, 'throughput': 2.054446855234875, 'latency_mean': 5.763219541311264, 'latency_p50': 5.889389991760254, 'latency_p90': 6.60491042137146}, {'batch_size': 15, 'throughput': 2.066638307552604, 'latency_mean': 7.11609249830246, 'latency_p50': 7.228039741516113, 'latency_p90': 7.948485589027404}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-feedback-dpo-3_v1

is_internal_developer: False

language_model: rica40325/feedback_dpo_3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.04

us_pacific_date: 2024-09-09

win_ratio: 0.41936616627161794

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-dpo-3-v1-mkmlizer
Waiting for job on rica40325-feedback-dpo-3-v1-mkmlizer to finish
rica40325-feedback-dpo-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-dpo-3-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║       /___/                                                         ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-feedback-dpo-3-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-dpo-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedback-dpo-3-v1-mkmlizer: Downloaded to shared memory in 63.062s
rica40325-feedback-dpo-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1j8g1pqt, device:0
rica40325-feedback-dpo-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedback-dpo-3-v1-mkmlizer: quantized model in 29.176s
rica40325-feedback-dpo-3-v1-mkmlizer: Processed model rica40325/feedback_dpo_3 in 92.238s
rica40325-feedback-dpo-3-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-dpo-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-dpo-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-dpo-3-v1
rica40325-feedback-dpo-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-dpo-3-v1/config.json
rica40325-feedback-dpo-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-dpo-3-v1/special_tokens_map.json
rica40325-feedback-dpo-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-dpo-3-v1/tokenizer_config.json
rica40325-feedback-dpo-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-dpo-3-v1/tokenizer.json
rica40325-feedback-dpo-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedback-dpo-3-v1/flywheel_model.0.safetensors
rica40325-feedback-dpo-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.65it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 34.83it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.44it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 35.06it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.58it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 36.93it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:09, 25.78it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:09, 26.99it/s]
Loading 0:  14%|█▍        | 42/291 [00:01<00:09, 25.91it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.71it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.11it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.22it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.51it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.29it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.32it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.82it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.77it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.52it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.30it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.43it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.67it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.96it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 30.95it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.66it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 31.97it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 36.28it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 34.46it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.34it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.21it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.60it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.76it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.23it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 34.58it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 32.58it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.15it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.10it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.22it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 32.94it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 36.22it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:04, 25.51it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 26.41it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:04, 23.52it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.94it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.23it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 32.81it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 31.66it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 34.88it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.28it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 32.48it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 32.33it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.16it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.15it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 31.21it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 30.41it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.44it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 32.26it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.22it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.43it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 34.54it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 32.56it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 32.73it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.22it/s]
                                                            
Job rica40325-feedback-dpo-3-v1-mkmlizer completed after 115.67s with status: succeeded
Stopping job with name rica40325-feedback-dpo-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-dpo-3-v1
Waiting for inference service rica40325-feedback-dpo-3-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-feedback-dpo-3-v1 ready after 161.14144134521484s
Pipeline stage MKMLDeployer completed in 161.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.433790922164917s
Received healthy response to inference request in 1.5320236682891846s
Received healthy response to inference request in 2.697145938873291s
Received healthy response to inference request in 3.0879430770874023s
Received healthy response to inference request in 1.7186615467071533s
5 requests
0 failed requests
5th percentile: 1.5693512439727784
10th percentile: 1.6066788196563722
20th percentile: 1.6813339710235595
30th percentile: 1.861687421798706
40th percentile: 2.1477391719818115
50th percentile: 2.433790922164917
60th percentile: 2.5391329288482667
70th percentile: 2.6444749355316164
80th percentile: 2.7753053665161134
90th percentile: 2.9316242218017576
95th percentile: 3.00978364944458
99th percentile: 3.0723111915588377
mean time: 2.2939130306243896
Pipeline stage StressChecker completed in 12.85s
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 5.20s
Shutdown handler de-registered
rica40325-feedback-dpo-3_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-feedback-dpo-3-v1-profiler
Waiting for inference service rica40325-feedback-dpo-3-v1-profiler to be ready
Inference service rica40325-feedback-dpo-3-v1-profiler ready after 160.37533402442932s
Pipeline stage MKMLProfilerDeployer completed in 160.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-dpo-3-v1-profiler-predictor-00001-deplopflz4:/code/chaiverse_profiler_1725948410 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-dpo-3-v1-profiler-predictor-00001-deplopflz4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725948410 && 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_1725948410/summary.json'
kubectl exec -it rica40325-feedback-dpo-3-v1-profiler-predictor-00001-deplopflz4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725948410/summary.json'
Pipeline stage MKMLProfilerRunner completed in 834.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-dpo-3-v1-profiler is running
Tearing down inference service rica40325-feedback-dpo-3-v1-profiler
Service rica40325-feedback-dpo-3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.97s
Shutdown handler de-registered
rica40325-feedback-dpo-3_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-feedback-dpo-3_v1 status is now torndown due to DeploymentManager action