rinen0721-llama0903-e2

developer_uid: rinen0721

submission_id: rinen0721-llama0903-e2_v1

model_name: rinen0721-llama0903-e2_v1

model_group: rinen0721/llama0903-e2

status: torndown

timestamp: 2024-09-03T02:23:00+00:00

num_battles: 13169

num_wins: 6154

celo_rating: 1217.28

family_friendly_score: 0.0

submission_type: basic

model_repo: rinen0721/llama0903-e2

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: rinen0721-llama0903-e2_v1

is_internal_developer: False

language_model: rinen0721/llama0903-e2

model_size: 8B

ranking_group: single

us_pacific_date: 2024-09-02

win_ratio: 0.4673095907054446

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

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rinen0721-llama0903-e2-v1-mkmlizer
Waiting for job on rinen0721-llama0903-e2-v1-mkmlizer to finish
rinen0721-llama0903-e2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama0903-e2-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama0903-e2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama0903-e2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama0903-e2-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama0903-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama0903-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama0903-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama0903-e2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama0903-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0903-e2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
rinen0721-llama0903-e2-v1-mkmlizer: Downloaded to shared memory in 36.452s
rinen0721-llama0903-e2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5a_6tzso, device:0
rinen0721-llama0903-e2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama0903-e2-v1-mkmlizer: quantized model in 26.840s
rinen0721-llama0903-e2-v1-mkmlizer: Processed model rinen0721/llama0903-e2 in 63.293s
rinen0721-llama0903-e2-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama0903-e2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama0903-e2-v1/config.json
rinen0721-llama0903-e2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama0903-e2-v1/special_tokens_map.json
rinen0721-llama0903-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama0903-e2-v1/tokenizer_config.json
rinen0721-llama0903-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama0903-e2-v1/tokenizer.json
rinen0721-llama0903-e2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama0903-e2-v1/flywheel_model.0.safetensors
rinen0721-llama0903-e2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 44.10it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 76.90it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 68.76it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 68.74it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 66.83it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 70.85it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 75.77it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 74.95it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 20.10it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:08, 22.79it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 27.41it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 34.27it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 41.84it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.49it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 52.50it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 59.96it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 63.62it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 64.49it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 66.39it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 68.50it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 20.29it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 25.38it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 31.31it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:01, 38.75it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.67it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 50.37it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 55.05it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 61.66it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 67.90it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 70.82it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 70.77it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 42.22it/s]
                                                            
Job rinen0721-llama0903-e2-v1-mkmlizer completed after 84.65s with status: succeeded
Stopping job with name rinen0721-llama0903-e2-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.48s
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-llama0903-e2-v1
Waiting for inference service rinen0721-llama0903-e2-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
Inference service rinen0721-llama0903-e2-v1 ready after 150.9241440296173s
Pipeline stage MKMLDeployer completed in 151.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9270460605621338s
Received healthy response to inference request in 2.0804355144500732s
Received healthy response to inference request in 2.010868787765503s
Received healthy response to inference request in 2.2605059146881104s
Received healthy response to inference request in 1.670419692993164s
5 requests
0 failed requests
5th percentile: 1.721744966506958
10th percentile: 1.7730702400207519
20th percentile: 1.8757207870483399
30th percentile: 1.9438106060028075
40th percentile: 1.9773396968841552
50th percentile: 2.010868787765503
60th percentile: 2.038695478439331
70th percentile: 2.066522169113159
80th percentile: 2.1164495944976807
90th percentile: 2.1884777545928955
95th percentile: 2.224491834640503
99th percentile: 2.2533030986785887
mean time: 1.9898551940917968
Pipeline stage StressChecker completed in 10.85s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.37s
rinen0721-llama0903-e2_v1 status is now deployed due to DeploymentManager action
run pipeline %s
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 rinen0721-llama0903-e2-v1-profiler
Waiting for inference service rinen0721-llama0903-e2-v1-profiler to be ready
Inference service rinen0721-llama0903-e2-v1-profiler ready after 150.33795976638794s
Pipeline stage MKMLProfilerDeployer completed in 150.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rinen0721-llama0903-e2-v1-profiler-predictor-00001-deploymdjpc2:/code/chaiverse_profiler_1725330625 --namespace tenant-chaiml-guanaco
kubectl exec -it rinen0721-llama0903-e2-v1-profiler-predictor-00001-deploymdjpc2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725330625 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --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_1725330625/summary.json'
rinen0721-llama0903-e2_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-llama0903-e2_v1 status is now torndown due to DeploymentManager action