submission_id: rinen0721-llama0901_v1
developer_uid: rinen0721
alignment_samples: 12069
alignment_score: -0.3388006482891096
best_of: 16
celo_rating: 1222.27
display_name: rinen0721-llama0901_v1
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}
is_internal_developer: False
language_model: rinen0721/llama0901
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rinen0721/llama0901
model_name: rinen0721-llama0901_v1
model_num_parameters: 8030261248.0
model_repo: rinen0721/llama0901
model_size: 8B
num_battles: 12069
num_wins: 5788
propriety_score: 0.7387914230019493
propriety_total_count: 1026.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-01T03:50:01+00:00
us_pacific_date: 2024-08-31
win_ratio: 0.4795757726406496
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rinen0721-llama0901-v1-mkmlizer
Waiting for job on rinen0721-llama0901-v1-mkmlizer to finish
Stopping job with name rinen0721-llama0901-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name rinen0721-llama0901-v1-mkmlizer
Waiting for job on rinen0721-llama0901-v1-mkmlizer to finish
rinen0721-llama0901-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama0901-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama0901-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama0901-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama0901-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama0901-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama0901-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rinen0721-llama0901-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama0901-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama0901-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama0901-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama0901-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama0901-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama0901-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama0901-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama0901-v1-mkmlizer: quantized model in 26.402s
rinen0721-llama0901-v1-mkmlizer: Processed model rinen0721/llama0901 in 62.268s
rinen0721-llama0901-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama0901-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-llama0901-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-llama0901-v1
rinen0721-llama0901-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama0901-v1/config.json
rinen0721-llama0901-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama0901-v1/special_tokens_map.json
rinen0721-llama0901-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama0901-v1/tokenizer_config.json
rinen0721-llama0901-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama0901-v1/tokenizer.json
rinen0721-llama0901-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama0901-v1/flywheel_model.0.safetensors
rinen0721-llama0901-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.58it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 68.56it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 66.58it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 65.07it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 68.86it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 71.31it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 76.29it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 79.05it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 76.89it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:09, 21.00it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 24.69it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:06, 30.47it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 36.70it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 44.89it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.92it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 58.13it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 64.25it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 70.08it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 69.52it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 69.53it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 72.67it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 20.98it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 23.81it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 29.02it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 35.68it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.05it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 49.75it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 57.50it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 62.73it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 64.37it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 69.26it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 73.07it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 75.84it/s]
                                                            

Job rinen0721-llama0901-v1-mkmlizer completed after 85.28s with status: succeeded
Stopping job with name rinen0721-llama0901-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.33s
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-llama0901-v1
Waiting for inference service rinen0721-llama0901-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
Inference service rinen0721-llama0901-v1 ready after 190.91001272201538s
Pipeline stage MKMLDeployer completed in 191.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4560253620147705s
Received healthy response to inference request in 1.821012258529663s
Received healthy response to inference request in 1.9362874031066895s
Received healthy response to inference request in 1.65543532371521s
Received healthy response to inference request in 1.4217309951782227s
5 requests
0 failed requests
5th percentile: 1.4684718608856202
10th percentile: 1.5152127265930175
20th percentile: 1.6086944580078124
30th percentile: 1.6885507106781006
40th percentile: 1.7547814846038818
50th percentile: 1.821012258529663
60th percentile: 1.8671223163604735
70th percentile: 1.9132323741912842
80th percentile: 2.240234994888306
90th percentile: 2.8481301784515383
95th percentile: 3.152077770233154
99th percentile: 3.395235843658447
mean time: 2.0580982685089113
Pipeline stage StressChecker completed in 11.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.74s
rinen0721-llama0901_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-llama0901-v1-profiler
Waiting for inference service rinen0721-llama0901-v1-profiler to be ready
Inference service rinen0721-llama0901-v1-profiler ready after 190.42838859558105s
Pipeline stage MKMLProfilerDeployer completed in 190.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rinen0721-llama0901-v1-profiler is running
Tearing down inference service rinen0721-llama0901-v1-profiler
Service rinen0721-llama0901-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.89s
rinen0721-llama0901_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics