rica40325-lora32-first

submission_id: rica40325-lora32-first_v2

developer_uid: rica40325

best_of: 16

celo_rating: 1258.93

display_name: rica40325-lora32-first_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': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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: rica40325/lora32_first

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rica40325/lora32_first

model_name: rica40325-lora32-first_v1

model_num_parameters: 8030261248.0

model_repo: rica40325/lora32_first

model_size: 8B

num_battles: 11389

num_wins: 6085

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-08-30T10:35:38+00:00

us_pacific_date: 2024-08-30

win_ratio: 0.5342874703661428

Resubmit model

Running pipeline stage MKMLizer
Starting job with name rica40325-lora32-first-v2-mkmlizer
Waiting for job on rica40325-lora32-first-v2-mkmlizer to finish
Stopping job with name rica40325-lora32-first-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-lora32-first-v2-mkmlizer
Waiting for job on rica40325-lora32-first-v2-mkmlizer to finish
rica40325-lora32-first-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-first-v2-mkmlizer: ║     _____            __           __                                ║
rica40325-lora32-first-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-lora32-first-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-lora32-first-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-lora32-first-v2-mkmlizer: ║       /___/                                                         ║
rica40325-lora32-first-v2-mkmlizer: ║                                                                     ║
rica40325-lora32-first-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-lora32-first-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-lora32-first-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-lora32-first-v2-mkmlizer: ║                                                                     ║
rica40325-lora32-first-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-lora32-first-v2-mkmlizer: ║  belonging to:                                                      ║
rica40325-lora32-first-v2-mkmlizer: ║                                                                     ║
rica40325-lora32-first-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-lora32-first-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-lora32-first-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-lora32-first-v2-mkmlizer: ║                                                                     ║
rica40325-lora32-first-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-lora32-first-v2-mkmlizer: Downloaded to shared memory in 20.693s
rica40325-lora32-first-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_hzayk8y, device:0
rica40325-lora32-first-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
rica40325-lora32-first-v2-mkmlizer: quantized model in 26.991s
rica40325-lora32-first-v2-mkmlizer: Processed model rica40325/lora32_first in 47.684s
rica40325-lora32-first-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-first-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-first-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-first-v2
rica40325-lora32-first-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-first-v2/config.json
rica40325-lora32-first-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-first-v2/special_tokens_map.json
rica40325-lora32-first-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-first-v2/tokenizer_config.json
rica40325-lora32-first-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-first-v2/tokenizer.json
rica40325-lora32-first-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-first-v2/flywheel_model.0.safetensors
rica40325-lora32-first-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 36.07it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.17it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 57.47it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 59.67it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 63.14it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 60.57it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 61.34it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 60.55it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 61.80it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:11, 18.08it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:10, 20.11it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 32.96it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 40.32it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.00it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 51.74it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 59.58it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 65.26it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 66.21it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 69.80it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 68.51it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 20.20it/s]
Loading 0:  67%|██████▋   | 196/291 [00:05<00:03, 25.68it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 31.05it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 35.92it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 41.56it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 46.71it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 50.35it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 53.79it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 56.54it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 57.77it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 57.02it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 58.10it/s]
                                                            
Job rica40325-lora32-first-v2-mkmlizer completed after 86.68s with status: succeeded
Stopping job with name rica40325-lora32-first-v2-mkmlizer
Pipeline stage MKMLizer completed in 89.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.27s
Running pipeline stage ISVCDeployer
Creating inference service rica40325-lora32-first-v2
Waiting for inference service rica40325-lora32-first-v2 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
Inference service rica40325-lora32-first-v2 ready after 291.5881290435791s
Pipeline stage ISVCDeployer completed in 291.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4790868759155273s
Received healthy response to inference request in 1.6766891479492188s
Received healthy response to inference request in 1.6142010688781738s
Received healthy response to inference request in 1.4483394622802734s
Received healthy response to inference request in 2.0781872272491455s
5 requests
0 failed requests
5th percentile: 1.4815117835998535
10th percentile: 1.5146841049194335
20th percentile: 1.5810287475585938
30th percentile: 1.6266986846923828
40th percentile: 1.6516939163208009
50th percentile: 1.6766891479492188
60th percentile: 1.8372883796691895
70th percentile: 1.9978876113891602
80th percentile: 2.158367156982422
90th percentile: 2.3187270164489746
95th percentile: 2.398906946182251
99th percentile: 2.463050889968872
mean time: 1.8593007564544677
Pipeline stage StressChecker completed in 10.21s
rica40325-lora32-first_v2 status is now deployed due to DeploymentManager action
rica40325-lora32-first_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-lora32-first_v2 status is now torndown due to DeploymentManager action