rica40325-lora32-secend

submission_id: rica40325-lora32-secend_v3

developer_uid: rica40325

best_of: 16

celo_rating: 1253.67

display_name: rica40325-lora32-secend_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': 0.95, '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_secend

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rica40325/lora32_secend

model_name: rica40325-lora32-secend_v1

model_num_parameters: 8030261248.0

model_repo: rica40325/lora32_secend

model_size: 8B

num_battles: 11475

num_wins: 6043

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-08-30T10:37:30+00:00

us_pacific_date: 2024-08-30

win_ratio: 0.5266230936819172

Resubmit model

Running pipeline stage MKMLizer
Starting job with name rica40325-lora32-secend-v3-mkmlizer
Waiting for job on rica40325-lora32-secend-v3-mkmlizer to finish
Stopping job with name rica40325-lora32-secend-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-lora32-secend-v3-mkmlizer
Waiting for job on rica40325-lora32-secend-v3-mkmlizer to finish
rica40325-lora32-secend-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-secend-v3-mkmlizer: ║     _____            __           __                                ║
rica40325-lora32-secend-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-lora32-secend-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-lora32-secend-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-lora32-secend-v3-mkmlizer: ║       /___/                                                         ║
rica40325-lora32-secend-v3-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-lora32-secend-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-lora32-secend-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-lora32-secend-v3-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-lora32-secend-v3-mkmlizer: ║  belonging to:                                                      ║
rica40325-lora32-secend-v3-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-lora32-secend-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-lora32-secend-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-lora32-secend-v3-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-lora32-secend-v3-mkmlizer: Downloaded to shared memory in 21.041s
rica40325-lora32-secend-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_i9fjmie, device:0
rica40325-lora32-secend-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-lora32-secend-v3-mkmlizer: quantized model in 26.047s
rica40325-lora32-secend-v3-mkmlizer: Processed model rica40325/lora32_secend in 47.089s
rica40325-lora32-secend-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-secend-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-secend-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-secend-v3
rica40325-lora32-secend-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-secend-v3/special_tokens_map.json
rica40325-lora32-secend-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v3/config.json
rica40325-lora32-secend-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v3/tokenizer_config.json
rica40325-lora32-secend-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-secend-v3/tokenizer.json
rica40325-lora32-secend-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-secend-v3/flywheel_model.0.safetensors
rica40325-lora32-secend-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.07it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 73.33it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 79.91it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 74.10it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 78.19it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 93.26it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 87.44it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 86.97it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 22.42it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 27.96it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.54it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 44.85it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 51.25it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 53.75it/s]
Loading 0:  52%|█████▏    | 150/291 [00:02<00:02, 64.50it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 67.30it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:01, 74.48it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:01, 74.87it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:04, 21.47it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 26.17it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 38.27it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 44.39it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 51.39it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 60.28it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 63.97it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 76.48it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 76.13it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 75.06it/s]
                                                            
Job rica40325-lora32-secend-v3-mkmlizer completed after 73.94s with status: succeeded
Stopping job with name rica40325-lora32-secend-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.20s
Running pipeline stage ISVCDeployer
Creating inference service rica40325-lora32-secend-v3
Waiting for inference service rica40325-lora32-secend-v3 to be ready
Inference service rica40325-lora32-secend-v3 ready after 202.36908197402954s
Pipeline stage ISVCDeployer completed in 204.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.974496841430664s
Received healthy response to inference request in 2.101987838745117s
Received healthy response to inference request in 2.1300268173217773s
Received healthy response to inference request in 1.7711069583892822s
Received healthy response to inference request in 1.4288458824157715s
5 requests
0 failed requests
5th percentile: 1.4972980976104737
10th percentile: 1.5657503128051757
20th percentile: 1.70265474319458
30th percentile: 1.8372831344604492
40th percentile: 1.9696354866027832
50th percentile: 2.101987838745117
60th percentile: 2.113203430175781
70th percentile: 2.124419021606445
80th percentile: 2.298920822143555
90th percentile: 2.6367088317871095
95th percentile: 2.8056028366088865
99th percentile: 2.9407180404663085
mean time: 2.0812928676605225
Pipeline stage StressChecker completed in 11.59s
rica40325-lora32-secend_v3 status is now deployed due to DeploymentManager action
rica40325-lora32-secend_v3 status is now inactive due to auto deactivation removed underperforming models
rica40325-lora32-secend_v3 status is now torndown due to DeploymentManager action