rica40325-lora32-secend

submission_id: rica40325-lora32-secend_v4

developer_uid: rica40325

best_of: 16

celo_rating: 1250.69

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': 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_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: 11101

num_wins: 5805

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-08-30T12:01:48+00:00

us_pacific_date: 2024-08-30

win_ratio: 0.5229258625349068

Resubmit model

Running pipeline stage MKMLizer
Starting job with name rica40325-lora32-secend-v4-mkmlizer
Waiting for job on rica40325-lora32-secend-v4-mkmlizer to finish
Stopping job with name rica40325-lora32-secend-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-lora32-secend-v4-mkmlizer
Waiting for job on rica40325-lora32-secend-v4-mkmlizer to finish
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
Failed to get response for submission blend_jidor_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43680->127.0.0.1:8080: read: connection reset by peer\n')
rica40325-lora32-secend-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-secend-v4-mkmlizer: ║     _____            __           __                                ║
rica40325-lora32-secend-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-lora32-secend-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-lora32-secend-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-lora32-secend-v4-mkmlizer: ║       /___/                                                         ║
rica40325-lora32-secend-v4-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-lora32-secend-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-lora32-secend-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-lora32-secend-v4-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-lora32-secend-v4-mkmlizer: ║  belonging to:                                                      ║
rica40325-lora32-secend-v4-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-lora32-secend-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-lora32-secend-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-lora32-secend-v4-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-lora32-secend-v4-mkmlizer: Downloaded to shared memory in 20.892s
rica40325-lora32-secend-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu5x4_r3t, device:0
rica40325-lora32-secend-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-lora32-secend-v4-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-secend-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-secend-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-secend-v4
rica40325-lora32-secend-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v4/config.json
rica40325-lora32-secend-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-secend-v4/special_tokens_map.json
rica40325-lora32-secend-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v4/tokenizer_config.json
rica40325-lora32-secend-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-secend-v4/tokenizer.json
rica40325-lora32-secend-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-secend-v4/flywheel_model.0.safetensors
rica40325-lora32-secend-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 36.32it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 59.19it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 73.36it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 73.50it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 86.99it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 89.27it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 87.85it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 83.66it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 22.22it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 32.51it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 37.43it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 43.56it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 53.07it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 66.76it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 72.90it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 81.59it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 80.03it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 25.37it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 31.10it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 35.83it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 41.80it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 52.53it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 57.85it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 68.89it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 69.43it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 74.70it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 75.03it/s]
                                                            
Job rica40325-lora32-secend-v4-mkmlizer completed after 63.95s with status: succeeded
Stopping job with name rica40325-lora32-secend-v4-mkmlizer
Pipeline stage MKMLizer completed in 66.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service rica40325-lora32-secend-v4
Waiting for inference service rica40325-lora32-secend-v4 to be ready
Inference service rica40325-lora32-secend-v4 ready after 180.867041349411s
Pipeline stage ISVCDeployer completed in 181.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2631380558013916s
Received healthy response to inference request in 1.3647301197052002s
Received healthy response to inference request in 1.9479727745056152s
Received healthy response to inference request in 1.7366909980773926s
Received healthy response to inference request in 2.7884325981140137s
5 requests
0 failed requests
5th percentile: 1.4391222953796388
10th percentile: 1.513514471054077
20th percentile: 1.662298822402954
30th percentile: 1.778947353363037
40th percentile: 1.8634600639343262
50th percentile: 1.9479727745056152
60th percentile: 2.0740388870239257
70th percentile: 2.200104999542236
80th percentile: 2.368196964263916
90th percentile: 2.578314781188965
95th percentile: 2.6833736896514893
99th percentile: 2.7674208164215086
mean time: 2.0201929092407225
Pipeline stage StressChecker completed in 11.29s
rica40325-lora32-secend_v4 status is now deployed due to DeploymentManager action
rica40325-lora32-secend_v4 status is now inactive due to auto deactivation removed underperforming models
rica40325-lora32-secend_v4 status is now torndown due to DeploymentManager action