rinen0721-llama-defaultconfig

developer_uid: rinen0721

submission_id: rinen0721-llama-defaultconfig_v1

model_name: rinen0721-llama-defaultconfig_v1

model_group: rinen0721/llama-DefaultC

status: torndown

timestamp: 2024-08-27T13:48:13+00:00

num_battles: 12749

num_wins: 6121

celo_rating: 1222.97

family_friendly_score: 0.0

submission_type: basic

model_repo: rinen0721/llama-DefaultConfig

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: rinen0721-llama-defaultconfig_v1

is_internal_developer: False

language_model: rinen0721/llama-DefaultConfig

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-27

win_ratio: 0.4801160875362774

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

Running pipeline stage MKMLizer
Starting job with name rinen0721-llama-defaultconfig-v1-mkmlizer
Waiting for job on rinen0721-llama-defaultconfig-v1-mkmlizer to finish
rinen0721-llama-defaultconfig-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama-defaultconfig-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║                                                                     ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║                                                                     ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║                                                                     ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ║                                                                     ║
rinen0721-llama-defaultconfig-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama-defaultconfig-v1-mkmlizer: Downloaded to shared memory in 36.745s
rinen0721-llama-defaultconfig-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4bp3l19y, device:0
rinen0721-llama-defaultconfig-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama-defaultconfig-v1-mkmlizer: quantized model in 25.902s
rinen0721-llama-defaultconfig-v1-mkmlizer: Processed model rinen0721/llama-DefaultConfig in 62.647s
rinen0721-llama-defaultconfig-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama-defaultconfig-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-llama-defaultconfig-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-llama-defaultconfig-v1
rinen0721-llama-defaultconfig-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama-defaultconfig-v1/config.json
rinen0721-llama-defaultconfig-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama-defaultconfig-v1/special_tokens_map.json
rinen0721-llama-defaultconfig-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama-defaultconfig-v1/tokenizer_config.json
rinen0721-llama-defaultconfig-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama-defaultconfig-v1/tokenizer.json
rinen0721-llama-defaultconfig-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama-defaultconfig-v1/flywheel_model.0.safetensors
rinen0721-llama-defaultconfig-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 49.14it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 83.56it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 85.72it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 86.03it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:02, 93.86it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 85.92it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 83.01it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 78.58it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:09, 20.47it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 24.94it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 32.37it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 40.19it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 50.12it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:02, 59.60it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:02, 65.65it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 65.46it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 65.91it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 67.74it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 68.96it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 20.82it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 26.82it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 33.67it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 46.54it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 53.26it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 58.86it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 63.09it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 63.31it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 64.01it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 68.79it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 69.30it/s]
Loading 0: 100%|██████████| 291/291 [00:10<00:00,  5.18it/s]
                                                            
Job rinen0721-llama-defaultconfig-v1-mkmlizer completed after 83.81s with status: succeeded
Stopping job with name rinen0721-llama-defaultconfig-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service rinen0721-llama-defaultconfig-v1
Waiting for inference service rinen0721-llama-defaultconfig-v1 to be ready
Inference service rinen0721-llama-defaultconfig-v1 ready after 170.38975977897644s
Pipeline stage ISVCDeployer completed in 170.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9749488830566406s
Received healthy response to inference request in 2.002502202987671s
Received healthy response to inference request in 1.7747712135314941s
Received healthy response to inference request in 1.705322027206421s
Received healthy response to inference request in 2.056396722793579s
5 requests
0 failed requests
5th percentile: 1.7192118644714356
10th percentile: 1.7331017017364503
20th percentile: 1.7608813762664794
30th percentile: 1.8148067474365235
40th percentile: 1.894877815246582
50th percentile: 1.9749488830566406
60th percentile: 1.9859702110290527
70th percentile: 1.9969915390014648
80th percentile: 2.0132811069488525
90th percentile: 2.034838914871216
95th percentile: 2.0456178188323975
99th percentile: 2.0542409420013428
mean time: 1.9027882099151612
Pipeline stage StressChecker completed in 10.17s
rinen0721-llama-defaultconfig_v1 status is now deployed due to DeploymentManager action
rinen0721-llama-defaultconfig_v1 status is now inactive due to auto deactivation removed underperforming models
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
rinen0721-llama-defaultconfig_v1 status is now torndown due to DeploymentManager action