developer_uid: Riverise
submission_id: riverise-model-on-sonnet_v2
model_name: riverise-model-on-sonnet_v2
model_group: Riverise/model_on_sonnet
status: torndown
timestamp: 2024-08-30T11:51:29+00:00
num_battles: 10950
num_wins: 5569
celo_rating: 1240.81
family_friendly_score: 0.0
submission_type: basic
model_repo: Riverise/model_on_sonnet
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: riverise-model-on-sonnet_v2
is_internal_developer: False
language_model: Riverise/model_on_sonnet
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-30
win_ratio: 0.5085844748858448
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 riverise-model-on-sonnet-v2-mkmlizer
Waiting for job on riverise-model-on-sonnet-v2-mkmlizer to finish
Stopping job with name riverise-model-on-sonnet-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-model-on-sonnet-v2-mkmlizer
Waiting for job on riverise-model-on-sonnet-v2-mkmlizer to finish
riverise-model-on-sonnet-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-model-on-sonnet-v2-mkmlizer: ║     _____            __           __                                ║
riverise-model-on-sonnet-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-model-on-sonnet-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-model-on-sonnet-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-model-on-sonnet-v2-mkmlizer: ║       /___/                                                         ║
riverise-model-on-sonnet-v2-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-model-on-sonnet-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-model-on-sonnet-v2-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-model-on-sonnet-v2-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-model-on-sonnet-v2-mkmlizer: ║  belonging to:                                                      ║
riverise-model-on-sonnet-v2-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v2-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-model-on-sonnet-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-model-on-sonnet-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-model-on-sonnet-v2-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-model-on-sonnet-v2-mkmlizer: Downloaded to shared memory in 21.142s
riverise-model-on-sonnet-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoa_dbi__, device:0
riverise-model-on-sonnet-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-model-on-sonnet-v2-mkmlizer: creating bucket guanaco-mkml-models
riverise-model-on-sonnet-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-model-on-sonnet-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-model-on-sonnet-v2
riverise-model-on-sonnet-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v2/config.json
riverise-model-on-sonnet-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v2/tokenizer_config.json
riverise-model-on-sonnet-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v2/special_tokens_map.json
riverise-model-on-sonnet-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v2/tokenizer.json
riverise-model-on-sonnet-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-model-on-sonnet-v2/flywheel_model.0.safetensors
riverise-model-on-sonnet-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 51.54it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 65.21it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 72.32it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 86.64it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:02, 93.40it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 83.61it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 84.23it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 81.84it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 22.37it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 28.18it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 34.45it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 42.13it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.87it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:02, 57.51it/s]
Loading 0:  49%|████▉     | 143/291 [00:02<00:02, 64.23it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 74.00it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 76.95it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 79.89it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 77.05it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:04, 22.43it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 28.27it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 34.99it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 42.18it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 47.13it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 54.20it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 61.19it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 65.68it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 73.75it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 74.96it/s]
Loading 0:  98%|█████████▊| 284/291 [00:05<00:00, 74.89it/s]
                                                            

Job riverise-model-on-sonnet-v2-mkmlizer completed after 74.03s with status: succeeded
Stopping job with name riverise-model-on-sonnet-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service riverise-model-on-sonnet-v2
Waiting for inference service riverise-model-on-sonnet-v2 to be ready
Inference service riverise-model-on-sonnet-v2 ready after 181.1411371231079s
Pipeline stage ISVCDeployer completed in 181.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2625133991241455s
Received healthy response to inference request in 1.819676399230957s
Received healthy response to inference request in 1.7057764530181885s
Received healthy response to inference request in 1.5428667068481445s
Received healthy response to inference request in 2.271233081817627s
5 requests
0 failed requests
5th percentile: 1.5754486560821532
10th percentile: 1.6080306053161622
20th percentile: 1.6731945037841798
30th percentile: 1.7285564422607422
40th percentile: 1.7741164207458495
50th percentile: 1.819676399230957
60th percentile: 1.9968111991882325
70th percentile: 2.173945999145508
80th percentile: 2.2642573356628417
90th percentile: 2.2677452087402346
95th percentile: 2.2694891452789308
99th percentile: 2.2708842945098877
mean time: 1.9204132080078125
Pipeline stage StressChecker completed in 10.61s
riverise-model-on-sonnet_v2 status is now deployed due to DeploymentManager action
riverise-model-on-sonnet_v2 status is now inactive due to auto deactivation removed underperforming models
riverise-model-on-sonnet_v2 status is now torndown due to DeploymentManager action