locutusque-apollo-0-2-ll_3902

developer_uid: Locutusque

submission_id: locutusque-apollo-0-2-ll_3902_v1

model_name: locutusque-apollo-0-2-ll_3902_v1

model_group: Locutusque/Apollo-0.2-Ll

status: torndown

timestamp: 2024-07-22T19:36:30+00:00

num_battles: 33830

num_wins: 3780

celo_rating: 786.47

family_friendly_score: 0.0

submission_type: basic

model_repo: Locutusque/Apollo-0.2-Llama-3-8B

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 1536

max_output_tokens: 64

display_name: locutusque-apollo-0-2-ll_3902_v1

is_internal_developer: False

language_model: Locutusque/Apollo-0.2-Llama-3-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-22

win_ratio: 0.11173514631983447

generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.05, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '<|end_of_text|>', '<|im_start|>'], 'max_input_tokens': 1536, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_tokens': 256}

formatter: {'memory_template': '<|im_start|>system\\n{memory}<|im_end|>\\n', 'prompt_template': '<|im_start|>user\\n{prompt}<|im_end|>\\n', 'bot_template': '<|im_start|>assistant\\n{bot_name}: {message}<|im_end|>\\n', 'user_template': '<|im_start|>user\\n{user_name}: {message}<|im_end|>\\n', 'response_template': '', 'truncate_by_message': False}

reward_formatter: {'bot_template': '<|im_start|>assistant\\n{bot_name}: {message}<|im_end|>\\n', 'memory_template': '<|im_start|>system\\n{memory}<|im_end|>\\n', 'prompt_template': '<|im_start|>user\\n{prompt}<|im_end|>\\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '<|im_start|>user\\n{user_name}: {message}<|im_end|>\\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name locutusque-apollo-0-2-ll-3902-v1-mkmlizer
Waiting for job on locutusque-apollo-0-2-ll-3902-v1-mkmlizer to finish
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║     _____            __           __                                ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║       /___/                                                         ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  Version: 0.9.5.post3                                               ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  https://mk1.ai                                                     ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  belonging to:                                                      ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  Chai Research Corp.                                                ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Downloaded to shared memory in 43.195s
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp73ktxlfx, device:0
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 111.26it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 71.35it/s] 
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 90.34it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 96.12it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 86.42it/s]
Loading 0:  25%|██▍       | 72/291 [00:00<00:02, 91.87it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:02, 101.73it/s]
Loading 0:  35%|███▍      | 101/291 [00:01<00:02, 90.96it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 94.16it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 109.09it/s]
Loading 0:  49%|████▉     | 142/291 [00:01<00:01, 95.31it/s] 
Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 98.45it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 105.86it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 117.48it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 86.96it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 102.65it/s]
Loading 0:  77%|███████▋  | 223/291 [00:02<00:00, 89.68it/s] 
Loading 0:  81%|████████  | 235/291 [00:02<00:00, 96.13it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 100.19it/s]
Loading 0:  90%|█████████ | 263/291 [00:02<00:00, 91.96it/s] 
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 95.34it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00,  8.32it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: quantized model in 22.450s
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Processed model Locutusque/Apollo-0.2-Llama-3-8B in 65.645s
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: creating bucket guanaco-mkml-models
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v1
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v1/config.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v1/special_tokens_map.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v1/tokenizer_config.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v1/tokenizer.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v1/flywheel_model.0.safetensors
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
locutusque-apollo-0-2-ll-3902-v1-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
locutusque-apollo-0-2-ll-3902-v1-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
locutusque-apollo-0-2-ll-3902-v1-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Saving duration: 0.322s
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.907s
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: creating bucket guanaco-reward-models
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/config.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/special_tokens_map.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/tokenizer_config.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/merges.txt
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/vocab.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/tokenizer.json
locutusque-apollo-0-2-ll-3902-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v1_reward/reward.tensors
Job locutusque-apollo-0-2-ll-3902-v1-mkmlizer completed after 107.24s with status: succeeded
Stopping job with name locutusque-apollo-0-2-ll-3902-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.18s
Running pipeline stage ISVCDeployer
Creating inference service locutusque-apollo-0-2-ll-3902-v1
Waiting for inference service locutusque-apollo-0-2-ll-3902-v1 to be ready
Inference service locutusque-apollo-0-2-ll-3902-v1 ready after 50.89342498779297s
Pipeline stage ISVCDeployer completed in 52.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3235700130462646s
Received healthy response to inference request in 0.35216212272644043s
Received healthy response to inference request in 0.3551328182220459s
Received healthy response to inference request in 0.37139272689819336s
Received healthy response to inference request in 0.3648543357849121s
5 requests
0 failed requests
5th percentile: 0.3527562618255615
10th percentile: 0.3533504009246826
20th percentile: 0.3545386791229248
30th percentile: 0.35707712173461914
40th percentile: 0.3609657287597656
50th percentile: 0.3648543357849121
60th percentile: 0.36746969223022463
70th percentile: 0.3700850486755371
80th percentile: 0.5618281841278078
90th percentile: 0.9426990985870363
95th percentile: 1.1331345558166501
99th percentile: 1.2854829216003418
mean time: 0.5534224033355712
Pipeline stage StressChecker completed in 3.37s
locutusque-apollo-0-2-ll_3902_v1 status is now deployed due to DeploymentManager action
locutusque-apollo-0-2-ll_3902_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of locutusque-apollo-0-2-ll_3902_v1
Running pipeline stage ISVCDeleter
Checking if service locutusque-apollo-0-2-ll-3902-v1 is running
Tearing down inference service locutusque-apollo-0-2-ll-3902-v1
Service locutusque-apollo-0-2-ll-3902-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key locutusque-apollo-0-2-ll-3902-v1/config.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.79s
locutusque-apollo-0-2-ll_3902_v1 status is now torndown due to DeploymentManager action