developer_uid: Locutusque
submission_id: locutusque-apollo-0-2-ll_3902_v2
model_name: locutusque-apollo-0-2-ll_3902_v2
model_group: Locutusque/Apollo-0.2-Ll
status: torndown
timestamp: 2024-07-22T20:58:34+00:00
num_battles: 17351
num_wins: 2166
celo_rating: 779.96
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_v2
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: 0.12483430349835745
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': '{bot_name}: {message}\\n', 'memory_template': "{bot_name}'s Persona: {memory}\\n####\\n", 'prompt_template': '{prompt}\\n<START>\\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name locutusque-apollo-0-2-ll-3902-v2-mkmlizer
Waiting for job on locutusque-apollo-0-2-ll-3902-v2-mkmlizer to finish
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║     _____            __           __                                ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║       /___/                                                         ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  Version: 0.9.5.post3                                               ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  https://mk1.ai                                                     ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  belonging to:                                                      ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  Chai Research Corp.                                                ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ║                                                                     ║
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Downloaded to shared memory in 34.771s
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz23imx9l, device:0
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 129.36it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:03, 79.83it/s] 
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 98.75it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:01, 123.52it/s]
Loading 0:  25%|██▌       | 73/291 [00:00<00:02, 99.18it/s] 
Loading 0:  30%|██▉       | 86/291 [00:00<00:01, 105.01it/s]
Loading 0:  35%|███▍      | 101/291 [00:01<00:01, 97.88it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 100.89it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 117.08it/s]
Loading 0:  49%|████▉     | 143/291 [00:01<00:01, 101.00it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 108.13it/s]
Loading 0:  60%|█████▉    | 174/291 [00:01<00:00, 122.66it/s]
Loading 0:  65%|██████▍   | 188/291 [00:01<00:01, 96.33it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 105.17it/s]
Loading 0:  75%|███████▍  | 218/291 [00:02<00:00, 116.41it/s]
Loading 0:  79%|███████▉  | 231/291 [00:02<00:00, 92.97it/s] 
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 106.41it/s]
Loading 0:  90%|█████████ | 263/291 [00:02<00:00, 98.97it/s] 
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 101.29it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00,  8.82it/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-v2-mkmlizer: quantized model in 21.886s
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Processed model Locutusque/Apollo-0.2-Llama-3-8B in 56.657s
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: creating bucket guanaco-mkml-models
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v2
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v2/config.json
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/locutusque-apollo-0-2-ll-3902-v2/flywheel_model.0.safetensors
locutusque-apollo-0-2-ll-3902-v2-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-v2-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-v2-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-v2-mkmlizer:   warnings.warn(
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Saving duration: 0.337s
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.418s
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: creating bucket guanaco-reward-models
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/config.json
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/special_tokens_map.json
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/tokenizer_config.json
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/merges.txt
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/vocab.json
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/tokenizer.json
locutusque-apollo-0-2-ll-3902-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/locutusque-apollo-0-2-ll-3902-v2_reward/reward.tensors
Job locutusque-apollo-0-2-ll-3902-v2-mkmlizer completed after 97.69s with status: succeeded
Stopping job with name locutusque-apollo-0-2-ll-3902-v2-mkmlizer
Pipeline stage MKMLizer completed in 98.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service locutusque-apollo-0-2-ll-3902-v2
Waiting for inference service locutusque-apollo-0-2-ll-3902-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service locutusque-apollo-0-2-ll-3902-v2 ready after 50.79236149787903s
Pipeline stage ISVCDeployer completed in 53.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.1908905506134033s
Received healthy response to inference request in 0.3590404987335205s
Received healthy response to inference request in 0.35164761543273926s
Received healthy response to inference request in 0.3861706256866455s
Received healthy response to inference request in 0.37386226654052734s
5 requests
0 failed requests
5th percentile: 0.35312619209289553
10th percentile: 0.35460476875305175
20th percentile: 0.35756192207336424
30th percentile: 0.36200485229492185
40th percentile: 0.3679335594177246
50th percentile: 0.37386226654052734
60th percentile: 0.3787856101989746
70th percentile: 0.3837089538574219
80th percentile: 0.5471146106719972
90th percentile: 0.8690025806427002
95th percentile: 1.0299465656280515
99th percentile: 1.1587017536163329
mean time: 0.5323223114013672
Pipeline stage StressChecker completed in 3.71s
locutusque-apollo-0-2-ll_3902_v2 status is now deployed due to DeploymentManager action
locutusque-apollo-0-2-ll_3902_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of locutusque-apollo-0-2-ll_3902_v2
Running pipeline stage ISVCDeleter
Checking if service locutusque-apollo-0-2-ll-3902-v2 is running
Tearing down inference service locutusque-apollo-0-2-ll-3902-v2
Service locutusque-apollo-0-2-ll-3902-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key locutusque-apollo-0-2-ll-3902-v2/config.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-2-ll-3902-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-2-ll-3902-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.23s
locutusque-apollo-0-2-ll_3902_v2 status is now torndown due to DeploymentManager action