submission_id: mpasila-llama-3-instruct_5140_v1
developer_uid: Azazelle
best_of: 16
celo_rating: 1157.34
display_name: mpasila-Llama-3-I-LiPPA-8B
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: mpasila/Llama-3-Instruct-LiPPA-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: mpasila/Llama-3-Instruct
model_name: mpasila-Llama-3-I-LiPPA-8B
model_num_parameters: 8030261248.0
model_repo: mpasila/Llama-3-Instruct-LiPPA-8B
model_size: 8B
num_battles: 33120
num_wins: 15322
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-06T02:16:00+00:00
us_pacific_date: 2024-07-05
win_ratio: 0.4626207729468599
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mpasila-llama-3-instruct-5140-v1-mkmlizer
Waiting for job on mpasila-llama-3-instruct-5140-v1-mkmlizer to finish
mpasila-llama-3-instruct-5140-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║     _____            __           __                                ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║       /___/                                                         ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║                                                                     ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  https://mk1.ai                                                     ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║                                                                     ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  belonging to:                                                      ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║                                                                     ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  Chai Research Corp.                                                ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ║                                                                     ║
mpasila-llama-3-instruct-5140-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mpasila-llama-3-instruct-5140-v1-mkmlizer: Downloaded to shared memory in 31.360s
mpasila-llama-3-instruct-5140-v1-mkmlizer: quantizing model to /dev/shm/model_cache
mpasila-llama-3-instruct-5140-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mpasila-llama-3-instruct-5140-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:16, 17.06it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 46.13it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 65.65it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 93.83it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 93.42it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:02, 109.24it/s]
Loading 0:  27%|██▋       | 78/291 [00:00<00:01, 106.61it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:03, 61.76it/s] 
Loading 0:  35%|███▌      | 102/291 [00:01<00:02, 73.69it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 78.42it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 94.21it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 93.75it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 106.46it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:01, 104.71it/s]
Loading 0:  62%|██████▏   | 181/291 [00:02<00:01, 107.49it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 68.36it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:02<00:01, 74.11it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 89.01it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 91.57it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 107.55it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 120.32it/s]
Loading 0:  96%|█████████▌| 278/291 [00:03<00:00, 124.24it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
mpasila-llama-3-instruct-5140-v1-mkmlizer: quantized model in 24.881s
mpasila-llama-3-instruct-5140-v1-mkmlizer: Processed model mpasila/Llama-3-Instruct-LiPPA-8B in 56.241s
mpasila-llama-3-instruct-5140-v1-mkmlizer: creating bucket guanaco-mkml-models
mpasila-llama-3-instruct-5140-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mpasila-llama-3-instruct-5140-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mpasila-llama-3-instruct-5140-v1
mpasila-llama-3-instruct-5140-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mpasila-llama-3-instruct-5140-v1/special_tokens_map.json
mpasila-llama-3-instruct-5140-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mpasila-llama-3-instruct-5140-v1/tokenizer_config.json
mpasila-llama-3-instruct-5140-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mpasila-llama-3-instruct-5140-v1/config.json
mpasila-llama-3-instruct-5140-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mpasila-llama-3-instruct-5140-v1/tokenizer.json
Connection pool is full, discarding connection: %s
mpasila-llama-3-instruct-5140-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mpasila-llama-3-instruct-5140-v1/flywheel_model.0.safetensors
mpasila-llama-3-instruct-5140-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
mpasila-llama-3-instruct-5140-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mpasila-llama-3-instruct-5140-v1-mkmlizer:   warnings.warn(
mpasila-llama-3-instruct-5140-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
mpasila-llama-3-instruct-5140-v1-mkmlizer:   warnings.warn(
mpasila-llama-3-instruct-5140-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mpasila-llama-3-instruct-5140-v1-mkmlizer:   warnings.warn(
mpasila-llama-3-instruct-5140-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mpasila-llama-3-instruct-5140-v1-mkmlizer:   warnings.warn(
Job mpasila-llama-3-instruct-5140-v1-mkmlizer completed after 104.13s with status: succeeded
Stopping job with name mpasila-llama-3-instruct-5140-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service mpasila-llama-3-instruct-5140-v1
Waiting for inference service mpasila-llama-3-instruct-5140-v1 to be ready
Connection pool is full, discarding connection: %s
Inference service mpasila-llama-3-instruct-5140-v1 ready after 50.253623962402344s
Pipeline stage ISVCDeployer completed in 60.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.01957106590271s
Received healthy response to inference request in 1.3102574348449707s
Received healthy response to inference request in 1.2970554828643799s
Received healthy response to inference request in 1.2464358806610107s
Received healthy response to inference request in 1.3086462020874023s
5 requests
0 failed requests
5th percentile: 1.2565598011016845
10th percentile: 1.2666837215423583
20th percentile: 1.286931562423706
30th percentile: 1.2993736267089844
40th percentile: 1.3040099143981934
50th percentile: 1.3086462020874023
60th percentile: 1.3092906951904297
70th percentile: 1.3099351882934571
80th percentile: 1.4521201610565186
90th percentile: 1.7358456134796143
95th percentile: 1.877708339691162
99th percentile: 1.9911985206604004
mean time: 1.4363932132720947
Pipeline stage StressChecker completed in 7.86s
mpasila-llama-3-instruct_5140_v1 status is now deployed due to DeploymentManager action
mpasila-llama-3-instruct_5140_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mpasila-llama-3-instruct_5140_v1
Running pipeline stage ISVCDeleter
Checking if service mpasila-llama-3-instruct-5140-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mpasila-llama-3-instruct-5140-v1/config.json from bucket guanaco-mkml-models
Deleting key mpasila-llama-3-instruct-5140-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mpasila-llama-3-instruct-5140-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mpasila-llama-3-instruct-5140-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key mpasila-llama-3-instruct-5140-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mpasila-llama-3-instruct-5140-v1_reward/config.json from bucket guanaco-reward-models
Deleting key mpasila-llama-3-instruct-5140-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key mpasila-llama-3-instruct-5140-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mpasila-llama-3-instruct-5140-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mpasila-llama-3-instruct-5140-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mpasila-llama-3-instruct-5140-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mpasila-llama-3-instruct-5140-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.09s
mpasila-llama-3-instruct_5140_v1 status is now torndown due to DeploymentManager action