developer_uid: Azazelle
submission_id: neversleep-llama-3-lumim_7054_v1
model_name: neversleep-llama-3-lumim_7054_v1
model_group: NeverSleep/Llama-3-Lumim
status: torndown
timestamp: 2024-07-06T00:12:40+00:00
num_battles: 29929
num_wins: 14498
celo_rating: 1173.22
family_friendly_score: 0.0
submission_type: basic
model_repo: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-llama-3-lumim_7054_v1
is_internal_developer: False
language_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-05
win_ratio: 0.48441311102943635
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}
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}
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 neversleep-llama-3-lumim-7054-v1-mkmlizer
Waiting for job on neversleep-llama-3-lumim-7054-v1-mkmlizer to finish
neversleep-llama-3-lumim-7054-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║     _____            __           __                                ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║       /___/                                                         ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  belonging to:                                                      ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-7054-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-7054-v1-mkmlizer: Downloaded to shared memory in 37.320s
neversleep-llama-3-lumim-7054-v1-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-7054-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-7054-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:18, 15.40it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:17, 16.12it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 64.53it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:03, 75.17it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 97.55it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:02, 95.89it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:01, 109.74it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:03, 60.82it/s] 
Loading 0:  35%|███▌      | 102/291 [00:01<00:02, 75.55it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 79.72it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 94.71it/s]
Loading 0:  48%|████▊     | 141/291 [00:01<00:01, 96.49it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 106.89it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:01, 104.05it/s]
Loading 0:  62%|██████▏   | 181/291 [00:02<00:01, 107.33it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 67.71it/s] 
Loading 0:  71%|███████   | 206/291 [00:02<00:01, 78.52it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 88.52it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 90.24it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 103.51it/s]
Loading 0:  89%|████████▊ | 258/291 [00:02<00:00, 101.56it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 108.52it/s]
Loading 0:  98%|█████████▊| 285/291 [00:03<00:00, 106.54it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-7054-v1-mkmlizer: quantized model in 26.953s
neversleep-llama-3-lumim-7054-v1-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS in 64.274s
neversleep-llama-3-lumim-7054-v1-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-7054-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-7054-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-7054-v1
neversleep-llama-3-lumim-7054-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7054-v1/config.json
neversleep-llama-3-lumim-7054-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7054-v1/tokenizer_config.json
neversleep-llama-3-lumim-7054-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7054-v1/special_tokens_map.json
neversleep-llama-3-lumim-7054-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7054-v1/tokenizer.json
neversleep-llama-3-lumim-7054-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-7054-v1/flywheel_model.0.safetensors
neversleep-llama-3-lumim-7054-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-7054-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.
neversleep-llama-3-lumim-7054-v1-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-7054-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`.
neversleep-llama-3-lumim-7054-v1-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job neversleep-llama-3-lumim-7054-v1-mkmlizer completed after 103.85s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-7054-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-7054-v1
Waiting for inference service neversleep-llama-3-lumim-7054-v1 to be ready
Inference service neversleep-llama-3-lumim-7054-v1 ready after 40.45635533332825s
Pipeline stage ISVCDeployer completed in 48.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.058126211166382s
Received healthy response to inference request in 1.3306691646575928s
Received healthy response to inference request in 1.286849021911621s
Received healthy response to inference request in 1.2696938514709473s
Received healthy response to inference request in 1.4061219692230225s
5 requests
0 failed requests
5th percentile: 1.273124885559082
10th percentile: 1.2765559196472167
20th percentile: 1.2834179878234864
30th percentile: 1.2956130504608154
40th percentile: 1.313141107559204
50th percentile: 1.3306691646575928
60th percentile: 1.3608502864837646
70th percentile: 1.3910314083099364
80th percentile: 1.5365228176116945
90th percentile: 1.7973245143890382
95th percentile: 1.9277253627777098
99th percentile: 2.0320460414886474
mean time: 1.470292043685913
Pipeline stage StressChecker completed in 8.02s
neversleep-llama-3-lumim_7054_v1 status is now deployed due to DeploymentManager action
neversleep-llama-3-lumim_7054_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-llama-3-lumim_7054_v1
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-7054-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-7054-v1/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7054-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7054-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7054-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7054-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-7054-v1_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7054-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7054-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7054-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7054-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7054-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7054-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.35s
neversleep-llama-3-lumim_7054_v1 status is now torndown due to DeploymentManager action