submission_id: neversleep-lumi-8b-v0-2-_7154_v2
developer_uid: IkariDev
status: inactive
model_repo: NeverSleep/Lumi-8B-v0.2-WIP-Train2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.074, 'top_k': 70, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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}
reward_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}
timestamp: 2024-06-29T18:43:02+00:00
model_name: neversleep-lumi-8b-v0-2_7154_v1
model_group: NeverSleep/Lumi-8B-v0.2-
num_battles: 14166
num_wins: 6936
celo_rating: 1169.16
propriety_score: 0.711094783247612
propriety_total_count: 6805.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-lumi-8b-v0-2_7154_v1
ineligible_reason: None
language_model: NeverSleep/Lumi-8B-v0.2-WIP-Train2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-29
win_ratio: 0.48962304108428634
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-lumi-8b-v0-2-7154-v2-mkmlizer
Waiting for job on neversleep-lumi-8b-v0-2-7154-v2-mkmlizer to finish
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ _____ __ __ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ /___/ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ Version: 0.8.14 ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ https://mk1.ai ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ belonging to: ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ Chai Research Corp. ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Downloaded to shared memory in 19.348s
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 127.63it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 145.15it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 154.53it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 147.71it/s] Loading 0: 28%|██▊ | 82/291 [00:00<00:01, 141.33it/s] Loading 0: 33%|███▎ | 97/291 [00:00<00:02, 77.51it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 90.79it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 105.53it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 115.00it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 116.99it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 129.22it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 77.42it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:01, 85.26it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 100.55it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 114.98it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 122.84it/s] Loading 0: 92%|█████████▏| 267/291 [00:02<00:00, 128.15it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 133.23it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: quantized model in 23.330s
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Processed model NeverSleep/Lumi-8B-v0.2-WIP-Train2 in 45.354s
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: creating bucket guanaco-mkml-models
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v2
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v2/tokenizer_config.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v2/config.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v2/special_tokens_map.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v2/tokenizer.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v2/flywheel_model.0.safetensors
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: warnings.warn(
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: warnings.warn(
neversleep-lumi-8b-v0-2-7154-v2-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.
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: warnings.warn(
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Saving duration: 0.423s
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.640s
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: creating bucket guanaco-reward-models
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/config.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/special_tokens_map.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/tokenizer_config.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/merges.txt
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/vocab.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/tokenizer.json
neversleep-lumi-8b-v0-2-7154-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v2_reward/reward.tensors
Job neversleep-lumi-8b-v0-2-7154-v2-mkmlizer completed after 73.42s with status: succeeded
Stopping job with name neversleep-lumi-8b-v0-2-7154-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-lumi-8b-v0-2-7154-v2
Waiting for inference service neversleep-lumi-8b-v0-2-7154-v2 to be ready
Inference service neversleep-lumi-8b-v0-2-7154-v2 ready after 40.27276015281677s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0711991786956787s
Received healthy response to inference request in 1.162795066833496s
Received healthy response to inference request in 1.1407685279846191s
Received healthy response to inference request in 1.1171643733978271s
Received healthy response to inference request in 1.1306936740875244s
5 requests
0 failed requests
5th percentile: 1.1198702335357666
10th percentile: 1.1225760936737061
20th percentile: 1.127987813949585
30th percentile: 1.1327086448669434
40th percentile: 1.1367385864257813
50th percentile: 1.1407685279846191
60th percentile: 1.14957914352417
70th percentile: 1.1583897590637207
80th percentile: 1.3444758892059328
90th percentile: 1.7078375339508058
95th percentile: 1.889518356323242
99th percentile: 2.0348630142211914
mean time: 1.324524164199829
Pipeline stage StressChecker completed in 7.29s
neversleep-lumi-8b-v0-2-_7154_v2 status is now deployed due to DeploymentManager action
neversleep-lumi-8b-v0-2-_7154_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics