submission_id: neversleep-lumi-8b-v0-2-_7154_v4
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', '<|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}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: {'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: 2024-06-29T19:28:11+00:00
model_name: neversleep-lumi-8b-v0-2_7154_v1
model_group: NeverSleep/Lumi-8B-v0.2-
num_battles: 32431
num_wins: 15570
celo_rating: 1167.74
propriety_score: 0.7256349863135783
propriety_total_count: 15709.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
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: 0.480096204249021
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-lumi-8b-v0-2-7154-v4-mkmlizer
Waiting for job on neversleep-lumi-8b-v0-2-7154-v4-mkmlizer to finish
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ _____ __ __ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ /___/ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ Version: 0.8.14 ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ https://mk1.ai ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ belonging to: ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ Chai Research Corp. ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ║ ║
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-lumi-8b-v0-2-7154-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Downloaded to shared memory in 18.284s
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 15/291 [00:00<00:01, 148.99it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 156.03it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 157.51it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 160.64it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 87.27it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 105.04it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 118.58it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 130.21it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 138.10it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 148.85it/s] Loading 0: 66%|██████▌ | 192/291 [00:01<00:01, 90.42it/s] Loading 0: 70%|███████ | 205/291 [00:01<00:00, 96.05it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 106.51it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 119.46it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 131.55it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 139.03it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.81it/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-v4-mkmlizer: quantized model in 23.043s
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Processed model NeverSleep/Lumi-8B-v0.2-WIP-Train2 in 43.837s
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: creating bucket guanaco-mkml-models
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v4
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v4/tokenizer.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v4/config.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v4/tokenizer_config.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v4/special_tokens_map.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-lumi-8b-v0-2-7154-v4/flywheel_model.0.safetensors
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-lumi-8b-v0-2-7154-v4-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-v4-mkmlizer: warnings.warn(
neversleep-lumi-8b-v0-2-7154-v4-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-v4-mkmlizer: warnings.warn(
neversleep-lumi-8b-v0-2-7154-v4-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-v4-mkmlizer: warnings.warn(
neversleep-lumi-8b-v0-2-7154-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Saving duration: 0.389s
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.169s
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: creating bucket guanaco-reward-models
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward/config.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward/tokenizer_config.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward/merges.txt
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward/special_tokens_map.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward/vocab.json
neversleep-lumi-8b-v0-2-7154-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-lumi-8b-v0-2-7154-v4_reward/tokenizer.json
Job neversleep-lumi-8b-v0-2-7154-v4-mkmlizer completed after 73.17s with status: succeeded
Stopping job with name neversleep-lumi-8b-v0-2-7154-v4-mkmlizer
Pipeline stage MKMLizer completed in 74.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-lumi-8b-v0-2-7154-v4
Waiting for inference service neversleep-lumi-8b-v0-2-7154-v4 to be ready
Inference service neversleep-lumi-8b-v0-2-7154-v4 ready after 50.20948767662048s
Pipeline stage ISVCDeployer completed in 57.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3419089317321777s
Received healthy response to inference request in 1.3428599834442139s
Received healthy response to inference request in 1.3325340747833252s
Received healthy response to inference request in 1.3730361461639404s
Received healthy response to inference request in 1.6326406002044678s
5 requests
0 failed requests
5th percentile: 1.334599256515503
10th percentile: 1.3366644382476807
20th percentile: 1.3407948017120361
30th percentile: 1.348895215988159
40th percentile: 1.3609656810760498
50th percentile: 1.3730361461639404
60th percentile: 1.4768779277801514
70th percentile: 1.5807197093963623
80th percentile: 1.7744942665100099
90th percentile: 2.0582015991210936
95th percentile: 2.2000552654266357
99th percentile: 2.3135381984710692
mean time: 1.604595947265625
Pipeline stage StressChecker completed in 8.75s
neversleep-lumi-8b-v0-2-_7154_v4 status is now deployed due to DeploymentManager action
neversleep-lumi-8b-v0-2-_7154_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics