submission_id: neversleep-llama-3-lumim_8666_v1
developer_uid: zonemercy
status: inactive
model_repo: neversleep/llama-3-lumimaid-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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: 2024-05-06T16:31:05+00:00
model_name: neversleep-llama-3-lumim_8666_v1
model_eval_status: success
double_thumbs_up: 362
thumbs_up: 520
thumbs_down: 354
num_battles: 33142
num_wins: 15411
celo_rating: 1157.4
entertaining: 6.9
stay_in_character: 8.55
user_preference: 7.04
safety_score: 0.94
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-llama-3-lumim_8666_v1
double_thumbs_up_ratio: 0.2928802588996764
feedback_count: 1236
ineligible_reason: None
language_model: neversleep/llama-3-lumimaid-8b
model_score: 7.496666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.42071197411003236
thumbs_down_ratio: 0.28640776699029125
thumbs_up_ratio: 0.7135922330097088
us_pacific_date: 2024-05-06
win_ratio: 0.46499909480417595
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-8666-v1-mkmlizer
Waiting for job on neversleep-llama-3-lumim-8666-v1-mkmlizer to finish
neversleep-llama-3-lumim-8666-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ _____ __ __ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ /___/ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ Version: 0.8.10 ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ belonging to: ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ Chai Research Corp. ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8666-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-8666-v1-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-llama-3-lumim-8666-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-8666-v1-mkmlizer: Downloaded to shared memory in 22.010s
neversleep-llama-3-lumim-8666-v1-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-8666-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-8666-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:15, 2.13s/it] Loading 0: 57%|█████▋ | 166/291 [00:05<00:03, 37.15it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-8666-v1-mkmlizer: quantized model in 18.886s
neversleep-llama-3-lumim-8666-v1-mkmlizer: Processed model neversleep/llama-3-lumimaid-8b in 41.852s
neversleep-llama-3-lumim-8666-v1-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-8666-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-8666-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-8666-v1
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8666-v1/config.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8666-v1/special_tokens_map.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8666-v1/tokenizer_config.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8666-v1/tokenizer.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8666-v1/flywheel_model.0.safetensors
neversleep-llama-3-lumim-8666-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-8666-v1-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-llama-3-lumim-8666-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-8666-v1-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-llama-3-lumim-8666-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-8666-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.
neversleep-llama-3-lumim-8666-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-8666-v1-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-llama-3-lumim-8666-v1-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-llama-3-lumim-8666-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-llama-3-lumim-8666-v1-mkmlizer: Saving duration: 0.297s
neversleep-llama-3-lumim-8666-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 21.152s
neversleep-llama-3-lumim-8666-v1-mkmlizer: creating bucket guanaco-reward-models
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/config.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/special_tokens_map.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/tokenizer_config.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/merges.txt
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/vocab.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/tokenizer.json
neversleep-llama-3-lumim-8666-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-8666-v1_reward/reward.tensors
Job neversleep-llama-3-lumim-8666-v1-mkmlizer completed after 189.3s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-8666-v1-mkmlizer
Pipeline stage MKMLizer completed in 194.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-8666-v1
Waiting for inference service neversleep-llama-3-lumim-8666-v1 to be ready
Inference service neversleep-llama-3-lumim-8666-v1 ready after 40.258705139160156s
Pipeline stage ISVCDeployer completed in 48.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.311460494995117s
Received healthy response to inference request in 1.1220555305480957s
Received healthy response to inference request in 1.1316843032836914s
Received healthy response to inference request in 1.0838983058929443s
Received healthy response to inference request in 1.133920431137085s
5 requests
0 failed requests
5th percentile: 1.0915297508239745
10th percentile: 1.099161195755005
20th percentile: 1.1144240856170655
30th percentile: 1.1239812850952149
40th percentile: 1.127832794189453
50th percentile: 1.1316843032836914
60th percentile: 1.1325787544250487
70th percentile: 1.1334732055664063
80th percentile: 1.3694284439086917
90th percentile: 1.8404444694519044
95th percentile: 2.0759524822235105
99th percentile: 2.264358892440796
mean time: 1.3566038131713867
Pipeline stage StressChecker completed in 7.37s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.09s
neversleep-llama-3-lumim_8666_v1 status is now deployed due to DeploymentManager action
neversleep-llama-3-lumim_8666_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics