submission_id: neversleep-llama-3-lumim_2955_v3
developer_uid: Undi95
status: torndown
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': 16, '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: 2024-04-25T13:15:12+00:00
model_name: neversleep-llama-3-lumim_2955_v3
model_eval_status: success
model_group: NeverSleep/Llama-3-Lumim
num_battles: 8054
num_wins: 4286
celo_rating: 1176.2
propriety_score: 0.0
propriety_total_count: 0.0
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-llama-3-lumim_2955_v3
ineligible_reason: propriety_total_count < 800
language_model: NeverSleep/Llama-3-Lumimaid-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-25
win_ratio: 0.5321579339458654
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-2955-v3-mkmlizer
Waiting for job on neversleep-llama-3-lumim-2955-v3-mkmlizer to finish
neversleep-llama-3-lumim-2955-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ _____ __ __ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ /___/ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ Version: 0.8.10 ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ belonging to: ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ Chai Research Corp. ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ║ ║
neversleep-llama-3-lumim-2955-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-2955-v3-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-2955-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-2955-v3-mkmlizer: Downloaded to shared memory in 19.960s
neversleep-llama-3-lumim-2955-v3-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-2955-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-2955-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:29, 2.39s/it] Loading 0: 45%|████▌ | 132/291 [00:05<00:05, 30.26it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:02, 37.99it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-2955-v3-mkmlizer: quantized model in 20.222s
neversleep-llama-3-lumim-2955-v3-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-8B in 41.219s
neversleep-llama-3-lumim-2955-v3-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-2955-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-2955-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-2955-v3
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-2955-v3/config.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-2955-v3/special_tokens_map.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-2955-v3/tokenizer_config.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-2955-v3/tokenizer.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-2955-v3/flywheel_model.0.safetensors
neversleep-llama-3-lumim-2955-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-2955-v3-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-2955-v3-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-2955-v3-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-2955-v3-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-2955-v3-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-2955-v3-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-2955-v3-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-2955-v3-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-llama-3-lumim-2955-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-llama-3-lumim-2955-v3-mkmlizer: Saving duration: 0.298s
neversleep-llama-3-lumim-2955-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.492s
neversleep-llama-3-lumim-2955-v3-mkmlizer: creating bucket guanaco-reward-models
neversleep-llama-3-lumim-2955-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-llama-3-lumim-2955-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/config.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/tokenizer_config.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/special_tokens_map.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/merges.txt
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/vocab.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/tokenizer.json
neversleep-llama-3-lumim-2955-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-2955-v3_reward/reward.tensors
Job neversleep-llama-3-lumim-2955-v3-mkmlizer completed after 73.92s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-2955-v3-mkmlizer
Pipeline stage MKMLizer completed in 78.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-2955-v3
Waiting for inference service neversleep-llama-3-lumim-2955-v3 to be ready
Inference service neversleep-llama-3-lumim-2955-v3 ready after 40.36419224739075s
Pipeline stage ISVCDeployer completed in 47.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.134002923965454s
Received healthy response to inference request in 1.3143343925476074s
Received healthy response to inference request in 1.2484135627746582s
Received healthy response to inference request in 1.2294976711273193s
Received healthy response to inference request in 1.2550861835479736s
5 requests
0 failed requests
5th percentile: 1.233280849456787
10th percentile: 1.2370640277862548
20th percentile: 1.2446303844451905
30th percentile: 1.2497480869293214
40th percentile: 1.2524171352386475
50th percentile: 1.2550861835479736
60th percentile: 1.2787854671478271
70th percentile: 1.3024847507476807
80th percentile: 1.478268098831177
90th percentile: 1.8061355113983155
95th percentile: 1.9700692176818846
99th percentile: 2.10121618270874
mean time: 1.4362669467926026
Pipeline stage StressChecker completed in 7.79s
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 0.06s
neversleep-llama-3-lumim_2955_v3 status is now deployed due to DeploymentManager action
neversleep-llama-3-lumim_2955_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-llama-3-lumim_2955_v3
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-2955-v3 is running
admin requested tearing down of neversleep-llama-3-lumim_7274_v1
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-7274-v1 is running
Tearing down inference service neversleep-llama-3-lumim-2955-v3
Toredown service neversleep-llama-3-lumim-2955-v3
Pipeline stage ISVCDeleter completed in 6.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Tearing down inference service neversleep-llama-3-lumim-7274-v1
Toredown service neversleep-llama-3-lumim-7274-v1
Pipeline stage ISVCDeleter completed in 3.39s
Deleting key neversleep-llama-3-lumim-2955-v3/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Deleting key neversleep-llama-3-lumim-2955-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-7274-v1/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7274-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-2955-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-2955-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-2955-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-7274-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-7274-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-2955-v3_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-2955-v3_reward/merges.txt from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-2955-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-2955-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-2955-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-2955-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-2955-v3_reward/vocab.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-7274-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.21s
Deleting key neversleep-llama-3-lumim-7274-v1_reward/vocab.json from bucket guanaco-reward-models
neversleep-llama-3-lumim_2955_v3 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 2.64s

Usage Metrics

Latency Metrics