submission_id: maldv-badger-l3-instruct-32k_v1
developer_uid: maldevide
best_of: 8
celo_rating: 1195.46
display_name: maldv-badger-l3-instruct-32k_v1
family_friendly_score: 0.0
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}, and are meeting {user_name}.\n\n*emotes*\n\nMemory: {memory}', 'prompt_template': "{prompt}. Don't say too much.<|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}
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: False
language_model: maldv/badger-l3-instruct-32k
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: maldv/badger-l3-instruct
model_name: maldv-badger-l3-instruct-32k_v1
model_num_parameters: 8030261248.0
model_repo: maldv/badger-l3-instruct-32k
model_size: 8B
num_battles: 33327
num_wins: 17980
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-14T14:10:51+00:00
us_pacific_date: 2024-05-14
win_ratio: 0.5395025054760404
Resubmit model
Running pipeline stage MKMLizer
Starting job with name maldv-badger-l3-instruct-32k-v1-mkmlizer
Waiting for job on maldv-badger-l3-instruct-32k-v1-mkmlizer to finish
maldv-badger-l3-instruct-32k-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ _____ __ __ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ /___/ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ Version: 0.8.10 ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ The license key for the current software has been verified as ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ belonging to: ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ Chai Research Corp. ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ║ ║
maldv-badger-l3-instruct-32k-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maldv-badger-l3-instruct-32k-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.
maldv-badger-l3-instruct-32k-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
maldv-badger-l3-instruct-32k-v1-mkmlizer: Downloaded to shared memory in 61.937s
maldv-badger-l3-instruct-32k-v1-mkmlizer: quantizing model to /dev/shm/model_cache
maldv-badger-l3-instruct-32k-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maldv-badger-l3-instruct-32k-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:02, 84.84it/s] Loading 0: 63%|██████▎ | 182/291 [00:02<00:01, 87.74it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 28.63it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
maldv-badger-l3-instruct-32k-v1-mkmlizer: quantized model in 19.152s
maldv-badger-l3-instruct-32k-v1-mkmlizer: Processed model maldv/badger-l3-instruct-32k in 82.093s
maldv-badger-l3-instruct-32k-v1-mkmlizer: creating bucket guanaco-mkml-models
maldv-badger-l3-instruct-32k-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maldv-badger-l3-instruct-32k-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maldv-badger-l3-instruct-32k-v1
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maldv-badger-l3-instruct-32k-v1/config.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maldv-badger-l3-instruct-32k-v1/special_tokens_map.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maldv-badger-l3-instruct-32k-v1/tokenizer_config.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maldv-badger-l3-instruct-32k-v1/flywheel_model.0.safetensors
maldv-badger-l3-instruct-32k-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maldv-badger-l3-instruct-32k-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.
maldv-badger-l3-instruct-32k-v1-mkmlizer: warnings.warn(
maldv-badger-l3-instruct-32k-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.
maldv-badger-l3-instruct-32k-v1-mkmlizer: warnings.warn(
maldv-badger-l3-instruct-32k-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.
maldv-badger-l3-instruct-32k-v1-mkmlizer: warnings.warn(
maldv-badger-l3-instruct-32k-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()
maldv-badger-l3-instruct-32k-v1-mkmlizer: return self.fget.__get__(instance, owner)()
maldv-badger-l3-instruct-32k-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
maldv-badger-l3-instruct-32k-v1-mkmlizer: Saving duration: 0.284s
maldv-badger-l3-instruct-32k-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.760s
maldv-badger-l3-instruct-32k-v1-mkmlizer: creating bucket guanaco-reward-models
maldv-badger-l3-instruct-32k-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maldv-badger-l3-instruct-32k-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/special_tokens_map.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/tokenizer_config.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/config.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/merges.txt
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/vocab.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/tokenizer.json
maldv-badger-l3-instruct-32k-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maldv-badger-l3-instruct-32k-v1_reward/reward.tensors
Job maldv-badger-l3-instruct-32k-v1-mkmlizer completed after 197.91s with status: succeeded
Stopping job with name maldv-badger-l3-instruct-32k-v1-mkmlizer
Pipeline stage MKMLizer completed in 202.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service maldv-badger-l3-instruct-32k-v1
Waiting for inference service maldv-badger-l3-instruct-32k-v1 to be ready
Inference service maldv-badger-l3-instruct-32k-v1 ready after 30.25321388244629s
Pipeline stage ISVCDeployer completed in 37.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0430984497070312s
Received healthy response to inference request in 1.2502806186676025s
Received healthy response to inference request in 1.2209117412567139s
Received healthy response to inference request in 1.2421629428863525s
Received healthy response to inference request in 1.2552940845489502s
5 requests
0 failed requests
5th percentile: 1.2251619815826416
10th percentile: 1.2294122219085692
20th percentile: 1.2379127025604248
30th percentile: 1.2437864780426025
40th percentile: 1.2470335483551025
50th percentile: 1.2502806186676025
60th percentile: 1.2522860050201416
70th percentile: 1.2542913913726808
80th percentile: 1.4128549575805665
90th percentile: 1.727976703643799
95th percentile: 1.885537576675415
99th percentile: 2.011586275100708
mean time: 1.4023495674133302
Pipeline stage StressChecker completed in 7.60s
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 0.07s
maldv-badger-l3-instruct-32k_v1 status is now deployed due to DeploymentManager action
maldv-badger-l3-instruct-32k_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of maldv-badger-l3-instruct-32k_v1
Running pipeline stage ISVCDeleter
Checking if service maldv-badger-l3-instruct-32k-v1 is running
Tearing down inference service maldv-badger-l3-instruct-32k-v1
Toredown service maldv-badger-l3-instruct-32k-v1
Pipeline stage ISVCDeleter completed in 4.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key maldv-badger-l3-instruct-32k-v1/config.json from bucket guanaco-mkml-models
Deleting key maldv-badger-l3-instruct-32k-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key maldv-badger-l3-instruct-32k-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key maldv-badger-l3-instruct-32k-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key maldv-badger-l3-instruct-32k-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key maldv-badger-l3-instruct-32k-v1_reward/config.json from bucket guanaco-reward-models
Deleting key maldv-badger-l3-instruct-32k-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key maldv-badger-l3-instruct-32k-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key maldv-badger-l3-instruct-32k-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key maldv-badger-l3-instruct-32k-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key maldv-badger-l3-instruct-32k-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key maldv-badger-l3-instruct-32k-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.00s
maldv-badger-l3-instruct-32k_v1 status is now torndown due to DeploymentManager action