developer_uid: Hastagaras
submission_id: hastagaras-l3-uduts-8b_v1
model_name: hastagaras-l3-uduts-8b_v1
model_group: Hastagaras/L3-Uduts-8B
status: torndown
timestamp: 2024-04-25T09:02:54+00:00
num_battles: 7095
num_wins: 3899
celo_rating: 1185.19
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Uduts-8B
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-l3-uduts-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Uduts-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-25
win_ratio: 0.5495419309372798
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', '###', '\n{user_name}', '</s>', '\n{bot_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\nYou're {bot_name} in this is a never-ending natural and long roleplay between {user_name} and {bot_name}. Gestures and other non-verbal actions are written between asterisks (for example, *waves hello* or *moves closer*). Write your next reply as {bot_name}, based on the following information:\n\n{memory}\n\n", 'prompt_template': '### Response:\n{bot_name}: {prompt}\n', 'bot_template': '### Response:\n{bot_name}: {message}\n', 'user_template': '### Input:\n{user_name}: {message}\n', 'response_template': '### Response\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': 'Memory: {memory}\n####\n', 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-uduts-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-uduts-8b-v1-mkmlizer to finish
hastagaras-l3-uduts-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-uduts-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-uduts-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-uduts-8b-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.
hastagaras-l3-uduts-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-uduts-8b-v1-mkmlizer: Downloaded to shared memory in 35.056s
hastagaras-l3-uduts-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-uduts-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-uduts-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▍      | 100/291 [00:00<00:01, 100.04it/s]
Loading 0:  70%|██████▉   | 203/291 [00:02<00:00, 101.11it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.72it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-uduts-8b-v1-mkmlizer: quantized model in 19.100s
hastagaras-l3-uduts-8b-v1-mkmlizer: Processed model Hastagaras/L3-Uduts-8B in 55.170s
hastagaras-l3-uduts-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v1/tokenizer_config.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v1/config.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v1/special_tokens_map.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-uduts-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-uduts-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-uduts-8b-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.
hastagaras-l3-uduts-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-uduts-8b-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.
hastagaras-l3-uduts-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-uduts-8b-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.
hastagaras-l3-uduts-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-uduts-8b-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()
hastagaras-l3-uduts-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-uduts-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-uduts-8b-v1-mkmlizer: Saving duration: 0.271s
hastagaras-l3-uduts-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.067s
hastagaras-l3-uduts-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-uduts-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-uduts-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward/config.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward/tokenizer_config.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward/special_tokens_map.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward/merges.txt
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward/vocab.json
hastagaras-l3-uduts-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-uduts-8b-v1_reward/tokenizer.json
Job hastagaras-l3-uduts-8b-v1-mkmlizer completed after 83.18s with status: succeeded
Stopping job with name hastagaras-l3-uduts-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-uduts-8b-v1
Waiting for inference service hastagaras-l3-uduts-8b-v1 to be ready
Inference service hastagaras-l3-uduts-8b-v1 ready after 40.20728135108948s
Pipeline stage ISVCDeployer completed in 47.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2430007457733154s
Received healthy response to inference request in 1.277791976928711s
Received healthy response to inference request in 1.266561508178711s
Received healthy response to inference request in 1.2661166191101074s
Received healthy response to inference request in 1.27311372756958s
5 requests
0 failed requests
5th percentile: 1.2662055969238282
10th percentile: 1.266294574737549
20th percentile: 1.2664725303649902
30th percentile: 1.2678719520568849
40th percentile: 1.2704928398132325
50th percentile: 1.27311372756958
60th percentile: 1.2749850273132324
70th percentile: 1.2768563270568847
80th percentile: 1.470833730697632
90th percentile: 1.8569172382354737
95th percentile: 2.0499589920043944
99th percentile: 2.204392395019531
mean time: 1.4653169155120849
Pipeline stage StressChecker completed in 8.04s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-uduts-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-uduts-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-uduts-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-uduts-8b-v1 is running
Tearing down inference service hastagaras-l3-uduts-8b-v1
Toredown service hastagaras-l3-uduts-8b-v1
Pipeline stage ISVCDeleter completed in 4.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-uduts-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uduts-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-uduts-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uduts-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.67s
hastagaras-l3-uduts-8b_v1 status is now torndown due to DeploymentManager action