developer_uid: Nitral-AI
submission_id: nitral-ai-pp-0-72_v1
model_name: nitral-ai-pp-0-72_v1
model_group: Nitral-AI/PP_0.72
status: torndown
timestamp: 2024-05-02T01:13:27+00:00
num_battles: 29218
num_wins: 16029
celo_rating: 1205.19
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/PP_0.72
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: nitral-ai-pp-0-72_v1
is_internal_developer: False
language_model: Nitral-AI/PP_0.72
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-01
win_ratio: 0.5486001779724827
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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-0-72-v1-mkmlizer
Waiting for job on nitral-ai-pp-0-72-v1-mkmlizer to finish
nitral-ai-pp-0-72-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-0-72-v1-mkmlizer: ║     _____            __           __                                ║
nitral-ai-pp-0-72-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-pp-0-72-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-pp-0-72-v1-mkmlizer: ║       /___/                                                         ║
nitral-ai-pp-0-72-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-pp-0-72-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-pp-0-72-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-pp-0-72-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-pp-0-72-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-0-72-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.
nitral-ai-pp-0-72-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-0-72-v1-mkmlizer: Downloaded to shared memory in 59.767s
nitral-ai-pp-0-72-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-0-72-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-0-72-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:02, 80.06it/s]
Loading 0:  42%|████▏     | 123/291 [00:07<00:11, 14.68it/s]
Loading 0:  75%|███████▍  | 217/291 [00:14<00:05, 13.82it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-0-72-v1-mkmlizer: quantized model in 21.703s
nitral-ai-pp-0-72-v1-mkmlizer: Processed model Nitral-AI/PP_0.72 in 82.707s
nitral-ai-pp-0-72-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-0-72-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-0-72-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-0-72-v1
nitral-ai-pp-0-72-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-0-72-v1/special_tokens_map.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-0-72-v1/config.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-0-72-v1/tokenizer_config.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-0-72-v1/tokenizer.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-0-72-v1/flywheel_model.0.safetensors
nitral-ai-pp-0-72-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-0-72-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.
nitral-ai-pp-0-72-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-72-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.
nitral-ai-pp-0-72-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-72-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.
nitral-ai-pp-0-72-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-72-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()
nitral-ai-pp-0-72-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
nitral-ai-pp-0-72-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-0-72-v1-mkmlizer: Saving duration: 0.298s
nitral-ai-pp-0-72-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.191s
nitral-ai-pp-0-72-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-0-72-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-0-72-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/config.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/special_tokens_map.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/tokenizer_config.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/merges.txt
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/vocab.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/tokenizer.json
nitral-ai-pp-0-72-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-0-72-v1_reward/reward.tensors
Job nitral-ai-pp-0-72-v1-mkmlizer completed after 114.03s with status: succeeded
Stopping job with name nitral-ai-pp-0-72-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-0-72-v1
Waiting for inference service nitral-ai-pp-0-72-v1 to be ready
Inference service nitral-ai-pp-0-72-v1 ready after 40.32149147987366s
Pipeline stage ISVCDeployer completed in 47.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.136686325073242s
Received healthy response to inference request in 1.2557706832885742s
Received healthy response to inference request in 1.251094102859497s
Received healthy response to inference request in 1.258997917175293s
Received healthy response to inference request in 1.2670059204101562s
5 requests
0 failed requests
5th percentile: 1.2520294189453125
10th percentile: 1.252964735031128
20th percentile: 1.2548353672027588
30th percentile: 1.256416130065918
40th percentile: 1.2577070236206054
50th percentile: 1.258997917175293
60th percentile: 1.2622011184692383
70th percentile: 1.2654043197631837
80th percentile: 1.4409420013427736
90th percentile: 1.788814163208008
95th percentile: 1.9627502441406248
99th percentile: 2.1018991088867187
mean time: 1.4339109897613525
Pipeline stage StressChecker completed in 7.83s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
nitral-ai-pp-0-72_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-0-72_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-pp-0-72_v1
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-pp-0-72-v1 is running
Tearing down inference service nitral-ai-pp-0-72-v1
Toredown service nitral-ai-pp-0-72-v1
Pipeline stage ISVCDeleter completed in 5.69s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-72-v1/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-72-v1_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.21s
nitral-ai-pp-0-72_v1 status is now torndown due to DeploymentManager action