developer_uid: Nitral-AI
submission_id: nitral-ai-pp-0-71b_v1
model_name: nitral-ai-pp-0-71b_v1
model_group: Nitral-AI/PP_0.71b
status: torndown
timestamp: 2024-05-02T00:14:56+00:00
num_battles: 23475
num_wins: 12524
celo_rating: 1202.03
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/PP_0.71b
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-0-71b_v1
is_internal_developer: False
language_model: Nitral-AI/PP_0.71b
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-01
win_ratio: 0.5335037273695421
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}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-0-71b-v1-mkmlizer
Waiting for job on nitral-ai-pp-0-71b-v1-mkmlizer to finish
nitral-ai-pp-0-71b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-0-71b-v1-mkmlizer: ║     _____            __           __                                ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║       /___/                                                         ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-pp-0-71b-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-71b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-0-71b-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-0-71b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-0-71b-v1-mkmlizer: Downloaded to shared memory in 43.059s
nitral-ai-pp-0-71b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-0-71b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-0-71b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:02, 77.02it/s]
Loading 0:  56%|█████▌    | 162/291 [00:02<00:01, 79.04it/s]
Loading 0:  64%|██████▍   | 186/291 [00:08<00:06, 15.14it/s]
Loading 0:  88%|████████▊ | 257/291 [00:15<00:02, 12.77it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-0-71b-v1-mkmlizer: quantized model in 22.670s
nitral-ai-pp-0-71b-v1-mkmlizer: Processed model Nitral-AI/PP_0.71b in 67.163s
nitral-ai-pp-0-71b-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-0-71b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-0-71b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-0-71b-v1
nitral-ai-pp-0-71b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-0-71b-v1/special_tokens_map.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-0-71b-v1/config.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-0-71b-v1/tokenizer_config.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-0-71b-v1/tokenizer.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-0-71b-v1/flywheel_model.0.safetensors
nitral-ai-pp-0-71b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-0-71b-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-0-71b-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-71b-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-0-71b-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-71b-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-0-71b-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-71b-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-0-71b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
nitral-ai-pp-0-71b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-0-71b-v1-mkmlizer: Saving duration: 0.282s
nitral-ai-pp-0-71b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.189s
nitral-ai-pp-0-71b-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-0-71b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-0-71b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/config.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/special_tokens_map.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/tokenizer_config.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/merges.txt
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/vocab.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/tokenizer.json
nitral-ai-pp-0-71b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-0-71b-v1_reward/reward.tensors
Job nitral-ai-pp-0-71b-v1-mkmlizer completed after 93.19s with status: succeeded
Stopping job with name nitral-ai-pp-0-71b-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-0-71b-v1
Waiting for inference service nitral-ai-pp-0-71b-v1 to be ready
Inference service nitral-ai-pp-0-71b-v1 ready after 30.171541929244995s
Pipeline stage ISVCDeployer completed in 37.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.126941442489624s
Received healthy response to inference request in 1.2799172401428223s
Received healthy response to inference request in 1.2677736282348633s
Received healthy response to inference request in 1.2449009418487549s
Received healthy response to inference request in 1.2602403163909912s
5 requests
0 failed requests
5th percentile: 1.247968816757202
10th percentile: 1.2510366916656495
20th percentile: 1.257172441482544
30th percentile: 1.2617469787597657
40th percentile: 1.2647603034973145
50th percentile: 1.2677736282348633
60th percentile: 1.2726310729980468
70th percentile: 1.2774885177612305
80th percentile: 1.4493220806121827
90th percentile: 1.7881317615509034
95th percentile: 1.9575366020202636
99th percentile: 2.093060474395752
mean time: 1.435954713821411
Pipeline stage StressChecker completed in 7.82s
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
nitral-ai-pp-0-71b_v1 status is now deployed due to DeploymentManager action
nitral-ai-pp-0-71b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-pp-0-71b_v1
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-pp-0-71b-v1 is running
Tearing down inference service nitral-ai-pp-0-71b-v1
Toredown service nitral-ai-pp-0-71b-v1
Pipeline stage ISVCDeleter completed in 4.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-71b-v1/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-71b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-71b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-71b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-71b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-71b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.53s
nitral-ai-pp-0-71b_v1 status is now torndown due to DeploymentManager action