submission_id: nitral-ai-pp-0-75r3-l3-8b_v1
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/PP_0.75r3-l3-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, '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: 2024-05-06T05:11:19+00:00
model_name: nitral-ai-pp-0-75r3-l3-8b_v1
model_eval_status: success
double_thumbs_up: 1533
thumbs_up: 2338
thumbs_down: 1162
num_battles: 142057
num_wins: 72377
celo_rating: 1189.25
entertaining: 6.98
stay_in_character: 8.52
user_preference: 7.34
safety_score: 0.96
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-pp-0-75r3-l3-8b_v1
double_thumbs_up_ratio: 0.3045897079276773
feedback_count: 5033
ineligible_reason: None
language_model: Nitral-AI/PP_0.75r3-l3-8b
model_score: 7.613333333333333
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.46453407510431155
thumbs_down_ratio: 0.23087621696801114
thumbs_up_ratio: 0.7691237830319889
us_pacific_date: 2024-05-05
win_ratio: 0.5094926684359096
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer
Waiting for job on nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer to finish
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ /___/ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ belonging to: ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-0-75r3-l3-8b-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.
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Downloaded to shared memory in 37.252s
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▌ | 105/291 [00:01<00:01, 104.90it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:10, 16.35it/s] Loading 0: 76%|███████▌ | 220/291 [00:12<00:04, 15.56it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: quantized model in 23.800s
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Processed model Nitral-AI/PP_0.75r3-l3-8b in 63.708s
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-0-75r3-l3-8b-v1
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r3-l3-8b-v1/config.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r3-l3-8b-v1/tokenizer_config.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r3-l3-8b-v1/special_tokens_map.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r3-l3-8b-v1/tokenizer.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-0-75r3-l3-8b-v1/flywheel_model.0.safetensors
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-0-75r3-l3-8b-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.
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: warnings.warn(
nitral-ai-pp-0-75r3-l3-8b-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.
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: warnings.warn(
nitral-ai-pp-0-75r3-l3-8b-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.
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: warnings.warn(
nitral-ai-pp-0-75r3-l3-8b-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()
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/special_tokens_map.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/config.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/tokenizer_config.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/merges.txt
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/vocab.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/tokenizer.json
nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-0-75r3-l3-8b-v1_reward/reward.tensors
Job nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer completed after 93.58s with status: succeeded
Stopping job with name nitral-ai-pp-0-75r3-l3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-0-75r3-l3-8b-v1
Waiting for inference service nitral-ai-pp-0-75r3-l3-8b-v1 to be ready
Inference service nitral-ai-pp-0-75r3-l3-8b-v1 ready after 30.19100069999695s
Pipeline stage ISVCDeployer completed in 37.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1307685375213623s
Received healthy response to inference request in 1.2316908836364746s
Received healthy response to inference request in 1.2541792392730713s
Received healthy response to inference request in 1.2345490455627441s
Received healthy response to inference request in 1.2446050643920898s
5 requests
0 failed requests
5th percentile: 1.2322625160217284
10th percentile: 1.2328341484069825
20th percentile: 1.2339774131774903
30th percentile: 1.2365602493286132
40th percentile: 1.2405826568603515
50th percentile: 1.2446050643920898
60th percentile: 1.2484347343444824
70th percentile: 1.252264404296875
80th percentile: 1.4294970989227296
90th percentile: 1.780132818222046
95th percentile: 1.955450677871704
99th percentile: 2.095704965591431
mean time: 1.4191585540771485
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-0-75r3-l3-8b_v1 status is now deployed due to DeploymentManager action
nitral-ai-pp-0-75r3-l3-8b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics