submission_id: nitral-ai-pp-0-75r1-l3-8b_v1
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/PP_0.75r1-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: 2024-05-06T04:09:35+00:00
model_name: nitral-ai-pp-0-75r1-l3-8b_v1
model_eval_status: success
double_thumbs_up: 1753
thumbs_up: 2659
thumbs_down: 1236
num_battles: 156118
num_wins: 79271
celo_rating: 1188.44
entertaining: 7.18
stay_in_character: 8.48
user_preference: 7.54
safety_score: 0.95
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-0-75r1-l3-8b_v1
double_thumbs_up_ratio: 0.3103753541076487
feedback_count: 5648
ineligible_reason: None
language_model: Nitral-AI/PP_0.75r1-l3-8b
model_score: 7.733333333333333
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.47078611898017
thumbs_down_ratio: 0.2188385269121813
thumbs_up_ratio: 0.7811614730878187
us_pacific_date: 2024-05-05
win_ratio: 0.5077633584852483
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer
Waiting for job on nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer to finish
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ /___/ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ belonging to: ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ║ ║
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-0-75r1-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-0-75r1-l3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Downloaded to shared memory in 46.680s
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:02, 76.22it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:10, 16.17it/s] Loading 0: 70%|███████ | 204/291 [00:12<00:06, 14.31it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: quantized model in 20.355s
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Processed model Nitral-AI/PP_0.75r1-l3-8b in 68.180s
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-0-75r1-l3-8b-v1
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r1-l3-8b-v1/tokenizer.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r1-l3-8b-v1/special_tokens_map.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r1-l3-8b-v1/config.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-0-75r1-l3-8b-v1/tokenizer_config.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-0-75r1-l3-8b-v1/flywheel_model.0.safetensors
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-0-75r1-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-0-75r1-l3-8b-v1-mkmlizer: warnings.warn(
nitral-ai-pp-0-75r1-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-0-75r1-l3-8b-v1-mkmlizer: warnings.warn(
nitral-ai-pp-0-75r1-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-0-75r1-l3-8b-v1-mkmlizer: warnings.warn(
nitral-ai-pp-0-75r1-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-0-75r1-l3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Saving duration: 0.266s
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.658s
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward/config.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward/merges.txt
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward/special_tokens_map.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward/vocab.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward/tokenizer_config.json
nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-0-75r1-l3-8b-v1_reward/tokenizer.json
Job nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer completed after 93.95s with status: succeeded
Stopping job with name nitral-ai-pp-0-75r1-l3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-0-75r1-l3-8b-v1
Waiting for inference service nitral-ai-pp-0-75r1-l3-8b-v1 to be ready
Inference service nitral-ai-pp-0-75r1-l3-8b-v1 ready after 40.23756289482117s
Pipeline stage ISVCDeployer completed in 47.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3557350635528564s
Received healthy response to inference request in 1.2695517539978027s
Received healthy response to inference request in 1.26607084274292s
Received healthy response to inference request in 1.272632360458374s
Received healthy response to inference request in 1.2467877864837646s
5 requests
0 failed requests
5th percentile: 1.2506443977355957
10th percentile: 1.2545010089874267
20th percentile: 1.262214231491089
30th percentile: 1.2667670249938965
40th percentile: 1.2681593894958496
50th percentile: 1.2695517539978027
60th percentile: 1.2707839965820313
70th percentile: 1.2720162391662597
80th percentile: 1.4892529010772706
90th percentile: 1.9224939823150635
95th percentile: 2.13911452293396
99th percentile: 2.312410955429077
mean time: 1.4821555614471436
Pipeline stage StressChecker completed in 8.02s
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-0-75r1-l3-8b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-0-75r1-l3-8b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics