submission_id: nitral-ai-pp-1-25-privat_1951_v1
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/PP_1.25_Private-Test
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.03, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': "prompt_template': '{prompt}<|eot_id|>", 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-05-31T00:44:46+00:00
model_name: nitral-ai-pp-1-25-privat_1951_v1
model_eval_status: success
model_group: Nitral-AI/PP_1.25_Privat
num_battles: 6509
num_wins: 3487
celo_rating: 1215.53
safety_score: 0.94
propriety_score: 0.3333333333333333
propriety_total_count: 3.0
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-1-25-privat_1951_v1
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/PP_1.25_Private-Test
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5357197726225227
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-25-privat-1951-v1-mkmlizer
Waiting for job on nitral-ai-pp-1-25-privat-1951-v1-mkmlizer to finish
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-25-privat-1951-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-1-25-privat-1951-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Downloaded to shared memory in 35.810s
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:59, 2.28s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:51, 5.28it/s] Loading 0: 12%|█▏ | 34/291 [00:04<00:21, 11.70it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.54it/s] Loading 0: 23%|██▎ | 66/291 [00:05<00:08, 25.74it/s] Loading 0: 28%|██▊ | 82/291 [00:05<00:05, 36.77it/s] Loading 0: 34%|███▍ | 99/291 [00:05<00:03, 50.82it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 63.54it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.41it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 98.38it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 77.23it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 93.98it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 110.02it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 123.87it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 136.38it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 146.55it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 96.63it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 106.54it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: quantized model in 22.781s
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Processed model Nitral-AI/PP_1.25_Private-Test in 61.128s
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v1
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v1/special_tokens_map.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v1/tokenizer_config.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v1/config.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v1/tokenizer.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v1/flywheel_model.0.safetensors
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-25-privat-1951-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-1-25-privat-1951-v1-mkmlizer: warnings.warn(
nitral-ai-pp-1-25-privat-1951-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-1-25-privat-1951-v1-mkmlizer: warnings.warn(
nitral-ai-pp-1-25-privat-1951-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-1-25-privat-1951-v1-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Saving duration: 0.399s
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.092s
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/special_tokens_map.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/tokenizer_config.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/config.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/merges.txt
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/vocab.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/tokenizer.json
nitral-ai-pp-1-25-privat-1951-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v1_reward/reward.tensors
Job nitral-ai-pp-1-25-privat-1951-v1-mkmlizer completed after 83.89s with status: succeeded
Stopping job with name nitral-ai-pp-1-25-privat-1951-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-25-privat-1951-v1
Waiting for inference service nitral-ai-pp-1-25-privat-1951-v1 to be ready
Inference service nitral-ai-pp-1-25-privat-1951-v1 ready after 201.15375304222107s
Pipeline stage ISVCDeployer completed in 206.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.133150577545166s
Received healthy response to inference request in 1.325800895690918s
Received healthy response to inference request in 1.3378565311431885s
Received healthy response to inference request in 1.291274070739746s
Received healthy response to inference request in 1.3929455280303955s
5 requests
0 failed requests
5th percentile: 1.2981794357299805
10th percentile: 1.305084800720215
20th percentile: 1.3188955307006835
30th percentile: 1.328212022781372
40th percentile: 1.3330342769622803
50th percentile: 1.3378565311431885
60th percentile: 1.3598921298980713
70th percentile: 1.381927728652954
80th percentile: 1.5409865379333498
90th percentile: 1.8370685577392578
95th percentile: 1.9851095676422117
99th percentile: 2.103542375564575
mean time: 1.4962055206298828
Pipeline stage StressChecker completed in 8.09s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
nitral-ai-pp-1-25-privat_1951_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-1-25-privat_1951_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics