submission_id: nitral-ai-pp-1-25-privat_1951_v2
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}<|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: 2024-05-31T00:58:33+00:00
model_name: nitral-ai-pp-1-25-privat_1951_v2
model_eval_status: success
model_group: Nitral-AI/PP_1.25_Privat
num_battles: 5725
num_wins: 3056
celo_rating: 1214.98
safety_score: 0.96
propriety_score: 1.0
propriety_total_count: 5.0
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_v2
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: 0.5337991266375546
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-25-privat-1951-v2-mkmlizer
Waiting for job on nitral-ai-pp-1-25-privat-1951-v2-mkmlizer to finish
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ║ ║
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-25-privat-1951-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Downloaded to shared memory in 18.637s
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:11, 2.32s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:59, 4.59it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.32it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.45it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 25.04it/s] Loading 0: 27%|██▋ | 79/291 [00:05<00:06, 34.44it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.11it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.49it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.87it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 96.71it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 76.21it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 91.97it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 107.14it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 120.12it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 130.24it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 139.53it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 90.06it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 102.42it/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-v2-mkmlizer: quantized model in 23.157s
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Processed model Nitral-AI/PP_1.25_Private-Test in 44.291s
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v2
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v2/tokenizer_config.json
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v2/special_tokens_map.json
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v2/config.json
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v2/tokenizer.json
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-25-privat-1951-v2/flywheel_model.0.safetensors
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-25-privat-1951-v2-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-v2-mkmlizer: warnings.warn(
nitral-ai-pp-1-25-privat-1951-v2-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-v2-mkmlizer: warnings.warn(
nitral-ai-pp-1-25-privat-1951-v2-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-1-25-privat-1951-v2-mkmlizer: warnings.warn(
nitral-ai-pp-1-25-privat-1951-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Saving duration: 0.389s
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.068s
nitral-ai-pp-1-25-privat-1951-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-25-privat-1951-v2_reward/reward.tensors
Job nitral-ai-pp-1-25-privat-1951-v2-mkmlizer completed after 72.77s with status: succeeded
Stopping job with name nitral-ai-pp-1-25-privat-1951-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-25-privat-1951-v2
Waiting for inference service nitral-ai-pp-1-25-privat-1951-v2 to be ready
Inference service nitral-ai-pp-1-25-privat-1951-v2 ready after 60.35805416107178s
Pipeline stage ISVCDeployer completed in 66.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.137840986251831s
Received healthy response to inference request in 1.349191427230835s
Received healthy response to inference request in 1.3271608352661133s
Received healthy response to inference request in 1.3132908344268799s
Received healthy response to inference request in 1.248560905456543s
5 requests
0 failed requests
5th percentile: 1.2615068912506104
10th percentile: 1.2744528770446777
20th percentile: 1.3003448486328124
30th percentile: 1.3160648345947266
40th percentile: 1.32161283493042
50th percentile: 1.3271608352661133
60th percentile: 1.335973072052002
70th percentile: 1.3447853088378907
80th percentile: 1.5069213390350342
90th percentile: 1.8223811626434328
95th percentile: 1.9801110744476318
99th percentile: 2.1062950038909913
mean time: 1.4752089977264404
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-1-25-privat_1951_v2 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-25-privat_1951_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics