submission_id: nitral-ai-pp-1-3-private-test_v3
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/PP_1.3-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': "'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: 2024-05-31T02:13:08+00:00
model_name: nitral-ai-pp-1-3-private-test_v3
model_eval_status: success
model_group: Nitral-AI/PP_1.3-Private
num_battles: 10205
num_wins: 5454
celo_rating: 1207.57
safety_score: 0.9
propriety_score: 0.6666666666666666
propriety_total_count: 6.0
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-1-3-private-test_v3
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/PP_1.3-Private-Test
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5344439000489956
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-3-private-test-v3-mkmlizer
Waiting for job on nitral-ai-pp-1-3-private-test-v3-mkmlizer to finish
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ║ ║
nitral-ai-pp-1-3-private-test-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-3-private-test-v3-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-1-3-private-test-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Downloaded to shared memory in 18.716s
nitral-ai-pp-1-3-private-test-v3-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:48, 2.24s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:57, 4.75it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.70it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.20it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.91it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 37.21it/s] Loading 0: 34%|███▎ | 98/291 [00:05<00:03, 51.43it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.45it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 82.73it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 99.54it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 77.86it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 94.33it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 109.86it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 123.64it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 134.94it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 144.18it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 95.70it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 105.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-1-3-private-test-v3-mkmlizer: quantized model in 22.749s
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Processed model Nitral-AI/PP_1.3-Private-Test in 43.959s
nitral-ai-pp-1-3-private-test-v3-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-3-private-test-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-3-private-test-v3
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-3-private-test-v3/config.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-3-private-test-v3/special_tokens_map.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-3-private-test-v3/tokenizer_config.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-3-private-test-v3/tokenizer.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-3-private-test-v3-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-1-3-private-test-v3-mkmlizer: warnings.warn(
nitral-ai-pp-1-3-private-test-v3-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-1-3-private-test-v3-mkmlizer: warnings.warn(
nitral-ai-pp-1-3-private-test-v3-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-1-3-private-test-v3-mkmlizer: warnings.warn(
nitral-ai-pp-1-3-private-test-v3-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-1-3-private-test-v3-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Saving duration: 0.410s
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.074s
nitral-ai-pp-1-3-private-test-v3-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-3-private-test-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-3-private-test-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/special_tokens_map.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/config.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/tokenizer_config.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/vocab.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/merges.txt
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/tokenizer.json
nitral-ai-pp-1-3-private-test-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-3-private-test-v3_reward/reward.tensors
Job nitral-ai-pp-1-3-private-test-v3-mkmlizer completed after 73.27s with status: succeeded
Stopping job with name nitral-ai-pp-1-3-private-test-v3-mkmlizer
Pipeline stage MKMLizer completed in 73.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-3-private-test-v3
Waiting for inference service nitral-ai-pp-1-3-private-test-v3 to be ready
Inference service nitral-ai-pp-1-3-private-test-v3 ready after 40.25787806510925s
Pipeline stage ISVCDeployer completed in 45.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.179511070251465s
Received healthy response to inference request in 1.3274774551391602s
Received healthy response to inference request in 1.337205410003662s
Received healthy response to inference request in 1.2784037590026855s
Received healthy response to inference request in 1.2502377033233643s
5 requests
0 failed requests
5th percentile: 1.2558709144592286
10th percentile: 1.2615041255950927
20th percentile: 1.2727705478668212
30th percentile: 1.2882184982299805
40th percentile: 1.3078479766845703
50th percentile: 1.3274774551391602
60th percentile: 1.331368637084961
70th percentile: 1.3352598190307616
80th percentile: 1.505666542053223
90th percentile: 1.8425888061523439
95th percentile: 2.011049938201904
99th percentile: 2.145818843841553
mean time: 1.4745670795440673
Pipeline stage StressChecker completed in 7.99s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-1-3-private-test_v3 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-3-private-test_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics