submission_id: nitral-ai-pp-1-4-phase1_v1
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Pp-1.4-Phase1
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: 2024-06-02T00:01:11+00:00
model_name: nitral-ai-pp-1-4-phase1_v1
model_eval_status: success
model_group: Nitral-AI/Pp-1.4-Phase1
num_battles: 6528
num_wins: 3589
celo_rating: 1215.89
safety_score: 0.96
propriety_score: 0.7099236641221374
propriety_total_count: 131.0
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-1-4-phase1_v1
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/Pp-1.4-Phase1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5497855392156863
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-4-phase1-v1-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v1-mkmlizer to finish
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-4-phase1-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-1-4-phase1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Downloaded to shared memory in 34.279s
nitral-ai-pp-1-4-phase1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:55, 2.27s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.40it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.70it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.06it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.23it/s] Loading 0: 27%|██▋ | 79/291 [00:05<00:06, 34.64it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.48it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.67it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.04it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 97.61it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 75.61it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 91.69it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 106.94it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 120.77it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 131.83it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 141.35it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 93.78it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 104.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-1-4-phase1-v1-mkmlizer: quantized model in 23.046s
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Processed model Nitral-AI/Pp-1.4-Phase1 in 59.846s
nitral-ai-pp-1-4-phase1-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-4-phase1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v1
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v1/config.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v1/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v1/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v1/tokenizer.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v1/flywheel_model.0.safetensors
nitral-ai-pp-1-4-phase1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-4-phase1-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-1-4-phase1-v1-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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-1-4-phase1-v1-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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-1-4-phase1-v1-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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-1-4-phase1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Saving duration: 0.416s
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.332s
nitral-ai-pp-1-4-phase1-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-4-phase1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-4-phase1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/config.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/vocab.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/merges.txt
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/tokenizer.json
nitral-ai-pp-1-4-phase1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v1_reward/reward.tensors
Job nitral-ai-pp-1-4-phase1-v1-mkmlizer completed after 83.1s with status: succeeded
Stopping job with name nitral-ai-pp-1-4-phase1-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-4-phase1-v1
Waiting for inference service nitral-ai-pp-1-4-phase1-v1 to be ready
Inference service nitral-ai-pp-1-4-phase1-v1 ready after 30.252142906188965s
Pipeline stage ISVCDeployer completed in 37.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1154942512512207s
Received healthy response to inference request in 1.3676042556762695s
Received healthy response to inference request in 1.3398470878601074s
Received healthy response to inference request in 1.331712245941162s
Received healthy response to inference request in 1.2583916187286377s
5 requests
0 failed requests
5th percentile: 1.2730557441711425
10th percentile: 1.2877198696136474
20th percentile: 1.3170481204986573
30th percentile: 1.3333392143249512
40th percentile: 1.3365931510925293
50th percentile: 1.3398470878601074
60th percentile: 1.3509499549865722
70th percentile: 1.362052822113037
80th percentile: 1.51718225479126
90th percentile: 1.8163382530212404
95th percentile: 1.9659162521362303
99th percentile: 2.0855786514282224
mean time: 1.4826098918914794
Pipeline stage StressChecker completed in 8.02s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
nitral-ai-pp-1-4-phase1_v1 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-4-phase1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics