submission_id: nitral-ai-poppy-porpoise_7217_v6
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, '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: 2024-06-02T20:50:36+00:00
model_name: nitral-ai-poppy-porpoise_7217_v6
model_eval_status: success
model_group: Nitral-AI/Poppy_Porpoise
num_battles: 42014
num_wins: 23654
celo_rating: 1206.59
safety_score: 0.97
propriety_score: 0.6764705882352942
propriety_total_count: 1122.0
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-poppy-porpoise_7217_v6
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5630028085876136
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-poppy-porpoise-7217-v6-mkmlizer
Waiting for job on nitral-ai-poppy-porpoise-7217-v6-mkmlizer to finish
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ _____ __ __ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ /___/ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ https://mk1.ai ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ belonging to: ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ║ ║
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-poppy-porpoise-7217-v6-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-poppy-porpoise-7217-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Downloaded to shared memory in 47.987s
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 11/291 [00:00<00:02, 101.56it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:02, 93.27it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:02, 110.46it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 63.38it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:02, 79.00it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:02, 82.34it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 61.46it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:02, 78.86it/s] Loading 0: 40%|███▉ | 115/291 [00:01<00:01, 94.07it/s] Loading 0: 42%|████▏ | 123/291 [00:11<00:01, 94.07it/s] Loading 0: 43%|████▎ | 124/291 [00:11<00:44, 3.79it/s] Loading 0: 47%|████▋ | 136/291 [00:11<00:29, 5.34it/s] Loading 0: 51%|█████ | 148/291 [00:11<00:19, 7.23it/s] Loading 0: 54%|█████▍ | 158/291 [00:12<00:13, 9.56it/s] Loading 0: 60%|█████▉ | 174/291 [00:12<00:07, 14.74it/s] Loading 0: 64%|██████▎ | 185/291 [00:12<00:05, 17.78it/s] Loading 0: 67%|██████▋ | 196/291 [00:12<00:04, 23.01it/s] Loading 0: 73%|███████▎ | 212/291 [00:12<00:02, 33.33it/s] Loading 0: 77%|███████▋ | 223/291 [00:12<00:01, 34.99it/s] Loading 0: 82%|████████▏ | 239/291 [00:13<00:01, 47.64it/s] Loading 0: 86%|████████▌ | 250/291 [00:13<00:00, 54.07it/s] Loading 0: 90%|█████████ | 263/291 [00:13<00:00, 55.33it/s] Loading 0: 93%|█████████▎| 272/291 [00:13<00:00, 60.06it/s] Loading 0: 98%|█████████▊| 286/291 [00:13<00:00, 73.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: quantized model in 20.149s
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Processed model Nitral-AI/Poppy_Porpoise-0.72-L3-8B in 69.387s
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-poppy-porpoise-7217-v6
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-poppy-porpoise-7217-v6/tokenizer_config.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-poppy-porpoise-7217-v6/special_tokens_map.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-poppy-porpoise-7217-v6/config.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-poppy-porpoise-7217-v6/tokenizer.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-poppy-porpoise-7217-v6/flywheel_model.0.safetensors
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-poppy-porpoise-7217-v6-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-poppy-porpoise-7217-v6-mkmlizer: warnings.warn(
nitral-ai-poppy-porpoise-7217-v6-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-poppy-porpoise-7217-v6-mkmlizer: warnings.warn(
nitral-ai-poppy-porpoise-7217-v6-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-poppy-porpoise-7217-v6-mkmlizer: warnings.warn(
nitral-ai-poppy-porpoise-7217-v6-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-poppy-porpoise-7217-v6-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Saving duration: 0.311s
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.796s
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/config.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/tokenizer_config.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/merges.txt
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/special_tokens_map.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/vocab.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/tokenizer.json
nitral-ai-poppy-porpoise-7217-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-poppy-porpoise-7217-v6_reward/reward.tensors
Job nitral-ai-poppy-porpoise-7217-v6-mkmlizer completed after 93.44s with status: succeeded
Stopping job with name nitral-ai-poppy-porpoise-7217-v6-mkmlizer
Pipeline stage MKMLizer completed in 96.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-poppy-porpoise-7217-v6
Waiting for inference service nitral-ai-poppy-porpoise-7217-v6 to be ready
Inference service nitral-ai-poppy-porpoise-7217-v6 ready after 31.95849323272705s
Pipeline stage ISVCDeployer completed in 38.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.059821844100952s
Received healthy response to inference request in 1.3447480201721191s
Received healthy response to inference request in 1.3238043785095215s
Received healthy response to inference request in 1.311950445175171s
Received healthy response to inference request in 1.3570408821105957s
5 requests
0 failed requests
5th percentile: 1.314321231842041
10th percentile: 1.316692018508911
20th percentile: 1.3214335918426514
30th percentile: 1.327993106842041
40th percentile: 1.3363705635070802
50th percentile: 1.3447480201721191
60th percentile: 1.3496651649475098
70th percentile: 1.3545823097229004
80th percentile: 1.497597074508667
90th percentile: 1.7787094593048096
95th percentile: 1.9192656517028808
99th percentile: 2.031710605621338
mean time: 1.4794731140136719
Pipeline stage StressChecker completed in 8.00s
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-poppy-porpoise_7217_v6 status is now deployed due to DeploymentManager action
nitral-ai-poppy-porpoise_7217_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics