submission_id: chaoticneutrals-poppy-po_3816_v3
developer_uid: robert_irvine
status: inactive
model_repo: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
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}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-06-10T04:34:20+00:00
model_name: chaoticneutrals-poppy-po_3816_v3
model_eval_status: success
model_group: ChaoticNeutrals/Poppy_Po
num_battles: 10966
num_wins: 5632
celo_rating: 1194.17
safety_score: 0.95
propriety_score: 0.688508064516129
propriety_total_count: 992.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: chaoticneutrals-poppy-po_3816_v3
ineligible_reason: propriety_total_count < 5000
language_model: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
model_size: 8B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-09
win_ratio: 0.5135874521247492
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaoticneutrals-poppy-po-3816-v3-mkmlizer
Waiting for job on chaoticneutrals-poppy-po-3816-v3-mkmlizer to finish
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ _____ __ __ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ /___/ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ Version: 0.8.14 ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ https://mk1.ai ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ belonging to: ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ Chai Research Corp. ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaoticneutrals-poppy-po-3816-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.
chaoticneutrals-poppy-po-3816-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Downloaded to shared memory in 57.128s
chaoticneutrals-poppy-po-3816-v3-mkmlizer: quantizing model to /dev/shm/model_cache
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:01, 195.11it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 105.26it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 127.07it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 108.62it/s] Loading 0: 34%|███▍ | 100/291 [00:00<00:01, 126.74it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:12, 13.42it/s] Loading 0: 46%|████▌ | 133/291 [00:09<00:23, 6.70it/s] Loading 0: 49%|████▉ | 144/291 [00:10<00:17, 8.40it/s] Loading 0: 57%|█████▋ | 165/291 [00:10<00:09, 13.26it/s] Loading 0: 63%|██████▎ | 182/291 [00:10<00:06, 17.77it/s] Loading 0: 70%|██████▉ | 203/291 [00:10<00:03, 26.11it/s] Loading 0: 76%|███████▌ | 220/291 [00:10<00:02, 32.07it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 44.67it/s] Loading 0: 90%|█████████ | 263/291 [00:10<00:00, 55.33it/s] Loading 0: 96%|█████████▌| 280/291 [00:11<00:00, 67.63it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaoticneutrals-poppy-po-3816-v3-mkmlizer: quantized model in 17.178s
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Processed model ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B in 75.306s
chaoticneutrals-poppy-po-3816-v3-mkmlizer: creating bucket guanaco-mkml-models
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaoticneutrals-poppy-po-3816-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v3
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v3/config.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v3/tokenizer_config.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v3/special_tokens_map.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v3/tokenizer.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v3/flywheel_model.0.safetensors
chaoticneutrals-poppy-po-3816-v3-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
chaoticneutrals-poppy-po-3816-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.
chaoticneutrals-poppy-po-3816-v3-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-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.
chaoticneutrals-poppy-po-3816-v3-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-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.
chaoticneutrals-poppy-po-3816-v3-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-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()
chaoticneutrals-poppy-po-3816-v3-mkmlizer: return self.fget.__get__(instance, owner)()
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Saving duration: 0.227s
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 3.503s
chaoticneutrals-poppy-po-3816-v3-mkmlizer: creating bucket guanaco-reward-models
chaoticneutrals-poppy-po-3816-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaoticneutrals-poppy-po-3816-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/tokenizer_config.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/config.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/merges.txt
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/special_tokens_map.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/vocab.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/tokenizer.json
chaoticneutrals-poppy-po-3816-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v3_reward/reward.tensors
Job chaoticneutrals-poppy-po-3816-v3-mkmlizer completed after 103.83s with status: succeeded
Stopping job with name chaoticneutrals-poppy-po-3816-v3-mkmlizer
Pipeline stage MKMLizer completed in 106.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaoticneutrals-poppy-po-3816-v3
Waiting for inference service chaoticneutrals-poppy-po-3816-v3 to be ready
Inference service chaoticneutrals-poppy-po-3816-v3 ready after 40.25380611419678s
Pipeline stage ISVCDeployer completed in 47.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9737625122070312s
Received healthy response to inference request in 1.1748874187469482s
Received healthy response to inference request in 1.1681175231933594s
Received healthy response to inference request in 1.1763849258422852s
Received healthy response to inference request in 2.708954334259033s
5 requests
0 failed requests
5th percentile: 1.1694715023040771
10th percentile: 1.170825481414795
20th percentile: 1.1735334396362305
30th percentile: 1.1751869201660157
40th percentile: 1.1757859230041503
50th percentile: 1.1763849258422852
60th percentile: 1.4953359603881835
70th percentile: 1.8142869949340819
80th percentile: 2.120800876617432
90th percentile: 2.4148776054382326
95th percentile: 2.5619159698486325
99th percentile: 2.679546661376953
mean time: 1.6404213428497314
Pipeline stage StressChecker completed in 8.78s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
chaoticneutrals-poppy-po_3816_v3 status is now deployed due to DeploymentManager action
chaoticneutrals-poppy-po_3816_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics