submission_id: gryphe-pantheon-rp-8b-llama-3_v6
developer_uid: Gryphe
status: torndown
model_repo: Gryphe/Pantheon-RP-8b-Llama-3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, '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': "<|im_start|>system\n{bot_name}'s personality: {memory}\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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: 2024-05-15T16:14:51+00:00
model_name: gryphe-pantheon-rp-8b-l3_v1
model_eval_status: success
model_group: Gryphe/Pantheon-RP-8b-Ll
num_battles: 18150
num_wins: 9970
celo_rating: 1207.31
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: gryphe-pantheon-rp-8b-l3_v1
ineligible_reason: propriety_total_count < 800
language_model: Gryphe/Pantheon-RP-8b-Llama-3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-15
win_ratio: 0.5493112947658402
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer
Waiting for job on gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer to finish
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ _____ __ __ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ /___/ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ Version: 0.8.14 ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ https://mk1.ai ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ The license key for the current software has been verified as ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ belonging to: ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ Chai Research Corp. ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ║ ║
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
gryphe-pantheon-rp-8b-llama-3-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.
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Downloaded to shared memory in 54.917s
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: quantizing model to /dev/shm/model_cache
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 124.35it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 146.38it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 154.80it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 159.37it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 90.41it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 107.61it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 122.04it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 133.88it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 143.02it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 146.94it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 94.09it/s] Loading 0: 70%|███████ | 205/291 [00:01<00:00, 106.86it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 116.97it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 129.42it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 139.65it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 147.41it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.09it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: quantized model in 22.389s
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: creating bucket guanaco-mkml-models
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/gryphe-pantheon-rp-8b-llama-3-v6
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/gryphe-pantheon-rp-8b-llama-3-v6/config.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/gryphe-pantheon-rp-8b-llama-3-v6/special_tokens_map.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/gryphe-pantheon-rp-8b-llama-3-v6/tokenizer_config.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/gryphe-pantheon-rp-8b-llama-3-v6/tokenizer.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/gryphe-pantheon-rp-8b-llama-3-v6/flywheel_model.0.safetensors
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
gryphe-pantheon-rp-8b-llama-3-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.
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: warnings.warn(
gryphe-pantheon-rp-8b-llama-3-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.
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: warnings.warn(
gryphe-pantheon-rp-8b-llama-3-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.
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: warnings.warn(
gryphe-pantheon-rp-8b-llama-3-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()
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: return self.fget.__get__(instance, owner)()
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Saving duration: 0.399s
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 23.035s
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: creating bucket guanaco-reward-models
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/special_tokens_map.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/config.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/tokenizer_config.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/merges.txt
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/vocab.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/tokenizer.json
gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/gryphe-pantheon-rp-8b-llama-3-v6_reward/reward.tensors
Job gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer completed after 178.73s with status: succeeded
Stopping job with name gryphe-pantheon-rp-8b-llama-3-v6-mkmlizer
Pipeline stage MKMLizer completed in 181.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service gryphe-pantheon-rp-8b-llama-3-v6
Waiting for inference service gryphe-pantheon-rp-8b-llama-3-v6 to be ready
Inference service gryphe-pantheon-rp-8b-llama-3-v6 ready after 40.41310238838196s
Pipeline stage ISVCDeployer completed in 48.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1693084239959717s
Received healthy response to inference request in 1.2760682106018066s
Received healthy response to inference request in 1.2558324337005615s
Received healthy response to inference request in 1.277446985244751s
Received healthy response to inference request in 1.2771320343017578s
5 requests
0 failed requests
5th percentile: 1.2598795890808105
10th percentile: 1.2639267444610596
20th percentile: 1.2720210552215576
30th percentile: 1.276280975341797
40th percentile: 1.2767065048217774
50th percentile: 1.2771320343017578
60th percentile: 1.2772580146789552
70th percentile: 1.2773839950561523
80th percentile: 1.4558192729949953
90th percentile: 1.8125638484954836
95th percentile: 1.9909361362457274
99th percentile: 2.133633966445923
mean time: 1.4511576175689698
Pipeline stage StressChecker completed in 7.93s
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
gryphe-pantheon-rp-8b-llama-3_v6 status is now deployed due to DeploymentManager action
gryphe-pantheon-rp-8b-llama-3_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of gryphe-pantheon-rp-8b-llama-3_v6
Running pipeline stage ISVCDeleter
Checking if service gryphe-pantheon-rp-8b-llama-3-v6 is running
Tearing down inference service gryphe-pantheon-rp-8b-llama-3-v6
Toredown service gryphe-pantheon-rp-8b-llama-3-v6
Pipeline stage ISVCDeleter completed in 5.08s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key gryphe-pantheon-rp-8b-llama-3-v6/config.json from bucket guanaco-mkml-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/config.json from bucket guanaco-reward-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key gryphe-pantheon-rp-8b-llama-3-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.56s
gryphe-pantheon-rp-8b-llama-3_v6 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics