submission_id: hastagaras-llama-3-8b-duh_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1196.14
display_name: probably-low-safety
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this roleplay chat between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following {bot_name}'s persona: {memory}\n\n", 'prompt_template': 'Scenario: {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}
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-duh
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-du
model_name: probably-low-safety
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-duh
model_size: 8B
num_battles: 25398
num_wins: 13706
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-15T09:08:12+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.539648791243405
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-duh-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-duh-v1-mkmlizer to finish
hastagaras-llama-3-8b-duh-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-duh-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 174.51it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:01, 189.17it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:01, 179.08it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 178.33it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 65.71it/s] 
Loading 0:  37%|███▋      | 107/291 [00:01<00:02, 74.96it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 95.35it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 117.35it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 132.62it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 85.05it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 96.34it/s]
Loading 0:  77%|███████▋  | 225/291 [00:02<00:00, 119.12it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 136.19it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 147.63it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 12.70it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-duh-v1-mkmlizer: quantized model in 17.981s
hastagaras-llama-3-8b-duh-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-duh in 46.557s
hastagaras-llama-3-8b-duh-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-duh-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-duh-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v1
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v1/tokenizer_config.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v1/config.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v1/special_tokens_map.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v1/tokenizer.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-duh-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-duh-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()
hastagaras-llama-3-8b-duh-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-duh-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-duh-v1-mkmlizer: Saving duration: 0.270s
hastagaras-llama-3-8b-duh-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.062s
hastagaras-llama-3-8b-duh-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-duh-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-duh-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward/merges.txt
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward/vocab.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward/tokenizer.json
hastagaras-llama-3-8b-duh-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v1_reward/config.json
Job hastagaras-llama-3-8b-duh-v1-mkmlizer completed after 72.94s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-duh-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-duh-v1
Waiting for inference service hastagaras-llama-3-8b-duh-v1 to be ready
Inference service hastagaras-llama-3-8b-duh-v1 ready after 40.19493770599365s
Pipeline stage ISVCDeployer completed in 48.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2561917304992676s
Received healthy response to inference request in 1.3472731113433838s
Received healthy response to inference request in 1.276430606842041s
Received healthy response to inference request in 1.3237011432647705s
Received healthy response to inference request in 1.3116874694824219s
5 requests
0 failed requests
5th percentile: 1.283481979370117
10th percentile: 1.2905333518981934
20th percentile: 1.3046360969543458
30th percentile: 1.3140902042388916
40th percentile: 1.3188956737518311
50th percentile: 1.3237011432647705
60th percentile: 1.3331299304962159
70th percentile: 1.3425587177276612
80th percentile: 1.5290568351745608
90th percentile: 1.8926242828369142
95th percentile: 2.0744080066680906
99th percentile: 2.219834985733032
mean time: 1.503056812286377
Pipeline stage StressChecker completed in 8.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
hastagaras-llama-3-8b-duh_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-duh_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-duh_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-duh-v1 is running
Tearing down inference service hastagaras-llama-3-8b-duh-v1
Toredown service hastagaras-llama-3-8b-duh-v1
Pipeline stage ISVCDeleter completed in 5.30s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-duh-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-duh-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-duh-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-duh-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-duh-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-duh-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-duh-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-duh-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-duh-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-duh-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-duh-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-duh-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.53s
hastagaras-llama-3-8b-duh_v1 status is now torndown due to DeploymentManager action