maldv-badger-kappa-llama-3-8b

submission_id: maldv-badger-kappa-llama-3-8b_v1

developer_uid: maldevide

best_of: 8

celo_rating: 1193.76

display_name: maldv-badger-kappa-llama-3-8b_v1

family_friendly_score: 0.0

formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}, and are meeting {user_name}.\n\nUse *emotes*\n\nMemory: {memory}', 'prompt_template': "{prompt}. Don't say too much.<|eot_id|>", 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: ', 'truncate_by_message': True}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.01, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

is_internal_developer: False

language_model: maldv/badger-kappa-llama-3-8b

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: maldv/badger-kappa-llama

model_name: maldv-badger-kappa-llama-3-8b_v1

model_num_parameters: 8030261248.0

model_repo: maldv/badger-kappa-llama-3-8b

model_size: 8B

num_battles: 27679

num_wins: 14532

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: 2024-06-04T17:59:27+00:00

us_pacific_date: 2024-06-04

win_ratio: 0.5250189674482459

Resubmit model

Running pipeline stage MKMLizer
Starting job with name maldv-badger-kappa-llama-3-8b-v1-mkmlizer
Waiting for job on maldv-badger-kappa-llama-3-8b-v1-mkmlizer to finish
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║     _____            __           __                                ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║       /___/                                                         ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║                                                                     ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║                                                                     ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  belonging to:                                                      ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║                                                                     ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ║                                                                     ║
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maldv-badger-kappa-llama-3-8b-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.
maldv-badger-kappa-llama-3-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Downloaded to shared memory in 56.099s
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:00<00:22, 12.92it/s]
Loading 0:   3%|▎         | 9/291 [00:00<00:06, 40.31it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 66.32it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 52.58it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:04, 54.94it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:03, 63.15it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:03, 58.80it/s]
Loading 0:  24%|██▎       | 69/291 [00:01<00:03, 60.38it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:02, 76.15it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:03, 62.80it/s]
Loading 0:  34%|███▍      | 100/291 [00:01<00:02, 66.39it/s]
Loading 0:  38%|███▊      | 111/291 [00:01<00:02, 73.32it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:02, 62.83it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 61.63it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:02, 66.93it/s]
Loading 0:  52%|█████▏    | 152/291 [00:02<00:02, 57.31it/s]
Loading 0:  55%|█████▍    | 159/291 [00:02<00:02, 59.01it/s]
Loading 0:  58%|█████▊    | 170/291 [00:02<00:01, 69.36it/s]
Loading 0:  63%|██████▎   | 182/291 [00:02<00:01, 61.13it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 70.46it/s]
Loading 0:  71%|███████▏  | 208/291 [00:03<00:00, 87.97it/s]
Loading 0:  75%|███████▌  | 219/291 [00:03<00:01, 69.46it/s]
Loading 0:  79%|███████▉  | 231/291 [00:03<00:00, 79.51it/s]
Loading 0:  83%|████████▎ | 242/291 [00:03<00:00, 67.50it/s]
Loading 0:  86%|████████▋ | 251/291 [00:03<00:00, 68.56it/s]
Loading 0:  89%|████████▉ | 260/291 [00:03<00:00, 72.31it/s]
Loading 0:  93%|█████████▎| 272/291 [00:09<00:03,  5.86it/s]
Loading 0:  98%|█████████▊| 284/291 [00:09<00:00,  8.44it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: quantized model in 23.969s
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Processed model maldv/badger-kappa-llama-3-8b in 81.235s
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maldv-badger-kappa-llama-3-8b-v1
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maldv-badger-kappa-llama-3-8b-v1/config.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maldv-badger-kappa-llama-3-8b-v1/tokenizer_config.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maldv-badger-kappa-llama-3-8b-v1/special_tokens_map.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/maldv-badger-kappa-llama-3-8b-v1/tokenizer.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maldv-badger-kappa-llama-3-8b-v1/flywheel_model.0.safetensors
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maldv-badger-kappa-llama-3-8b-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.
maldv-badger-kappa-llama-3-8b-v1-mkmlizer:   warnings.warn(
maldv-badger-kappa-llama-3-8b-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.
maldv-badger-kappa-llama-3-8b-v1-mkmlizer:   warnings.warn(
maldv-badger-kappa-llama-3-8b-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.
maldv-badger-kappa-llama-3-8b-v1-mkmlizer:   warnings.warn(
maldv-badger-kappa-llama-3-8b-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()
maldv-badger-kappa-llama-3-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Saving duration: 0.281s
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.571s
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/config.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/tokenizer_config.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/special_tokens_map.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/merges.txt
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/vocab.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/tokenizer.json
maldv-badger-kappa-llama-3-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maldv-badger-kappa-llama-3-8b-v1_reward/reward.tensors
Job maldv-badger-kappa-llama-3-8b-v1-mkmlizer completed after 103.95s with status: succeeded
Stopping job with name maldv-badger-kappa-llama-3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service maldv-badger-kappa-llama-3-8b-v1
Waiting for inference service maldv-badger-kappa-llama-3-8b-v1 to be ready
Inference service maldv-badger-kappa-llama-3-8b-v1 ready after 50.2934148311615s
Pipeline stage ISVCDeployer completed in 55.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2035882472991943s
Received healthy response to inference request in 1.2957789897918701s
Received healthy response to inference request in 1.2709887027740479s
Received healthy response to inference request in 1.3229200839996338s
Received healthy response to inference request in 1.3091297149658203s
5 requests
0 failed requests
5th percentile: 1.2759467601776122
10th percentile: 1.2809048175811768
20th percentile: 1.2908209323883058
30th percentile: 1.2984491348266602
40th percentile: 1.3037894248962403
50th percentile: 1.3091297149658203
60th percentile: 1.3146458625793458
70th percentile: 1.320162010192871
80th percentile: 1.4990537166595461
90th percentile: 1.8513209819793701
95th percentile: 2.0274546146392822
99th percentile: 2.168361520767212
mean time: 1.4804811477661133
Pipeline stage StressChecker completed in 8.59s
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 0.10s
M-Eval Dataset for topic stay_in_character is loaded
maldv-badger-kappa-llama-3-8b_v1 status is now deployed due to DeploymentManager action
maldv-badger-kappa-llama-3-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of maldv-badger-kappa-llama-3-8b_v1
Running pipeline stage ISVCDeleter
Checking if service maldv-badger-kappa-llama-3-8b-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.33s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key maldv-badger-kappa-llama-3-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key maldv-badger-kappa-llama-3-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key maldv-badger-kappa-llama-3-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key maldv-badger-kappa-llama-3-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key maldv-badger-kappa-llama-3-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key maldv-badger-kappa-llama-3-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.66s
maldv-badger-kappa-llama-3-8b_v1 status is now torndown due to DeploymentManager action