submission_id: bbchicago-llama3-8b-lora_3778_v5
developer_uid: Bbbrun0
best_of: 16
celo_rating: 1168.74
display_name: bbchicago-llama3-8b-lora_3778_v5
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.0, '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': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: BBChicago/llama3-8b-lora-v0.0.0
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: BBChicago/llama3-8b-lora
model_name: bbchicago-llama3-8b-lora_3778_v5
model_num_parameters: 8030261248.0
model_repo: BBChicago/llama3-8b-lora-v0.0.0
model_size: 8B
num_battles: 7220
num_wins: 3565
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: 2024-06-03T02:26:06+00:00
us_pacific_date: 2024-06-02
win_ratio: 0.4937673130193906
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-llama3-8b-lora-3778-v5-mkmlizer
Waiting for job on bbchicago-llama3-8b-lora-3778-v5-mkmlizer to finish
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║     _____            __           __                                ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║       /___/                                                         ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  belonging to:                                                      ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-llama3-8b-lora-3778-v5-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.
bbchicago-llama3-8b-lora-3778-v5-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Downloaded to shared memory in 25.860s
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:00<00:17, 16.39it/s]
Loading 0:   5%|▌         | 15/291 [00:00<00:03, 77.56it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:03, 77.27it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:02, 96.48it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 83.52it/s]
Loading 0:  21%|██▏       | 62/291 [00:00<00:02, 80.98it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 95.73it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 84.57it/s]
Loading 0:  36%|███▌      | 105/291 [00:01<00:02, 90.88it/s]
Loading 0:  40%|███▉      | 116/291 [00:01<00:01, 94.74it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 84.56it/s]
Loading 0:  49%|████▉     | 143/291 [00:01<00:01, 86.49it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 97.99it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:01, 88.88it/s]
Loading 0:  64%|██████▍   | 186/291 [00:02<00:01, 96.23it/s]
Loading 0:  69%|██████▊   | 200/291 [00:02<00:00, 103.33it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 91.45it/s] 
Loading 0:  77%|███████▋  | 224/291 [00:02<00:00, 88.41it/s]
Loading 0:  82%|████████▏ | 239/291 [00:02<00:00, 100.23it/s]
Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 91.88it/s] 
Loading 0:  92%|█████████▏| 267/291 [00:02<00:00, 95.92it/s]
Loading 0:  97%|█████████▋| 281/291 [00:03<00:00, 103.46it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: quantized model in 23.420s
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Processed model BBChicago/llama3-8b-lora-v0.0.0 in 51.762s
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v5
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v5/tokenizer_config.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v5/config.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v5/special_tokens_map.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v5/tokenizer.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v5/flywheel_model.0.safetensors
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-llama3-8b-lora-3778-v5-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.
bbchicago-llama3-8b-lora-3778-v5-mkmlizer:   warnings.warn(
bbchicago-llama3-8b-lora-3778-v5-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.
bbchicago-llama3-8b-lora-3778-v5-mkmlizer:   warnings.warn(
bbchicago-llama3-8b-lora-3778-v5-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.
bbchicago-llama3-8b-lora-3778-v5-mkmlizer:   warnings.warn(
bbchicago-llama3-8b-lora-3778-v5-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()
bbchicago-llama3-8b-lora-3778-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Saving duration: 0.397s
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.108s
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: creating bucket guanaco-reward-models
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/special_tokens_map.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/tokenizer_config.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/config.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/vocab.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/tokenizer.json
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/merges.txt
bbchicago-llama3-8b-lora-3778-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v5_reward/reward.tensors
Job bbchicago-llama3-8b-lora-3778-v5-mkmlizer completed after 72.71s with status: succeeded
Stopping job with name bbchicago-llama3-8b-lora-3778-v5-mkmlizer
Pipeline stage MKMLizer completed in 76.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-llama3-8b-lora-3778-v5
Waiting for inference service bbchicago-llama3-8b-lora-3778-v5 to be ready
Inference service bbchicago-llama3-8b-lora-3778-v5 ready after 150.7248079776764s
Pipeline stage ISVCDeployer completed in 157.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1520156860351562s
Received healthy response to inference request in 1.2672960758209229s
Received healthy response to inference request in 1.2734792232513428s
Received healthy response to inference request in 1.2805049419403076s
Received healthy response to inference request in 1.2892241477966309s
5 requests
0 failed requests
5th percentile: 1.2685327053070068
10th percentile: 1.2697693347930907
20th percentile: 1.2722425937652588
30th percentile: 1.2748843669891357
40th percentile: 1.2776946544647216
50th percentile: 1.2805049419403076
60th percentile: 1.283992624282837
70th percentile: 1.2874803066253662
80th percentile: 1.4617824554443362
90th percentile: 1.806899070739746
95th percentile: 1.979457378387451
99th percentile: 2.117504024505615
mean time: 1.4525040149688722
Pipeline stage StressChecker completed in 7.88s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.23s
bbchicago-llama3-8b-lora_3778_v5 status is now deployed due to DeploymentManager action
bbchicago-llama3-8b-lora_3778_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-llama3-8b-lora_3778_v5
Running pipeline stage ISVCDeleter
Checking if service bbchicago-llama3-8b-lora-3778-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.15s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-llama3-8b-lora-3778-v5/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.30s
bbchicago-llama3-8b-lora_3778_v5 status is now torndown due to DeploymentManager action