bbchicago-llama3-8b-lora_3778

submission_id: bbchicago-llama3-8b-lora_3778_v3

developer_uid: Bbbrun0

best_of: 4

celo_rating: 1150.21

display_name: bbchicago-llama3-8b-lora_3778_v3

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': 4, '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_v3

model_num_parameters: 8030261248.0

model_repo: BBChicago/llama3-8b-lora-v0.0.0

model_size: 8B

num_battles: 8549

num_wins: 3988

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: 2024-06-03T02:13:08+00:00

us_pacific_date: 2024-06-02

win_ratio: 0.4664873084571295

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-llama3-8b-lora-3778-v3-mkmlizer
Waiting for job on bbchicago-llama3-8b-lora-3778-v3-mkmlizer to finish
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║     _____            __           __                                ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║       /___/                                                         ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  belonging to:                                                      ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ║                                                                     ║
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Downloaded to shared memory in 77.231s
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:00<00:17, 16.92it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:03, 72.03it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:03, 79.41it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:02, 97.33it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 85.66it/s]
Loading 0:  21%|██▏       | 62/291 [00:00<00:02, 83.21it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 97.69it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 85.69it/s]
Loading 0:  36%|███▌      | 105/291 [00:01<00:02, 92.54it/s]
Loading 0:  40%|███▉      | 115/291 [00:01<00:01, 94.04it/s]
Loading 0:  43%|████▎     | 125/291 [00:01<00:01, 86.31it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 101.54it/s]
Loading 0:  52%|█████▏    | 151/291 [00:01<00:01, 89.13it/s] 
Loading 0:  56%|█████▋    | 164/291 [00:01<00:01, 85.44it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:01, 99.53it/s]
Loading 0:  65%|██████▌   | 190/291 [00:02<00:01, 90.82it/s]
Loading 0:  70%|███████   | 205/291 [00:02<00:00, 89.60it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 98.23it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 88.42it/s]
Loading 0:  84%|████████▍ | 245/291 [00:02<00:00, 90.95it/s]
Loading 0:  89%|████████▉ | 260/291 [00:02<00:00, 103.29it/s]
Loading 0:  93%|█████████▎| 271/291 [00:02<00:00, 93.92it/s] 
Loading 0:  98%|█████████▊| 286/291 [00:03<00:00, 92.44it/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-v3-mkmlizer: quantized model in 23.573s
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Processed model BBChicago/llama3-8b-lora-v0.0.0 in 103.357s
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v3
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v3/tokenizer.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v3/tokenizer_config.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v3/config.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v3/special_tokens_map.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v3/flywheel_model.0.safetensors
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v3-mkmlizer:   warnings.warn(
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v3-mkmlizer:   warnings.warn(
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v3-mkmlizer:   warnings.warn(
bbchicago-llama3-8b-lora-3778-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()
bbchicago-llama3-8b-lora-3778-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Saving duration: 0.396s
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.548s
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: creating bucket guanaco-reward-models
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/special_tokens_map.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/config.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/tokenizer_config.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/vocab.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/merges.txt
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/tokenizer.json
bbchicago-llama3-8b-lora-3778-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v3_reward/reward.tensors
Job bbchicago-llama3-8b-lora-3778-v3-mkmlizer completed after 134.01s with status: succeeded
Stopping job with name bbchicago-llama3-8b-lora-3778-v3-mkmlizer
Pipeline stage MKMLizer completed in 138.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-llama3-8b-lora-3778-v3
Waiting for inference service bbchicago-llama3-8b-lora-3778-v3 to be ready
Inference service bbchicago-llama3-8b-lora-3778-v3 ready after 40.25741386413574s
Pipeline stage ISVCDeployer completed in 47.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.089144468307495s
Received healthy response to inference request in 1.1253538131713867s
Received healthy response to inference request in 2.2909560203552246s
Received healthy response to inference request in 1.1300325393676758s
Received healthy response to inference request in 1.1279902458190918s
5 requests
0 failed requests
5th percentile: 1.1258810997009276
10th percentile: 1.1264083862304688
20th percentile: 1.1274629592895509
30th percentile: 1.1283987045288086
40th percentile: 1.129215621948242
50th percentile: 1.1300325393676758
60th percentile: 1.5136773109436035
70th percentile: 1.8973220825195312
80th percentile: 2.129506778717041
90th percentile: 2.210231399536133
95th percentile: 2.2505937099456785
99th percentile: 2.2828835582733156
mean time: 1.5526954174041747
Pipeline stage StressChecker completed in 8.40s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
bbchicago-llama3-8b-lora_3778_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-llama3-8b-lora_3778_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-llama3-8b-lora_3778_v3
Running pipeline stage ISVCDeleter
Checking if service bbchicago-llama3-8b-lora-3778-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-llama3-8b-lora-3778-v3/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.64s
bbchicago-llama3-8b-lora_3778_v3 status is now torndown due to DeploymentManager action