bbchicago-test-l3-iterat_3475

submission_id: bbchicago-test-l3-iterat_3475_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1185.79

display_name: bbchicago-test-l3-iterat_3475_v1

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/test_L3-iterative-DPO-final

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: BBChicago/test_L3-iterat

model_name: bbchicago-test-l3-iterat_3475_v1

model_num_parameters: 8030261248.0

model_repo: BBChicago/test_L3-iterative-DPO-final

model_size: 8B

num_battles: 20344

num_wins: 10684

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: 2024-06-11T10:32:03+00:00

us_pacific_date: 2024-06-11

win_ratio: 0.5251671254423909

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-test-l3-iterat-3475-v1-mkmlizer
Waiting for job on bbchicago-test-l3-iterat-3475-v1-mkmlizer to finish
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ║                                                                     ║
bbchicago-test-l3-iterat-3475-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-l3-iterat-3475-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.
bbchicago-test-l3-iterat-3475-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Downloaded to shared memory in 33.281s
bbchicago-test-l3-iterat-3475-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-l3-iterat-3475-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 132.06it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 148.37it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 154.22it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 157.53it/s]
Loading 0:  29%|██▉       | 84/291 [00:00<00:02, 83.05it/s] 
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 101.24it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:01, 115.81it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 128.62it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 139.30it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 143.94it/s]
Loading 0:  65%|██████▍   | 189/291 [00:01<00:01, 91.16it/s] 
Loading 0:  70%|███████   | 204/291 [00:01<00:00, 102.20it/s]
Loading 0:  76%|███████▌  | 221/291 [00:01<00:00, 115.68it/s]
Loading 0:  82%|████████▏ | 239/291 [00:01<00:00, 127.93it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 138.99it/s]
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 148.50it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-l3-iterat-3475-v1-mkmlizer: quantized model in 22.600s
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Processed model BBChicago/test_L3-iterative-DPO-final in 58.401s
bbchicago-test-l3-iterat-3475-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-l3-iterat-3475-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-l3-iterat-3475-v1
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-l3-iterat-3475-v1/config.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-l3-iterat-3475-v1/special_tokens_map.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-l3-iterat-3475-v1/tokenizer_config.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-l3-iterat-3475-v1/tokenizer.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-l3-iterat-3475-v1/flywheel_model.0.safetensors
bbchicago-test-l3-iterat-3475-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-l3-iterat-3475-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.
bbchicago-test-l3-iterat-3475-v1-mkmlizer:   warnings.warn(
bbchicago-test-l3-iterat-3475-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.
bbchicago-test-l3-iterat-3475-v1-mkmlizer:   warnings.warn(
bbchicago-test-l3-iterat-3475-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.
bbchicago-test-l3-iterat-3475-v1-mkmlizer:   warnings.warn(
bbchicago-test-l3-iterat-3475-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()
bbchicago-test-l3-iterat-3475-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Saving duration: 0.405s
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.935s
bbchicago-test-l3-iterat-3475-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-l3-iterat-3475-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-l3-iterat-3475-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/special_tokens_map.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/config.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/vocab.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/merges.txt
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/tokenizer_config.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/tokenizer.json
bbchicago-test-l3-iterat-3475-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-l3-iterat-3475-v1_reward/reward.tensors
Job bbchicago-test-l3-iterat-3475-v1-mkmlizer completed after 83.04s with status: succeeded
Stopping job with name bbchicago-test-l3-iterat-3475-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-l3-iterat-3475-v1
Waiting for inference service bbchicago-test-l3-iterat-3475-v1 to be ready
Inference service bbchicago-test-l3-iterat-3475-v1 ready after 40.20316410064697s
Pipeline stage ISVCDeployer completed in 47.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1752519607543945s
Received healthy response to inference request in 1.2438926696777344s
Received healthy response to inference request in 1.2352614402770996s
Received healthy response to inference request in 1.258382797241211s
Received healthy response to inference request in 1.2530760765075684s
5 requests
0 failed requests
5th percentile: 1.2369876861572267
10th percentile: 1.2387139320373535
20th percentile: 1.2421664237976073
30th percentile: 1.245729351043701
40th percentile: 1.2494027137756347
50th percentile: 1.2530760765075684
60th percentile: 1.2551987648010254
70th percentile: 1.2573214530944825
80th percentile: 1.4417566299438478
90th percentile: 1.8085042953491213
95th percentile: 1.9918781280517577
99th percentile: 2.138577194213867
mean time: 1.4331729888916016
Pipeline stage StressChecker completed in 7.78s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-test-l3-iterat_3475_v1 status is now deployed due to DeploymentManager action
bbchicago-test-l3-iterat_3475_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-l3-iterat_3475_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-l3-iterat-3475-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-l3-iterat-3475-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-iterat-3475-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-iterat-3475-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-iterat-3475-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-l3-iterat-3475-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-l3-iterat-3475-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.55s
bbchicago-test-l3-iterat_3475_v1 status is now torndown due to DeploymentManager action