submission_id: bbchicago-test-lora-002_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Test_Lora_002
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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}
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}
reward_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}
timestamp: 2024-06-13T07:53:11+00:00
model_name: bbchicago-test-lora-002_v1
model_eval_status: success
model_group: BBChicago/Test_Lora_002
num_battles: 14022
num_wins: 7004
celo_rating: 1181.19
propriety_score: 0.6931137724550899
propriety_total_count: 6012.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bbchicago-test-lora-002_v1
ineligible_reason: None
language_model: BBChicago/Test_Lora_002
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-13
win_ratio: 0.499500784481529
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-002-v1-mkmlizer
Waiting for job on bbchicago-test-lora-002-v1-mkmlizer to finish
bbchicago-test-lora-002-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-002-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-lora-002-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-lora-002-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-lora-002-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-lora-002-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-lora-002-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-002-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-lora-002-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-lora-002-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-lora-002-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-002-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-lora-002-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-lora-002-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-002-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-lora-002-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-lora-002-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-lora-002-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-002-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-002-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-lora-002-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-002-v1-mkmlizer: Downloaded to shared memory in 30.193s
bbchicago-test-lora-002-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-002-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-002-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:46,  2.24s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:01,  4.46it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:21, 11.84it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.29it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.34it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 36.33it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.20it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.52it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 81.34it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 97.71it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.45it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 90.08it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 105.76it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 118.83it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 130.91it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 141.10it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 92.73it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:06<00:00, 103.13it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-002-v1-mkmlizer: quantized model in 22.911s
bbchicago-test-lora-002-v1-mkmlizer: Processed model BBChicago/Test_Lora_002 in 55.698s
bbchicago-test-lora-002-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-002-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-002-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-002-v1
bbchicago-test-lora-002-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-002-v1/special_tokens_map.json
bbchicago-test-lora-002-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-002-v1/config.json
bbchicago-test-lora-002-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-002-v1/tokenizer_config.json
bbchicago-test-lora-002-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-002-v1/tokenizer.json
bbchicago-test-lora-002-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-002-v1/flywheel_model.0.safetensors
bbchicago-test-lora-002-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-002-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-lora-002-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-002-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-lora-002-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-002-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-lora-002-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-002-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-lora-002-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-lora-002-v1-mkmlizer: Saving duration: 0.418s
bbchicago-test-lora-002-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.992s
bbchicago-test-lora-002-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-002-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-002-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/config.json
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/special_tokens_map.json
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/tokenizer_config.json
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/merges.txt
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/vocab.json
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/tokenizer.json
bbchicago-test-lora-002-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-002-v1_reward/reward.tensors
Job bbchicago-test-lora-002-v1-mkmlizer completed after 83.05s with status: succeeded
Stopping job with name bbchicago-test-lora-002-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-002-v1
Waiting for inference service bbchicago-test-lora-002-v1 to be ready
Inference service bbchicago-test-lora-002-v1 ready after 50.24176502227783s
Pipeline stage ISVCDeployer completed in 57.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.285813093185425s
Received healthy response to inference request in 1.2723774909973145s
Received healthy response to inference request in 1.274273157119751s
Received healthy response to inference request in 1.254054069519043s
Received healthy response to inference request in 1.258347511291504s
5 requests
0 failed requests
5th percentile: 1.254912757873535
10th percentile: 1.2557714462280274
20th percentile: 1.2574888229370118
30th percentile: 1.261153507232666
40th percentile: 1.2667654991149901
50th percentile: 1.2723774909973145
60th percentile: 1.2731357574462892
70th percentile: 1.2738940238952636
80th percentile: 1.476581144332886
90th percentile: 1.8811971187591554
95th percentile: 2.0835051059722898
99th percentile: 2.245351495742798
mean time: 1.4689730644226073
Pipeline stage StressChecker completed in 7.93s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
bbchicago-test-lora-002_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-002_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics