submission_id: bbchicago-test-lora-001_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Test_Lora_001
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: 2024-06-13T06:14:09+00:00
model_name: bbchicago-test-lora-001_v1
model_eval_status: success
model_group: BBChicago/Test_Lora_001
num_battles: 18019
num_wins: 8973
celo_rating: 1179.97
propriety_score: 0.6890386110391293
propriety_total_count: 7718.0
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-001_v1
ineligible_reason: None
language_model: BBChicago/Test_Lora_001
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.4979743603973583
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-001-v1-mkmlizer
Waiting for job on bbchicago-test-lora-001-v1-mkmlizer to finish
bbchicago-test-lora-001-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-001-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-lora-001-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-lora-001-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-lora-001-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-lora-001-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-lora-001-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-001-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-lora-001-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-lora-001-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-lora-001-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-001-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-lora-001-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-lora-001-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-001-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-lora-001-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-lora-001-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-lora-001-v1-mkmlizer: ║                                                                     ║
bbchicago-test-lora-001-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-001-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-001-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-001-v1-mkmlizer: Downloaded to shared memory in 26.977s
bbchicago-test-lora-001-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-001-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-001-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:51,  2.25s/it]
Loading 0:   5%|▌         | 16/291 [00:04<00:58,  4.73it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.64it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.05it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.13it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 36.15it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.59it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 63.57it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:02, 79.19it/s]
Loading 0:  51%|█████     | 148/291 [00:05<00:01, 93.46it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 73.86it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 89.30it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 104.29it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 118.15it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 129.71it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 139.70it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 91.80it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00, 104.35it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-001-v1-mkmlizer: quantized model in 22.970s
bbchicago-test-lora-001-v1-mkmlizer: Processed model BBChicago/Test_Lora_001 in 52.476s
bbchicago-test-lora-001-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-001-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-001-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-001-v1
bbchicago-test-lora-001-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-001-v1/config.json
bbchicago-test-lora-001-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-001-v1/special_tokens_map.json
bbchicago-test-lora-001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-001-v1/tokenizer_config.json
bbchicago-test-lora-001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-001-v1/tokenizer.json
bbchicago-test-lora-001-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-001-v1/flywheel_model.0.safetensors
bbchicago-test-lora-001-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-001-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-001-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-001-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-001-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-001-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-001-v1-mkmlizer:   warnings.warn(
bbchicago-test-lora-001-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-001-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-lora-001-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-001-v1-mkmlizer: Saving duration: 0.394s
bbchicago-test-lora-001-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.894s
bbchicago-test-lora-001-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-001-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-001-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/tokenizer_config.json
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/merges.txt
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/config.json
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/special_tokens_map.json
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/vocab.json
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/tokenizer.json
bbchicago-test-lora-001-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-001-v1_reward/reward.tensors
Job bbchicago-test-lora-001-v1-mkmlizer completed after 73.03s with status: succeeded
Stopping job with name bbchicago-test-lora-001-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-001-v1
Waiting for inference service bbchicago-test-lora-001-v1 to be ready
Inference service bbchicago-test-lora-001-v1 ready after 40.20387578010559s
Pipeline stage ISVCDeployer completed in 47.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 15.599466323852539s
Received healthy response to inference request in 1.2538161277770996s
Received healthy response to inference request in 1.2979540824890137s
Received healthy response to inference request in 1.2431423664093018s
Received healthy response to inference request in 1.2329683303833008s
5 requests
0 failed requests
5th percentile: 1.2350031375885009
10th percentile: 1.2370379447937012
20th percentile: 1.2411075592041017
30th percentile: 1.2452771186828613
40th percentile: 1.2495466232299806
50th percentile: 1.2538161277770996
60th percentile: 1.2714713096618653
70th percentile: 1.289126491546631
80th percentile: 4.158256530761721
90th percentile: 9.878861427307129
95th percentile: 12.73916387557983
99th percentile: 15.027405834197998
mean time: 4.125469446182251
Pipeline stage StressChecker completed in 21.40s
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-lora-001_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-001_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics