submission_id: bbchicago-test-lora-004-soda_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/Test_Lora_004_soda
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: 2024-06-18T06:50:21+00:00
model_name: bbchicago-test-lora-004-soda_v1
model_group: BBChicago/Test_Lora_004_
num_battles: 15246
num_wins: 7735
celo_rating: 1188.38
propriety_score: 0.6890620800859983
propriety_total_count: 7442.0
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-004-soda_v1
ineligible_reason: None
language_model: BBChicago/Test_Lora_004_soda
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-17
win_ratio: 0.507346189164371
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-004-soda-v1-mkmlizer
Waiting for job on bbchicago-test-lora-004-soda-v1-mkmlizer to finish
bbchicago-test-lora-004-soda-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ /___/ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ belonging to: ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ║ ║
bbchicago-test-lora-004-soda-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-004-soda-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-004-soda-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-004-soda-v1-mkmlizer: Downloaded to shared memory in 33.321s
bbchicago-test-lora-004-soda-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-004-soda-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-004-soda-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 135.55it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 149.86it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 156.49it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 158.32it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 85.14it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 102.17it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 116.56it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 128.88it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 138.86it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 142.49it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 90.38it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 101.44it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 114.44it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 127.11it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 137.82it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 143.84it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.82it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-004-soda-v1-mkmlizer: quantized model in 23.305s
bbchicago-test-lora-004-soda-v1-mkmlizer: Processed model BBChicago/Test_Lora_004_soda in 59.182s
bbchicago-test-lora-004-soda-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-004-soda-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-004-soda-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-004-soda-v1
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-004-soda-v1/config.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-004-soda-v1/special_tokens_map.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-004-soda-v1/tokenizer_config.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-004-soda-v1/tokenizer.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-004-soda-v1/flywheel_model.0.safetensors
bbchicago-test-lora-004-soda-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-004-soda-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-004-soda-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-soda-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-004-soda-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-soda-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-004-soda-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-004-soda-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-004-soda-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-lora-004-soda-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-004-soda-v1-mkmlizer: Saving duration: 0.408s
bbchicago-test-lora-004-soda-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.501s
bbchicago-test-lora-004-soda-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-004-soda-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-004-soda-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/config.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/special_tokens_map.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/tokenizer_config.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/vocab.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/merges.txt
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/tokenizer.json
bbchicago-test-lora-004-soda-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-lora-004-soda-v1_reward/reward.tensors
Job bbchicago-test-lora-004-soda-v1-mkmlizer completed after 83.43s with status: succeeded
Stopping job with name bbchicago-test-lora-004-soda-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-004-soda-v1
Waiting for inference service bbchicago-test-lora-004-soda-v1 to be ready
Inference service bbchicago-test-lora-004-soda-v1 ready after 40.20598101615906s
Pipeline stage ISVCDeployer completed in 47.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1504976749420166s
Received healthy response to inference request in 1.2672314643859863s
Received healthy response to inference request in 1.2860772609710693s
Received healthy response to inference request in 1.2590274810791016s
Received healthy response to inference request in 1.2468986511230469s
5 requests
0 failed requests
5th percentile: 1.249324417114258
10th percentile: 1.2517501831054687
20th percentile: 1.2566017150878905
30th percentile: 1.2606682777404785
40th percentile: 1.2639498710632324
50th percentile: 1.2672314643859863
60th percentile: 1.2747697830200195
70th percentile: 1.2823081016540527
80th percentile: 1.4589613437652589
90th percentile: 1.8047295093536377
95th percentile: 1.977613592147827
99th percentile: 2.115920858383179
mean time: 1.4419465065002441
Pipeline stage StressChecker completed in 7.83s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
bbchicago-test-lora-004-soda_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-004-soda_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics