submission_id: bbchicago-test-lora-005_v1
developer_uid: Bbbrun0
best_of: 16
celo_rating: 1179.57
display_name: bbchicago-test-lora-005_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_Lora_005
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: BBChicago/Test_Lora_005
model_name: bbchicago-test-lora-005_v1
model_num_parameters: 8030261248.0
model_repo: BBChicago/Test_Lora_005
model_size: 8B
num_battles: 24154
num_wins: 12014
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: 2024-06-13T04:21:52+00:00
us_pacific_date: 2024-06-12
win_ratio: 0.49739173635836714
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-lora-005-v1-mkmlizer
Waiting for job on bbchicago-test-lora-005-v1-mkmlizer to finish
bbchicago-test-lora-005-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-lora-005-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-test-lora-005-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-lora-005-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-lora-005-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-lora-005-v1-mkmlizer: ║ /___/ ║
bbchicago-test-lora-005-v1-mkmlizer: ║ ║
bbchicago-test-lora-005-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-lora-005-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-lora-005-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-lora-005-v1-mkmlizer: ║ ║
bbchicago-test-lora-005-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-lora-005-v1-mkmlizer: ║ belonging to: ║
bbchicago-test-lora-005-v1-mkmlizer: ║ ║
bbchicago-test-lora-005-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-lora-005-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-lora-005-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-lora-005-v1-mkmlizer: ║ ║
bbchicago-test-lora-005-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-lora-005-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-005-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-test-lora-005-v1-mkmlizer: Downloaded to shared memory in 33.924s
bbchicago-test-lora-005-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-lora-005-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-lora-005-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 126.83it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 149.63it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 156.41it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 157.15it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 150.11it/s] Loading 0: 33%|███▎ | 96/291 [00:00<00:02, 76.50it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 91.44it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 106.50it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 120.62it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 132.47it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 133.79it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 83.54it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 94.92it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 108.73it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 121.32it/s] Loading 0: 90%|████████▉ | 261/291 [00:02<00:00, 126.75it/s] Loading 0: 95%|█████████▍| 276/291 [00:02<00:00, 130.35it/s] Loading 0: 100%|██████████| 291/291 [00:08<00:00, 8.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-lora-005-v1-mkmlizer: quantized model in 24.212s
bbchicago-test-lora-005-v1-mkmlizer: Processed model BBChicago/Test_Lora_005 in 60.912s
bbchicago-test-lora-005-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-lora-005-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-lora-005-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-lora-005-v1
bbchicago-test-lora-005-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-lora-005-v1/config.json
bbchicago-test-lora-005-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-lora-005-v1/special_tokens_map.json
bbchicago-test-lora-005-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-lora-005-v1/tokenizer.json
bbchicago-test-lora-005-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-lora-005-v1/tokenizer_config.json
bbchicago-test-lora-005-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-lora-005-v1/flywheel_model.0.safetensors
bbchicago-test-lora-005-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-lora-005-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-005-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-005-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-005-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-005-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-005-v1-mkmlizer: warnings.warn(
bbchicago-test-lora-005-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-005-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-lora-005-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-lora-005-v1-mkmlizer: Saving duration: 0.399s
bbchicago-test-lora-005-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.374s
bbchicago-test-lora-005-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-lora-005-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-lora-005-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward
bbchicago-test-lora-005-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward/config.json
bbchicago-test-lora-005-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward/special_tokens_map.json
bbchicago-test-lora-005-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward/vocab.json
bbchicago-test-lora-005-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward/merges.txt
bbchicago-test-lora-005-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward/tokenizer_config.json
bbchicago-test-lora-005-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-lora-005-v1_reward/tokenizer.json
Job bbchicago-test-lora-005-v1-mkmlizer completed after 93.46s with status: succeeded
Stopping job with name bbchicago-test-lora-005-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-lora-005-v1
Waiting for inference service bbchicago-test-lora-005-v1 to be ready
Inference service bbchicago-test-lora-005-v1 ready after 40.397231578826904s
Pipeline stage ISVCDeployer completed in 47.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1670095920562744s
Received healthy response to inference request in 1.2635133266448975s
Received healthy response to inference request in 1.2565274238586426s
Received healthy response to inference request in 1.2501220703125s
Received healthy response to inference request in 1.2536647319793701s
5 requests
0 failed requests
5th percentile: 1.250830602645874
10th percentile: 1.251539134979248
20th percentile: 1.2529561996459961
30th percentile: 1.2542372703552247
40th percentile: 1.2553823471069336
50th percentile: 1.2565274238586426
60th percentile: 1.2593217849731446
70th percentile: 1.2621161460876464
80th percentile: 1.444212579727173
90th percentile: 1.8056110858917238
95th percentile: 1.986310338973999
99th percentile: 2.1308697414398194
mean time: 1.438167428970337
Pipeline stage StressChecker completed in 7.82s
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-005_v1 status is now deployed due to DeploymentManager action
bbchicago-test-lora-005_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-lora-005_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-lora-005-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-lora-005-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-005-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-005-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-005-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-lora-005-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-lora-005-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-005-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-005-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-005-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-005-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-005-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-lora-005-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.58s
bbchicago-test-lora-005_v1 status is now torndown due to DeploymentManager action