developer_uid: shiroe40
submission_id: cycy233-l3-bdpo-v4-c4_v1
model_name: auto
model_group: cycy233/L3-bdpo-v4-c4
status: torndown
timestamp: 2024-07-12T09:08:04+00:00
num_battles: 19800
num_wins: 10640
celo_rating: 1223.39
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bdpo-v4-c4
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-bdpo-v4-c4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-12
win_ratio: 0.5373737373737374
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: {'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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bdpo-v4-c4-v1-mkmlizer
Waiting for job on cycy233-l3-bdpo-v4-c4-v1-mkmlizer to finish
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Downloaded to shared memory in 39.034s
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 114.03it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 127.32it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 124.59it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:01, 123.69it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 120.90it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 126.76it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:03, 56.61it/s] 
Loading 0:  37%|███▋      | 107/291 [00:01<00:02, 68.35it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:02, 79.54it/s]
Loading 0:  45%|████▌     | 132/291 [00:01<00:01, 83.80it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 95.82it/s]
Loading 0:  55%|█████▍    | 159/291 [00:01<00:01, 92.78it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:01, 102.03it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 58.46it/s] 
Loading 0:  68%|██████▊   | 197/291 [00:02<00:01, 64.82it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 76.28it/s]
Loading 0:  77%|███████▋  | 225/291 [00:02<00:00, 88.56it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 96.25it/s]
Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 92.96it/s]
Loading 0:  90%|████████▉ | 261/291 [00:03<00:00, 90.06it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 91.30it/s]
Loading 0:  98%|█████████▊| 284/291 [00:03<00:00, 95.44it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: quantized model in 29.161s
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Processed model cycy233/L3-bdpo-v4-c4 in 68.195s
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v4-c4-v1
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v4-c4-v1/config.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v4-c4-v1/tokenizer_config.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v4-c4-v1/special_tokens_map.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v4-c4-v1/tokenizer.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v4-c4-v1/flywheel_model.0.safetensors
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v4-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cycy233-l3-bdpo-v4-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v4-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v4-c4-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.
cycy233-l3-bdpo-v4-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v4-c4-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()
cycy233-l3-bdpo-v4-c4-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Saving duration: 0.512s
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.250s
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/config.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/tokenizer_config.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/special_tokens_map.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/merges.txt
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/vocab.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/tokenizer.json
cycy233-l3-bdpo-v4-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v4-c4-v1_reward/reward.tensors
Job cycy233-l3-bdpo-v4-c4-v1-mkmlizer completed after 104.23s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v4-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v4-c4-v1
Waiting for inference service cycy233-l3-bdpo-v4-c4-v1 to be ready
Inference service cycy233-l3-bdpo-v4-c4-v1 ready after 40.17749738693237s
Pipeline stage ISVCDeployer completed in 46.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0592782497406006s
Received healthy response to inference request in 1.261315107345581s
Received healthy response to inference request in 1.2809467315673828s
Received healthy response to inference request in 1.2827990055084229s
Received healthy response to inference request in 1.2724378108978271s
5 requests
0 failed requests
5th percentile: 1.2635396480560304
10th percentile: 1.2657641887664794
20th percentile: 1.2702132701873778
30th percentile: 1.2741395950317382
40th percentile: 1.2775431632995606
50th percentile: 1.2809467315673828
60th percentile: 1.2816876411437987
70th percentile: 1.2824285507202149
80th percentile: 1.4380948543548586
90th percentile: 1.7486865520477295
95th percentile: 1.9039824008941648
99th percentile: 2.0282190799713136
mean time: 1.4313553810119628
Pipeline stage StressChecker completed in 7.82s
cycy233-l3-bdpo-v4-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v4-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v4-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v4-c4-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v4-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v4-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v4-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v4-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v4-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v4-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.57s
cycy233-l3-bdpo-v4-c4_v1 status is now torndown due to DeploymentManager action