developer_uid: shiroe40
submission_id: cycy233-l3-bdpo-v5-c2_v3
model_name: auto
model_group: cycy233/L3-bdpo-v5-c2
status: torndown
timestamp: 2024-07-12T16:10:12+00:00
num_battles: 11749
num_wins: 5029
celo_rating: 1127.72
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bdpo-v5-c2
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-v5-c2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-12
win_ratio: 0.428036428632224
generation_params: {'temperature': 0.6, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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-v5-c2-v3-mkmlizer
Waiting for job on cycy233-l3-bdpo-v5-c2-v3-mkmlizer to finish
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Downloaded to shared memory in 23.753s
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 118.46it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 130.53it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 121.55it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:01, 132.62it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:01, 129.88it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:03, 60.29it/s] 
Loading 0:  34%|███▍      | 100/291 [00:01<00:02, 75.36it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:02, 83.29it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 94.94it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 99.77it/s]
Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 109.50it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 112.56it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 119.37it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 62.32it/s] 
Loading 0:  71%|███████▏  | 208/291 [00:02<00:01, 76.81it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 83.69it/s]
Loading 0:  80%|████████  | 234/291 [00:02<00:00, 95.07it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 100.81it/s]
Loading 0:  90%|████████▉ | 261/291 [00:02<00:00, 109.35it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 110.94it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00,  6.28it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: quantized model in 28.967s
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Processed model cycy233/L3-bdpo-v5-c2 in 52.721s
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v3
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v3/special_tokens_map.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v3/config.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v3/tokenizer_config.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v3/tokenizer.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v5-c2-v3-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-v5-c2-v3-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c2-v3-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-v5-c2-v3-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c2-v3-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-v5-c2-v3-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c2-v3-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-v5-c2-v3-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c2-v3-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-v5-c2-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Saving duration: 0.529s
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.582s
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/special_tokens_map.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/vocab.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/config.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/tokenizer_config.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/merges.txt
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/tokenizer.json
cycy233-l3-bdpo-v5-c2-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v3_reward/reward.tensors
Job cycy233-l3-bdpo-v5-c2-v3-mkmlizer completed after 83.17s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v5-c2-v3-mkmlizer
Pipeline stage MKMLizer completed in 83.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v5-c2-v3
Waiting for inference service cycy233-l3-bdpo-v5-c2-v3 to be ready
Inference service cycy233-l3-bdpo-v5-c2-v3 ready after 40.2054603099823s
Pipeline stage ISVCDeployer completed in 47.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.113145351409912s
Received healthy response to inference request in 1.340878963470459s
Received healthy response to inference request in 1.3242266178131104s
Received healthy response to inference request in 1.276496410369873s
Received healthy response to inference request in 1.344374179840088s
5 requests
0 failed requests
5th percentile: 1.2860424518585205
10th percentile: 1.295588493347168
20th percentile: 1.314680576324463
30th percentile: 1.32755708694458
40th percentile: 1.3342180252075195
50th percentile: 1.340878963470459
60th percentile: 1.3422770500183105
70th percentile: 1.343675136566162
80th percentile: 1.498128414154053
90th percentile: 1.8056368827819824
95th percentile: 1.959391117095947
99th percentile: 2.082394504547119
mean time: 1.4798243045806885
Pipeline stage StressChecker completed in 8.05s
cycy233-l3-bdpo-v5-c2_v3 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v5-c2_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v5-c2_v3
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v5-c2-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v5-c2-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.26s
cycy233-l3-bdpo-v5-c2_v3 status is now torndown due to DeploymentManager action