submission_id: cycy233-l3-bdpo-v6-c2_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bdpo-v6-c2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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: {'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: 2024-07-12T23:10:08+00:00
model_name: auto
model_group: cycy233/L3-bdpo-v6-c2
num_battles: 24700
num_wins: 12775
celo_rating: 1212.34
alignment_score: None
alignment_samples: 0
propriety_score: 0.7017259541366178
propriety_total_count: 12341.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
ineligible_reason: None
language_model: cycy233/L3-bdpo-v6-c2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-12
win_ratio: 0.5172064777327935
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bdpo-v6-c2-v1-mkmlizer
Waiting for job on cycy233-l3-bdpo-v6-c2-v1-mkmlizer to finish
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Downloaded to shared memory in 39.054s
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 117.94it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 112.32it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 126.04it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:01, 119.92it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 124.02it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 118.18it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:03, 52.81it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:03, 62.10it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 74.48it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 84.16it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 86.49it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 102.07it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 104.48it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 110.38it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 55.48it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:01, 68.76it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 78.51it/s] Loading 0: 80%|████████ | 234/291 [00:02<00:00, 90.55it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 95.75it/s] Loading 0: 89%|████████▉ | 260/291 [00:02<00:00, 102.51it/s] Loading 0: 94%|█████████▍| 273/291 [00:03<00:00, 108.32it/s] Loading 0: 98%|█████████▊| 285/291 [00:03<00:00, 107.05it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: quantized model in 29.370s
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Processed model cycy233/L3-bdpo-v6-c2 in 68.425s
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v6-c2-v1
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v6-c2-v1/config.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v6-c2-v1/special_tokens_map.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v6-c2-v1/tokenizer_config.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v6-c2-v1/tokenizer.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v6-c2-v1/flywheel_model.0.safetensors
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v6-c2-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-v6-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v6-c2-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-v6-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v6-c2-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-v6-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v6-c2-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-v6-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v6-c2-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-v6-c2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Saving duration: 0.537s
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.367s
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/config.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/special_tokens_map.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/merges.txt
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/vocab.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/tokenizer_config.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/tokenizer.json
cycy233-l3-bdpo-v6-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v6-c2-v1_reward/reward.tensors
Job cycy233-l3-bdpo-v6-c2-v1-mkmlizer completed after 104.4s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v6-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v6-c2-v1
Waiting for inference service cycy233-l3-bdpo-v6-c2-v1 to be ready
Inference service cycy233-l3-bdpo-v6-c2-v1 ready after 40.1954665184021s
Pipeline stage ISVCDeployer completed in 47.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2473816871643066s
Received healthy response to inference request in 1.3412702083587646s
Received healthy response to inference request in 1.300605297088623s
Received healthy response to inference request in 1.7769732475280762s
Received healthy response to inference request in 1.9350855350494385s
5 requests
0 failed requests
5th percentile: 1.3087382793426514
10th percentile: 1.3168712615966798
20th percentile: 1.3331372261047363
30th percentile: 1.428410816192627
40th percentile: 1.6026920318603517
50th percentile: 1.7769732475280762
60th percentile: 1.8402181625366212
70th percentile: 1.903463077545166
80th percentile: 1.997544765472412
90th percentile: 2.1224632263183594
95th percentile: 2.184922456741333
99th percentile: 2.234889841079712
mean time: 1.7202631950378418
Pipeline stage StressChecker completed in 9.29s
cycy233-l3-bdpo-v6-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v6-c2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics