developer_uid: shiroe40
submission_id: cycy233-l3-bdpo-v5-c2_v1
model_name: auto
model_group: cycy233/L3-bdpo-v5-c2
status: torndown
timestamp: 2024-07-12T16:05:26+00:00
num_battles: 13016
num_wins: 5623
celo_rating: 1129.47
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: 0.4320067609096497
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-v5-c2-v1-mkmlizer
Waiting for job on cycy233-l3-bdpo-v5-c2-v1-mkmlizer to finish
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Downloaded to shared memory in 38.432s
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 113.54it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 127.07it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 123.98it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 127.71it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 122.98it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 128.30it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:03, 57.37it/s] 
Loading 0:  37%|███▋      | 108/291 [00:01<00:02, 70.53it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:02, 80.33it/s]
Loading 0:  46%|████▋     | 135/291 [00:01<00:01, 91.88it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 97.72it/s]
Loading 0:  56%|█████▌    | 162/291 [00:01<00:01, 107.63it/s]
Loading 0:  60%|██████    | 176/291 [00:01<00:01, 115.00it/s]
Loading 0:  65%|██████▍   | 189/291 [00:02<00:01, 60.25it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 70.71it/s]
Loading 0:  74%|███████▍  | 215/291 [00:02<00:00, 81.55it/s]
Loading 0:  79%|███████▊  | 229/291 [00:02<00:00, 91.07it/s]
Loading 0:  84%|████████▎ | 243/291 [00:02<00:00, 101.77it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 106.45it/s]
Loading 0:  93%|█████████▎| 270/291 [00:02<00:00, 114.42it/s]
Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 113.97it/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-v1-mkmlizer: quantized model in 28.632s
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Processed model cycy233/L3-bdpo-v5-c2 in 67.065s
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v1
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v1/special_tokens_map.json
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v1/config.json
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v1/tokenizer.json
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v1/tokenizer_config.json
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c2-v1/flywheel_model.0.safetensors
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v5-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-v5-c2-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-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-v5-c2-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-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-v5-c2-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-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-v5-c2-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-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-v5-c2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Saving duration: 0.501s
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.619s
cycy233-l3-bdpo-v5-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c2-v1_reward/reward.tensors
Job cycy233-l3-bdpo-v5-c2-v1-mkmlizer completed after 103.95s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v5-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v5-c2-v1
Waiting for inference service cycy233-l3-bdpo-v5-c2-v1 to be ready
Inference service cycy233-l3-bdpo-v5-c2-v1 ready after 40.374170541763306s
Pipeline stage ISVCDeployer completed in 47.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.164133071899414s
Received healthy response to inference request in 1.2625200748443604s
Received healthy response to inference request in 1.2853121757507324s
Received healthy response to inference request in 1.2669429779052734s
Received healthy response to inference request in 1.2625541687011719s
5 requests
0 failed requests
5th percentile: 1.2625268936157226
10th percentile: 1.262533712387085
20th percentile: 1.2625473499298097
30th percentile: 1.263431930541992
40th percentile: 1.2651874542236328
50th percentile: 1.2669429779052734
60th percentile: 1.2742906570434571
70th percentile: 1.2816383361816406
80th percentile: 1.4610763549804688
90th percentile: 1.8126047134399415
95th percentile: 1.9883688926696776
99th percentile: 2.128980236053467
mean time: 1.4482924938201904
Pipeline stage StressChecker completed in 7.91s
cycy233-l3-bdpo-v5-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v5-c2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v5-c2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v5-c2-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v5-c2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
cycy233-l3-bdpo-v5-c2_v1 status is now torndown due to DeploymentManager action