cycy233-l3-bdpo-v3-c1

developer_uid: shiroe40

submission_id: cycy233-l3-bdpo-v3-c1_v1

model_name: auto

model_group: cycy233/L3-bdpo-v3-c1

status: torndown

timestamp: 2024-07-12T03:06:10+00:00

num_battles: 19323

num_wins: 10391

celo_rating: 1225.59

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-bdpo-v3-c1

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-v3-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-11

win_ratio: 0.5377529369145578

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-v3-c1-v1-mkmlizer
Waiting for job on cycy233-l3-bdpo-v3-c1-v1-mkmlizer to finish
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Downloaded to shared memory in 31.211s
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 110.44it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 123.03it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 119.88it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 124.82it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 119.16it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:01, 121.74it/s]
Loading 0:  32%|███▏      | 93/291 [00:01<00:03, 50.54it/s] 
Loading 0:  36%|███▌      | 104/291 [00:01<00:03, 58.02it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:02, 74.58it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:02, 79.77it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 95.05it/s]
Loading 0:  55%|█████▍    | 159/291 [00:01<00:01, 97.04it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:01, 102.47it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 57.51it/s] 
Loading 0:  67%|██████▋   | 196/291 [00:02<00:01, 62.01it/s]
Loading 0:  72%|███████▏  | 210/291 [00:02<00:01, 74.09it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 78.49it/s]
Loading 0:  80%|███████▉  | 232/291 [00:02<00:00, 87.46it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 94.98it/s]
Loading 0:  88%|████████▊ | 257/291 [00:03<00:00, 94.00it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 106.66it/s]
Loading 0:  98%|█████████▊| 285/291 [00:03<00:00, 108.13it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: quantized model in 30.231s
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Processed model cycy233/L3-bdpo-v3-c1 in 61.442s
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v3-c1-v1
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v3-c1-v1/config.json
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v3-c1-v1/special_tokens_map.json
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v3-c1-v1/tokenizer_config.json
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v3-c1-v1/tokenizer.json
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v3-c1-v1/flywheel_model.0.safetensors
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v3-c1-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-v3-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v3-c1-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-v3-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v3-c1-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-v3-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v3-c1-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-v3-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v3-c1-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-v3-c1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Saving duration: 0.535s
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.346s
cycy233-l3-bdpo-v3-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v3-c1-v1_reward/reward.tensors
Job cycy233-l3-bdpo-v3-c1-v1-mkmlizer completed after 93.47s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v3-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v3-c1-v1
Waiting for inference service cycy233-l3-bdpo-v3-c1-v1 to be ready
Inference service cycy233-l3-bdpo-v3-c1-v1 ready after 40.18535780906677s
Pipeline stage ISVCDeployer completed in 46.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.004511594772339s
Received healthy response to inference request in 1.477609395980835s
Received healthy response to inference request in 1.2642359733581543s
Received healthy response to inference request in 1.250999927520752s
Received healthy response to inference request in 1.2660260200500488s
5 requests
0 failed requests
5th percentile: 1.2536471366882325
10th percentile: 1.256294345855713
20th percentile: 1.2615887641906738
30th percentile: 1.2645939826965331
40th percentile: 1.265310001373291
50th percentile: 1.2660260200500488
60th percentile: 1.3506593704223633
70th percentile: 1.4352927207946777
80th percentile: 1.5829898357391359
90th percentile: 1.7937507152557373
95th percentile: 1.899131155014038
99th percentile: 1.9834355068206786
mean time: 1.4526765823364258
Pipeline stage StressChecker completed in 8.23s
cycy233-l3-bdpo-v3-c1_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v3-c1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v3-c1_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v3-c1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v3-c1-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v3-c1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v3-c1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v3-c1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v3-c1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v3-c1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
cycy233-l3-bdpo-v3-c1_v1 status is now torndown due to DeploymentManager action