submission_id: cycy233-l3-bdpo-v5-c1_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bdpo-v5-c1
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'], '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: {'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: 2024-07-12T16:07:14+00:00
model_name: auto
model_group: cycy233/L3-bdpo-v5-c1
num_battles: 11676
num_wins: 4989
celo_rating: 1128.37
alignment_score: None
alignment_samples: 0
propriety_score: 0.7882139319907561
propriety_total_count: 6058.0
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-v5-c1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-12
win_ratio: 0.4272867420349435
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bdpo-v5-c1-v2-mkmlizer
Waiting for job on cycy233-l3-bdpo-v5-c1-v2-mkmlizer to finish
Failed to get response for submission neversleep-noromaid-v0_8068_v133: ('http://neversleep-noromaid-v0-8068-v133-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: remote connection failure, transport failure reason: delayed connect error: 113')
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ /___/ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Downloaded to shared memory in 22.376s
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 114.55it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:01, 133.53it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 112.12it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:02, 116.15it/s] Loading 0: 24%|██▎ | 69/291 [00:00<00:02, 110.88it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:03, 64.65it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 70.91it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 76.39it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 92.98it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 93.79it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 107.09it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 104.60it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 108.52it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 69.49it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 62.28it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 66.75it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 80.26it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 96.97it/s] Loading 0: 86%|████████▌ | 249/291 [00:02<00:00, 100.53it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 108.95it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 107.31it/s] Loading 0: 99%|█████████▉| 288/291 [00:09<00:00, 6.48it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: quantized model in 29.356s
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Processed model cycy233/L3-bdpo-v5-c1 in 51.732s
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v2
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v2/config.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v2/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v2/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v2/tokenizer.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v5-c1-v2-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-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v2-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-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v2-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-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v2-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-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v2-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-c1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Saving duration: 2.262s
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.656s
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/config.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/vocab.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/merges.txt
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/tokenizer.json
cycy233-l3-bdpo-v5-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v2_reward/reward.tensors
Job cycy233-l3-bdpo-v5-c1-v2-mkmlizer completed after 165.48s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v5-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 166.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v5-c1-v2
Waiting for inference service cycy233-l3-bdpo-v5-c1-v2 to be ready
Inference service cycy233-l3-bdpo-v5-c1-v2 ready after 40.20243525505066s
Pipeline stage ISVCDeployer completed in 47.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.107887029647827s
Received healthy response to inference request in 1.2723445892333984s
Received healthy response to inference request in 1.256141185760498s
Received healthy response to inference request in 1.2631208896636963s
Received healthy response to inference request in 1.2682359218597412s
5 requests
0 failed requests
5th percentile: 1.2575371265411377
10th percentile: 1.2589330673217773
20th percentile: 1.2617249488830566
30th percentile: 1.2641438961029052
40th percentile: 1.2661899089813233
50th percentile: 1.2682359218597412
60th percentile: 1.2698793888092041
70th percentile: 1.271522855758667
80th percentile: 1.4394530773162844
90th percentile: 1.7736700534820558
95th percentile: 1.9407785415649412
99th percentile: 2.07446533203125
mean time: 1.4335459232330323
Pipeline stage StressChecker completed in 7.77s
cycy233-l3-bdpo-v5-c1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v5-c1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics