submission_id: bbchicago-test-turboderp_4595_v2
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/test_turboderp_DPO_L3-8B-ins-based_e2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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: {'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: 2024-07-03T06:52:09+00:00
model_name: bbchicago-test-turboderp_4595_v2
model_group: BBChicago/test_turboderp
num_battles: 13616
num_wins: 6689
celo_rating: 1171.33
propriety_score: 0.7157765500306936
propriety_total_count: 6516.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bbchicago-test-turboderp_4595_v2
ineligible_reason: None
language_model: BBChicago/test_turboderp_DPO_L3-8B-ins-based_e2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.4912602820211516
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-turboderp-4595-v2-mkmlizer
Waiting for job on bbchicago-test-turboderp-4595-v2-mkmlizer to finish
bbchicago-test-turboderp-4595-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ _____ __ __ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ /___/ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ belonging to: ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ║ ║
bbchicago-test-turboderp-4595-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-turboderp-4595-v2-mkmlizer: Downloaded to shared memory in 46.086s
bbchicago-test-turboderp-4595-v2-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-turboderp-4595-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-turboderp-4595-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 115.66it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 128.31it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 125.30it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:02, 107.15it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 112.01it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 119.94it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 66.40it/s] Loading 0: 37%|███▋ | 108/291 [00:01<00:02, 79.54it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 88.62it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 100.31it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 105.53it/s] Loading 0: 56%|█████▌ | 163/291 [00:01<00:01, 116.47it/s] Loading 0: 61%|██████ | 177/291 [00:01<00:00, 122.59it/s] Loading 0: 66%|██████▌ | 191/291 [00:02<00:01, 71.97it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 77.52it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 89.52it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 96.96it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 107.00it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 111.21it/s] Loading 0: 93%|█████████▎| 270/291 [00:02<00:00, 118.44it/s] Loading 0: 97%|█████████▋| 283/291 [00:02<00:00, 118.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-turboderp-4595-v2-mkmlizer: quantized model in 23.404s
bbchicago-test-turboderp-4595-v2-mkmlizer: Processed model BBChicago/test_turboderp_DPO_L3-8B-ins-based_e2 in 69.491s
bbchicago-test-turboderp-4595-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-turboderp-4595-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-turboderp-4595-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-turboderp-4595-v2
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4595-v2/config.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4595-v2/special_tokens_map.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4595-v2/tokenizer_config.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4595-v2/tokenizer.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-turboderp-4595-v2/flywheel_model.0.safetensors
bbchicago-test-turboderp-4595-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-turboderp-4595-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.
bbchicago-test-turboderp-4595-v2-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4595-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`.
bbchicago-test-turboderp-4595-v2-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4595-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.
bbchicago-test-turboderp-4595-v2-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4595-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.
bbchicago-test-turboderp-4595-v2-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4595-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()
bbchicago-test-turboderp-4595-v2-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-turboderp-4595-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-turboderp-4595-v2-mkmlizer: Saving duration: 0.630s
bbchicago-test-turboderp-4595-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.385s
bbchicago-test-turboderp-4595-v2-mkmlizer: WARNING: Retrying failed request: / ([Errno 110] Connection timed out)
bbchicago-test-turboderp-4595-v2-mkmlizer: WARNING: Waiting 3 sec...
bbchicago-test-turboderp-4595-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-turboderp-4595-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/config.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/tokenizer_config.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/special_tokens_map.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/merges.txt
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/vocab.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/tokenizer.json
bbchicago-test-turboderp-4595-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-turboderp-4595-v2_reward/reward.tensors
Job bbchicago-test-turboderp-4595-v2-mkmlizer completed after 247.89s with status: succeeded
Stopping job with name bbchicago-test-turboderp-4595-v2-mkmlizer
Pipeline stage MKMLizer completed in 248.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-turboderp-4595-v2
Waiting for inference service bbchicago-test-turboderp-4595-v2 to be ready
Inference service bbchicago-test-turboderp-4595-v2 ready after 40.19069814682007s
Pipeline stage ISVCDeployer completed in 47.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.191800355911255s
Received healthy response to inference request in 1.2648849487304688s
Received healthy response to inference request in 1.2545037269592285s
Received healthy response to inference request in 1.2471492290496826s
Received healthy response to inference request in 1.2412707805633545s
5 requests
0 failed requests
5th percentile: 1.2424464702606202
10th percentile: 1.2436221599578858
20th percentile: 1.245973539352417
30th percentile: 1.2486201286315919
40th percentile: 1.2515619277954102
50th percentile: 1.2545037269592285
60th percentile: 1.2586562156677246
70th percentile: 1.2628087043762206
80th percentile: 1.4502680301666262
90th percentile: 1.8210341930389404
95th percentile: 2.0064172744750977
99th percentile: 2.1547237396240235
mean time: 1.4399218082427978
Pipeline stage StressChecker completed in 7.95s
bbchicago-test-turboderp_4595_v2 status is now deployed due to DeploymentManager action
bbchicago-test-turboderp_4595_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics