submission_id: bbchicago-test-turboderp_4964_v1
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/test_turboderp_DPO_L3-8B-ins-based_e2.5
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: 2024-07-03T06:40:42+00:00
model_name: bbchicago-test-turboderp_4964_v1
model_group: BBChicago/test_turboderp
num_battles: 15053
num_wins: 7453
celo_rating: 1173.53
propriety_score: 0.717291983940191
propriety_total_count: 7223.0
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_4964_v1
ineligible_reason: None
language_model: BBChicago/test_turboderp_DPO_L3-8B-ins-based_e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.49511725237494186
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-turboderp-4964-v1-mkmlizer
Waiting for job on bbchicago-test-turboderp-4964-v1-mkmlizer to finish
bbchicago-test-turboderp-4964-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ /___/ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ belonging to: ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ║ ║
bbchicago-test-turboderp-4964-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-turboderp-4964-v1-mkmlizer: Downloaded to shared memory in 52.932s
bbchicago-test-turboderp-4964-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-turboderp-4964-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-turboderp-4964-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 117.68it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 129.11it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 125.20it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 128.68it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 126.68it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 130.77it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:03, 55.05it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 71.53it/s] Loading 0: 42%|████▏ | 123/291 [00:01<00:02, 79.70it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 94.11it/s] Loading 0: 52%|█████▏ | 151/291 [00:01<00:01, 99.84it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 109.18it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 116.54it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 71.09it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:01, 83.38it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 91.60it/s] Loading 0: 80%|████████ | 234/291 [00:02<00:00, 102.27it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 106.75it/s] Loading 0: 90%|█████████ | 262/291 [00:02<00:00, 117.26it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 113.34it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 7.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-turboderp-4964-v1-mkmlizer: quantized model in 23.541s
bbchicago-test-turboderp-4964-v1-mkmlizer: Processed model BBChicago/test_turboderp_DPO_L3-8B-ins-based_e2.5 in 76.473s
bbchicago-test-turboderp-4964-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-turboderp-4964-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-turboderp-4964-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-turboderp-4964-v1
bbchicago-test-turboderp-4964-v1-mkmlizer: DEBUG retryable error: RequestError: send request failed
bbchicago-test-turboderp-4964-v1-mkmlizer: caused by: dial tcp 216.153.53.63:443: i/o timeout
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4964-v1/special_tokens_map.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4964-v1/config.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4964-v1/tokenizer.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-turboderp-4964-v1/tokenizer_config.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-turboderp-4964-v1/flywheel_model.0.safetensors
bbchicago-test-turboderp-4964-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-turboderp-4964-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.
bbchicago-test-turboderp-4964-v1-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4964-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`.
bbchicago-test-turboderp-4964-v1-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4964-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.
bbchicago-test-turboderp-4964-v1-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4964-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.
bbchicago-test-turboderp-4964-v1-mkmlizer: warnings.warn(
bbchicago-test-turboderp-4964-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()
bbchicago-test-turboderp-4964-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-test-turboderp-4964-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-turboderp-4964-v1-mkmlizer: Saving duration: 0.594s
bbchicago-test-turboderp-4964-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.828s
bbchicago-test-turboderp-4964-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-turboderp-4964-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-turboderp-4964-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/tokenizer_config.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/special_tokens_map.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/config.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/merges.txt
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/vocab.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/tokenizer.json
bbchicago-test-turboderp-4964-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-turboderp-4964-v1_reward/reward.tensors
Job bbchicago-test-turboderp-4964-v1-mkmlizer completed after 209.24s with status: succeeded
Stopping job with name bbchicago-test-turboderp-4964-v1-mkmlizer
Pipeline stage MKMLizer completed in 210.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-turboderp-4964-v1
Waiting for inference service bbchicago-test-turboderp-4964-v1 to be ready
Inference service bbchicago-test-turboderp-4964-v1 ready after 40.180577516555786s
Pipeline stage ISVCDeployer completed in 47.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.068387508392334s
Received healthy response to inference request in 1.273043155670166s
Received healthy response to inference request in 1.2606263160705566s
Received healthy response to inference request in 1.2465448379516602s
Received healthy response to inference request in 1.2512426376342773s
5 requests
0 failed requests
5th percentile: 1.2474843978881835
10th percentile: 1.248423957824707
20th percentile: 1.250303077697754
30th percentile: 1.2531193733215331
40th percentile: 1.2568728446960449
50th percentile: 1.2606263160705566
60th percentile: 1.2655930519104004
70th percentile: 1.2705597877502441
80th percentile: 1.4321120262145997
90th percentile: 1.750249767303467
95th percentile: 1.9093186378479003
99th percentile: 2.036573734283447
mean time: 1.4199688911437989
Pipeline stage StressChecker completed in 7.91s
bbchicago-test-turboderp_4964_v1 status is now deployed due to DeploymentManager action
bbchicago-test-turboderp_4964_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics