bbchicago-test-turboderp_5936

submission_id: bbchicago-test-turboderp_5936_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1173.04

display_name: bbchicago-test-turboderp_5936_v1

family_friendly_score: 0.0

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}

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}

is_internal_developer: False

language_model: BBChicago/test_turboderp_DPO_L3-8B-ins-based_e3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: BBChicago/test_turboderp

model_name: bbchicago-test-turboderp_5936_v1

model_num_parameters: 8030261248.0

model_repo: BBChicago/test_turboderp_DPO_L3-8B-ins-based_e3

model_size: 8B

num_battles: 14926

num_wins: 7386

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-03T06:41:07+00:00

us_pacific_date: 2024-07-02

win_ratio: 0.4948412166688999

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-test-turboderp-5936-v1-mkmlizer
Waiting for job on bbchicago-test-turboderp-5936-v1-mkmlizer to finish
bbchicago-test-turboderp-5936-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-turboderp-5936-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║                                                                     ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║                                                                     ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║                                                                     ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ║                                                                     ║
bbchicago-test-turboderp-5936-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-turboderp-5936-v1-mkmlizer: Downloaded to shared memory in 30.442s
bbchicago-test-turboderp-5936-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-turboderp-5936-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-turboderp-5936-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 114.57it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 125.88it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 121.70it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 126.81it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 123.42it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 126.43it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 67.95it/s] 
Loading 0:  37%|███▋      | 107/291 [00:01<00:02, 79.59it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 89.76it/s]
Loading 0:  46%|████▋     | 135/291 [00:01<00:01, 100.55it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 105.39it/s]
Loading 0:  56%|█████▌    | 163/291 [00:01<00:01, 116.39it/s]
Loading 0:  60%|██████    | 176/291 [00:01<00:00, 119.61it/s]
Loading 0:  65%|██████▍   | 189/291 [00:02<00:01, 73.17it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 82.42it/s]
Loading 0:  74%|███████▍  | 216/291 [00:02<00:00, 93.82it/s]
Loading 0:  79%|███████▊  | 229/291 [00:02<00:00, 99.65it/s]
Loading 0:  83%|████████▎ | 242/291 [00:02<00:00, 106.59it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 110.23it/s]
Loading 0:  93%|█████████▎| 270/291 [00:02<00:00, 116.47it/s]
Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 116.12it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-turboderp-5936-v1-mkmlizer: quantized model in 23.833s
bbchicago-test-turboderp-5936-v1-mkmlizer: Processed model BBChicago/test_turboderp_DPO_L3-8B-ins-based_e3 in 54.276s
bbchicago-test-turboderp-5936-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-turboderp-5936-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-turboderp-5936-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-turboderp-5936-v1
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-turboderp-5936-v1/config.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-turboderp-5936-v1/special_tokens_map.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-turboderp-5936-v1/tokenizer_config.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-turboderp-5936-v1/tokenizer.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-turboderp-5936-v1/flywheel_model.0.safetensors
bbchicago-test-turboderp-5936-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-turboderp-5936-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-5936-v1-mkmlizer:   warnings.warn(
bbchicago-test-turboderp-5936-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-5936-v1-mkmlizer:   warnings.warn(
bbchicago-test-turboderp-5936-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-5936-v1-mkmlizer:   warnings.warn(
bbchicago-test-turboderp-5936-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-5936-v1-mkmlizer:   warnings.warn(
bbchicago-test-turboderp-5936-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-5936-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-turboderp-5936-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-turboderp-5936-v1-mkmlizer: Saving duration: 0.408s
bbchicago-test-turboderp-5936-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.757s
bbchicago-test-turboderp-5936-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-turboderp-5936-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-turboderp-5936-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/config.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/merges.txt
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/special_tokens_map.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/tokenizer_config.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/vocab.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/tokenizer.json
bbchicago-test-turboderp-5936-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-turboderp-5936-v1_reward/reward.tensors
Job bbchicago-test-turboderp-5936-v1-mkmlizer completed after 83.78s with status: succeeded
Stopping job with name bbchicago-test-turboderp-5936-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-turboderp-5936-v1
Waiting for inference service bbchicago-test-turboderp-5936-v1 to be ready
Failed to get response for submission trace2333-duduk-llama2-v0_v2: ('http://trace2333-duduk-llama2-v0-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60786->127.0.0.1:8080: read: connection reset by peer\n')
Inference service bbchicago-test-turboderp-5936-v1 ready after 251.03969836235046s
Pipeline stage ISVCDeployer completed in 258.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2281336784362793s
Received healthy response to inference request in 1.278418779373169s
Received healthy response to inference request in 1.2600131034851074s
Received healthy response to inference request in 1.2367029190063477s
Received healthy response to inference request in 1.235375165939331s
5 requests
0 failed requests
5th percentile: 1.2356407165527343
10th percentile: 1.2359062671661376
20th percentile: 1.2364373683929444
30th percentile: 1.2413649559020996
40th percentile: 1.2506890296936035
50th percentile: 1.2600131034851074
60th percentile: 1.267375373840332
70th percentile: 1.2747376441955567
80th percentile: 1.4683617591857911
90th percentile: 1.8482477188110353
95th percentile: 2.038190698623657
99th percentile: 2.1901450824737547
mean time: 1.447728729248047
Pipeline stage StressChecker completed in 7.94s
bbchicago-test-turboderp_5936_v1 status is now deployed due to DeploymentManager action
bbchicago-test-turboderp_5936_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-turboderp_5936_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-turboderp-5936-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-turboderp-5936-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-turboderp-5936-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-turboderp-5936-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-turboderp-5936-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-turboderp-5936-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-turboderp-5936-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-turboderp-5936-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-turboderp-5936-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-turboderp-5936-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-turboderp-5936-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-turboderp-5936-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-turboderp-5936-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.59s
bbchicago-test-turboderp_5936_v1 status is now torndown due to DeploymentManager action