submission_id: bbchicago-test-120k-pref-dpo_v5
developer_uid: Bbbrun0
best_of: 16
celo_rating: 1216.04
display_name: bbchicago-test_120k_pref_dpo_v5
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: BBChicago/test_120k_pref_dpo
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: BBChicago/test_120k_pref
model_name: bbchicago-test_120k_pref_dpo_v5
model_num_parameters: 8030261248.0
model_repo: BBChicago/test_120k_pref_dpo
model_size: 8B
num_battles: 17860
num_wins: 9633
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: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-18T01:43:51+00:00
us_pacific_date: 2024-07-17
win_ratio: 0.5393617021276595
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-120k-pref-dpo-v5-mkmlizer
Waiting for job on bbchicago-test-120k-pref-dpo-v5-mkmlizer to finish
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║       /___/                                                         ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║                                                                     ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  Version: 0.9.5.post3                                               ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║                                                                     ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║                                                                     ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ║                                                                     ║
bbchicago-test-120k-pref-dpo-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Downloaded to shared memory in 22.070s
bbchicago-test-120k-pref-dpo-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0_pgfgyg, device:0
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-120k-pref-dpo-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 123.93it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 149.74it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:01, 144.37it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:01, 123.16it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 127.30it/s]
Loading 0:  31%|███       | 90/291 [00:00<00:02, 68.37it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 78.56it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:01, 95.63it/s]
Loading 0:  46%|████▋     | 135/291 [00:01<00:01, 107.00it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 112.47it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 126.20it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 130.16it/s]
Loading 0:  67%|██████▋   | 196/291 [00:01<00:01, 79.79it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 92.53it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 106.67it/s]
Loading 0:  84%|████████▎ | 243/291 [00:02<00:00, 115.31it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 116.00it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 128.13it/s]
Loading 0:  99%|█████████▉| 289/291 [00:08<00:00,  8.49it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-120k-pref-dpo-v5-mkmlizer: quantized model in 24.459s
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Processed model BBChicago/test_120k_pref_dpo in 46.529s
bbchicago-test-120k-pref-dpo-v5-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-120k-pref-dpo-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v5
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v5/config.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v5/special_tokens_map.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v5/tokenizer_config.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v5/tokenizer.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v5/flywheel_model.0.safetensors
bbchicago-test-120k-pref-dpo-v5-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-test-120k-pref-dpo-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-120k-pref-dpo-v5-mkmlizer:   warnings.warn(
bbchicago-test-120k-pref-dpo-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-120k-pref-dpo-v5-mkmlizer:   warnings.warn(
bbchicago-test-120k-pref-dpo-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-120k-pref-dpo-v5-mkmlizer:   warnings.warn(
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Saving duration: 1.718s
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.387s
bbchicago-test-120k-pref-dpo-v5-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-120k-pref-dpo-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-120k-pref-dpo-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/special_tokens_map.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/config.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/tokenizer_config.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/merges.txt
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/vocab.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/tokenizer.json
bbchicago-test-120k-pref-dpo-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-120k-pref-dpo-v5_reward/reward.tensors
Job bbchicago-test-120k-pref-dpo-v5-mkmlizer completed after 95.4s with status: succeeded
Stopping job with name bbchicago-test-120k-pref-dpo-v5-mkmlizer
Pipeline stage MKMLizer completed in 96.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-120k-pref-dpo-v5
Waiting for inference service bbchicago-test-120k-pref-dpo-v5 to be ready
Inference service bbchicago-test-120k-pref-dpo-v5 ready after 161.42144989967346s
Pipeline stage ISVCDeployer completed in 162.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.367222309112549s
Received healthy response to inference request in 1.4686906337738037s
Received healthy response to inference request in 1.444835901260376s
Received healthy response to inference request in 1.4416186809539795s
Received healthy response to inference request in 1.4588868618011475s
5 requests
0 failed requests
5th percentile: 1.4422621250152587
10th percentile: 1.442905569076538
20th percentile: 1.4441924571990967
30th percentile: 1.4476460933685302
40th percentile: 1.453266477584839
50th percentile: 1.4588868618011475
60th percentile: 1.46280837059021
70th percentile: 1.4667298793792725
80th percentile: 1.648396968841553
90th percentile: 2.007809638977051
95th percentile: 2.1875159740448
99th percentile: 2.331281042098999
mean time: 1.636250877380371
Pipeline stage StressChecker completed in 8.83s
bbchicago-test-120k-pref-dpo_v5 status is now deployed due to DeploymentManager action
bbchicago-test-120k-pref-dpo_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-120k-pref-dpo_v5
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-120k-pref-dpo-v5 is running
Tearing down inference service bbchicago-test-120k-pref-dpo-v5
Service bbchicago-test-120k-pref-dpo-v5 has been torndown
Pipeline stage ISVCDeleter completed in 4.55s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-120k-pref-dpo-v5/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.57s
bbchicago-test-120k-pref-dpo_v5 status is now torndown due to DeploymentManager action