submission_id: bbchicago-test-120k-pref-dpo_v3
developer_uid: Bbbrun0
best_of: 8
celo_rating: 1212.47
display_name: bbchicago-test_120k_pref_dpo_v3
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': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: False
language_model: BBChicago/test_120k_pref_dpo
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: BBChicago/test_120k_pref
model_name: bbchicago-test_120k_pref_dpo_v3
model_num_parameters: 8030261248.0
model_repo: BBChicago/test_120k_pref_dpo
model_size: 8B
num_battles: 17628
num_wins: 9431
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: 2024-07-18T01:42:20+00:00
us_pacific_date: 2024-07-17
win_ratio: 0.5350011345586567
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-120k-pref-dpo-v3-mkmlizer
Waiting for job on bbchicago-test-120k-pref-dpo-v3-mkmlizer to finish
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ _____ __ __ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ /___/ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ Version: 0.9.5.post3 ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ belonging to: ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ║ ║
bbchicago-test-120k-pref-dpo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-120k-pref-dpo-v3-mkmlizer: Downloaded to shared memory in 21.756s
bbchicago-test-120k-pref-dpo-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphish5gfa, device:0
bbchicago-test-120k-pref-dpo-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-120k-pref-dpo-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 127.26it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 143.32it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 149.67it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 152.42it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 78.89it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 82.85it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 99.77it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 113.31it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 121.15it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 121.87it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 139.59it/s] Loading 0: 67%|██████▋ | 194/291 [00:01<00:01, 79.79it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 95.40it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 109.21it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 121.50it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 131.52it/s] Loading 0: 96%|█████████▌| 280/291 [00:02<00:00, 137.60it/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-v3-mkmlizer: quantized model in 24.203s
bbchicago-test-120k-pref-dpo-v3-mkmlizer: Processed model BBChicago/test_120k_pref_dpo in 45.959s
bbchicago-test-120k-pref-dpo-v3-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-120k-pref-dpo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-120k-pref-dpo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v3
bbchicago-test-120k-pref-dpo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v3/special_tokens_map.json
bbchicago-test-120k-pref-dpo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v3/config.json
bbchicago-test-120k-pref-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v3/tokenizer_config.json
bbchicago-test-120k-pref-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v3/tokenizer.json
bbchicago-test-120k-pref-dpo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-120k-pref-dpo-v3/flywheel_model.0.safetensors
bbchicago-test-120k-pref-dpo-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-test-120k-pref-dpo-v3-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-v3-mkmlizer: warnings.warn(
bbchicago-test-120k-pref-dpo-v3-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-v3-mkmlizer: warnings.warn(
bbchicago-test-120k-pref-dpo-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Job bbchicago-test-120k-pref-dpo-v3-mkmlizer completed after 104.89s with status: succeeded
Stopping job with name bbchicago-test-120k-pref-dpo-v3-mkmlizer
Pipeline stage MKMLizer completed in 106.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-120k-pref-dpo-v3
Waiting for inference service bbchicago-test-120k-pref-dpo-v3 to be ready
Inference service bbchicago-test-120k-pref-dpo-v3 ready after 91.28171682357788s
Pipeline stage ISVCDeployer completed in 93.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1643288135528564s
Received healthy response to inference request in 1.2750225067138672s
Received healthy response to inference request in 1.2841894626617432s
Received healthy response to inference request in 1.2559394836425781s
Received healthy response to inference request in 1.245375156402588s
5 requests
0 failed requests
5th percentile: 1.247488021850586
10th percentile: 1.249600887298584
20th percentile: 1.25382661819458
30th percentile: 1.259756088256836
40th percentile: 1.2673892974853516
50th percentile: 1.2750225067138672
60th percentile: 1.2786892890930175
70th percentile: 1.282356071472168
80th percentile: 1.460217332839966
90th percentile: 1.8122730731964112
95th percentile: 1.9883009433746337
99th percentile: 2.1291232395172117
mean time: 1.4449710845947266
Pipeline stage StressChecker completed in 7.93s
bbchicago-test-120k-pref-dpo_v3 status is now deployed due to DeploymentManager action
bbchicago-test-120k-pref-dpo_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-120k-pref-dpo_v3
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-120k-pref-dpo-v3 is running
Tearing down inference service bbchicago-test-120k-pref-dpo-v3
Service bbchicago-test-120k-pref-dpo-v3 has been torndown
Pipeline stage ISVCDeleter completed in 5.55s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-120k-pref-dpo-v3/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-120k-pref-dpo-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-120k-pref-dpo-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.26s
bbchicago-test-120k-pref-dpo_v3 status is now torndown due to DeploymentManager action