submission_id: cgato-l3-thespice-8b-dpo_8432_v1
developer_uid: c.gato
best_of: 16
celo_rating: 1226.53
display_name: cgato-l3-thespice-8b-dpo_8432_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': 0.8, 'top_p': 0.9, '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: cgato/L3-TheSpice-8b-DPO-v1.3-e6.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
model_name: cgato-l3-thespice-8b-dpo_8432_v1
model_num_parameters: 8030261248.0
model_repo: cgato/L3-TheSpice-8b-DPO-v1.3-e6.2
model_size: 8B
num_battles: 5975
num_wins: 3588
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: 2024-04-27T21:51:13+00:00
us_pacific_date: 2024-04-27
win_ratio: 0.6005020920502092
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║     _____            __           __                                ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║       /___/                                                         ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  belonging to:                                                      ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Downloaded to shared memory in 35.896s
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 82.55it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 130.76it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: quantized model in 19.002s
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v1.3-e6.2 in 55.925s
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8432-v1
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8432-v1/config.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8432-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8432-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8432-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8432-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-8432-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.
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-8432-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()
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Saving duration: 0.294s
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.680s
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/config.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8432-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer completed after 85.07s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-8432-v1-mkmlizer
Pipeline stage MKMLizer completed in 91.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-8432-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-8432-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-8432-v1 ready after 40.235926151275635s
Pipeline stage ISVCDeployer completed in 48.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.228188991546631s
Received healthy response to inference request in 1.265737771987915s
Received healthy response to inference request in 1.2616279125213623s
Received healthy response to inference request in 1.2596659660339355s
Received healthy response to inference request in 1.2436156272888184s
5 requests
0 failed requests
5th percentile: 1.2468256950378418
10th percentile: 1.2500357627868652
20th percentile: 1.256455898284912
30th percentile: 1.2600583553314209
40th percentile: 1.2608431339263917
50th percentile: 1.2616279125213623
60th percentile: 1.2632718563079834
70th percentile: 1.2649158000946046
80th percentile: 1.4582280158996583
90th percentile: 1.8432085037231447
95th percentile: 2.0356987476348873
99th percentile: 2.1896909427642823
mean time: 1.4517672538757325
Pipeline stage StressChecker completed in 8.09s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.12s
%s, retrying in %s seconds...
cgato-l3-thespice-8b-dpo_8432_v1 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
cgato-l3-thespice-8b-dpo_8432_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_8432_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-8432-v1 is running
Tearing down inference service cgato-l3-thespice-8b-dpo-8432-v1
Toredown service cgato-l3-thespice-8b-dpo-8432-v1
Pipeline stage ISVCDeleter completed in 4.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-8432-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8432-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.90s
cgato-l3-thespice-8b-dpo_8432_v1 status is now torndown due to DeploymentManager action