submission_id: cgato-l3-thespice-8b-dpo_6378_v4
developer_uid: c.gato
best_of: 16
display_name: cgato-l3-thespice-8b-dpo_6378_v4
family_friendly_score: 0.0
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '***\n{prompt}\n***<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e14.3
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_6378_v4
model_num_parameters: 8030277632.0
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e14.3
model_size: 8B
num_battles: 394
num_wins: 211
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': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: rejected
submission_type: basic
timestamp: 2024-06-02T11:38:49+00:00
us_pacific_date: 2024-06-02
win_ratio: 0.5355329949238579
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer to finish
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║     _____            __           __                                ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║       /___/                                                         ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  belonging to:                                                      ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-6378-v4-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-6378-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Downloaded to shared memory in 43.137s
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 70.33it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 82.43it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 119.03it/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-6378-v4-mkmlizer: quantized model in 23.725s
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e14.3 in 69.278s
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v4
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v4/config.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v4/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v4/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v4/tokenizer.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v4/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-6378-v4-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-6378-v4-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-6378-v4-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-6378-v4-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-6378-v4-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-6378-v4-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-6378-v4-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-6378-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Saving duration: 0.382s
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.371s
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/config.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/merges.txt
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/vocab.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v4_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer completed after 103.76s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-6378-v4-mkmlizer
Pipeline stage MKMLizer completed in 112.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-6378-v4
Waiting for inference service cgato-l3-thespice-8b-dpo-6378-v4 to be ready
Inference service cgato-l3-thespice-8b-dpo-6378-v4 ready after 60.34111928939819s
Pipeline stage ISVCDeployer completed in 67.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2573325634002686s
Received healthy response to inference request in 1.338780164718628s
Received healthy response to inference request in 1.321354866027832s
Received healthy response to inference request in 1.336280107498169s
Received healthy response to inference request in 1.3076353073120117s
5 requests
0 failed requests
5th percentile: 1.3103792190551757
10th percentile: 1.3131231307983398
20th percentile: 1.318610954284668
30th percentile: 1.3243399143218995
40th percentile: 1.330310010910034
50th percentile: 1.336280107498169
60th percentile: 1.3372801303863526
70th percentile: 1.338280153274536
80th percentile: 1.5224906444549562
90th percentile: 1.8899116039276125
95th percentile: 2.07362208366394
99th percentile: 2.220590467453003
mean time: 1.5122766017913818
Pipeline stage StressChecker completed in 8.16s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_6378_v4 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_6378_v4 status is now rejected due to its M-Eval score being less than the acceptable minimum 6.5 to serve to users. Please consider iterating on your model's ability to adhere to prompts to improve this score.