cgato-l3-thespice-8b-dpo_8377

submission_id: cgato-l3-thespice-8b-dpo_8377_v2

developer_uid: c.gato

best_of: 16

display_name: cgato-l3-thespice-8b-dpo_8377_v2

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|>{bot_name}\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>{bot_name}\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-e15.2

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_8377_v2

model_num_parameters: 8030277632.0

model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e15.2

model_size: 8B

num_battles: 231

num_wins: 131

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: 2024-06-04T02:04:26+00:00

us_pacific_date: 2024-06-03

win_ratio: 0.5670995670995671

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║     _____            __           __                                ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║       /___/                                                         ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  belonging to:                                                      ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-8377-v2-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-8377-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Downloaded to shared memory in 19.380s
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 78.80it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 92.12it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 132.74it/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-8377-v2-mkmlizer: quantized model in 23.841s
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e15.2 in 45.855s
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8377-v2
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8377-v2/config.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8377-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8377-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8377-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8377-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-8377-v2-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-8377-v2-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-8377-v2-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-8377-v2-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-8377-v2-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-8377-v2-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-8377-v2-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-8377-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Saving duration: 0.419s
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.847s
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/config.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8377-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer completed after 73.02s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-8377-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-8377-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-8377-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-8377-v2 ready after 40.24017286300659s
Pipeline stage ISVCDeployer completed in 48.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.353177070617676s
Received healthy response to inference request in 1.3230020999908447s
Received healthy response to inference request in 1.3271889686584473s
Received healthy response to inference request in 1.312772512435913s
Received healthy response to inference request in 1.3027141094207764s
5 requests
0 failed requests
5th percentile: 1.3047257900238036
10th percentile: 1.306737470626831
20th percentile: 1.3107608318328858
30th percentile: 1.3148184299468995
40th percentile: 1.318910264968872
50th percentile: 1.3230020999908447
60th percentile: 1.3246768474578858
70th percentile: 1.3263515949249267
80th percentile: 1.5323865890502932
90th percentile: 1.9427818298339845
95th percentile: 2.14797945022583
99th percentile: 2.3121375465393066
mean time: 1.5237709522247314
Pipeline stage StressChecker completed in 8.26s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-dpo_8377_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_8377_v2 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.