cgato-l3-thespice-8b-dpo_5102

submission_id: cgato-l3-thespice-8b-dpo_5102_v1

developer_uid: c.gato

best_of: 16

display_name: cgato-l3-thespice-8b-dpo_5102_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': True}

generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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-e12.3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: error

model_group: cgato/L3-TheSpice-8b-DPO

model_name: cgato-l3-thespice-8b-dpo_5102_v1

model_num_parameters: 8030277632.0

model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e12.3

model_size: 8B

num_battles: 575

num_wins: 304

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: 2024-05-29T00:11:58+00:00

us_pacific_date: 2024-05-28

win_ratio: 0.528695652173913

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║     _____            __           __                                ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║       /___/                                                         ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  belonging to:                                                      ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-5102-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-5102-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Downloaded to shared memory in 37.170s
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 79.26it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 93.51it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 135.07it/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-5102-v1-mkmlizer: quantized model in 23.522s
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e12.3 in 63.321s
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v1
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v1/config.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-5102-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-5102-v1-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-5102-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-5102-v1-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-5102-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-5102-v1-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-5102-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-5102-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Saving duration: 0.412s
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.159s
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward/config.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v1_reward/tokenizer.json
Job cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer completed after 93.24s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-5102-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-5102-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-5102-v1 to be ready
Tearing down inference service cgato-l3-thespice-8b-dpo-5102-v1
%s, retrying in %s seconds...
Creating inference service cgato-l3-thespice-8b-dpo-5102-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-5102-v1 to be ready
Tearing down inference service cgato-l3-thespice-8b-dpo-5102-v1
%s, retrying in %s seconds...
Creating inference service cgato-l3-thespice-8b-dpo-5102-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-5102-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-5102-v1 ready after 40.26660394668579s
Pipeline stage ISVCDeployer completed in 79.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.025686740875244s
Received healthy response to inference request in 1.481868028640747s
Received healthy response to inference request in 1.2328989505767822s
Received healthy response to inference request in 1.2426776885986328s
Received healthy response to inference request in 1.3097574710845947s
5 requests
0 failed requests
5th percentile: 1.2348546981811523
10th percentile: 1.2368104457855225
20th percentile: 1.2407219409942627
30th percentile: 1.256093645095825
40th percentile: 1.28292555809021
50th percentile: 1.3097574710845947
60th percentile: 1.3786016941070556
70th percentile: 1.4474459171295166
80th percentile: 1.5906317710876465
90th percentile: 1.8081592559814454
95th percentile: 1.9169229984283447
99th percentile: 2.003933992385864
mean time: 1.4585777759552
Pipeline stage StressChecker completed in 8.06s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_5102_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_5102_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.