cgato-l3-thespice-8b-dpo_3142

developer_uid: c.gato

submission_id: cgato-l3-thespice-8b-dpo_3142_v2

model_name: cgato-l3-thespice-8b-dpo_3142_v2

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

status: torndown

timestamp: 2024-05-31T11:01:53+00:00

num_battles: 5775

num_wins: 3136

celo_rating: 1223.9

family_friendly_score: 0.0

submission_type: basic

model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030277632.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: cgato-l3-thespice-8b-dpo_3142_v2

is_internal_developer: False

language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-31

win_ratio: 0.5430303030303031

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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|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}

model_eval_status: success

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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║     _____            __           __                                ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║       /___/                                                         ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  belonging to:                                                      ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ║                                                                     ║
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-3142-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-3142-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Downloaded to shared memory in 45.858s
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 72.06it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 84.79it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 123.56it/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-3142-v2-mkmlizer: quantized model in 23.131s
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 71.511s
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v2
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v2/config.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-3142-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-3142-v2-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-3142-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-3142-v2-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-3142-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-3142-v2-mkmlizer:   warnings.warn(
cgato-l3-thespice-8b-dpo-3142-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-3142-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Saving duration: 0.531s
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 23.051s
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/config.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer completed after 124.15s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-3142-v2-mkmlizer
Pipeline stage MKMLizer completed in 124.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-3142-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-3142-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service cgato-l3-thespice-8b-dpo-3142-v2 ready after 100.7225239276886s
Pipeline stage ISVCDeployer completed in 106.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.352682113647461s
Received healthy response to inference request in 1.3246972560882568s
Received healthy response to inference request in 1.3236894607543945s
Received healthy response to inference request in 1.3063769340515137s
Received healthy response to inference request in 1.3051373958587646s
5 requests
0 failed requests
5th percentile: 1.3053853034973144
10th percentile: 1.3056332111358642
20th percentile: 1.306129026412964
30th percentile: 1.3098394393920898
40th percentile: 1.3167644500732423
50th percentile: 1.3236894607543945
60th percentile: 1.3240925788879394
70th percentile: 1.3244956970214843
80th percentile: 1.530294227600098
90th percentile: 1.9414881706237794
95th percentile: 2.14708514213562
99th percentile: 2.3115627193450927
mean time: 1.522516632080078
Pipeline stage StressChecker completed in 8.28s
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_3142_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_3142_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_3142_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-3142-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-3142-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3142-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.63s
cgato-l3-thespice-8b-dpo_3142_v2 status is now torndown due to DeploymentManager action