developer_uid: Gryphe
submission_id: gryphe-tiamat-8b-1-2-lla_6673_v2
model_name: Gryphe-Tiamat-L3-8B
model_group: Gryphe/Tiamat-8b-1.2-Lla
status: torndown
timestamp: 2024-05-08T13:14:27+00:00
num_battles: 32295
num_wins: 15040
celo_rating: 1143.59
family_friendly_score: 0.0
submission_type: basic
model_repo: Gryphe/Tiamat-8b-1.2-Llama-3-DPO
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030523392.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: Gryphe-Tiamat-L3-8B
is_internal_developer: False
language_model: Gryphe/Tiamat-8b-1.2-Llama-3-DPO
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-08
win_ratio: 0.46570676575321257
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer
Waiting for job on gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer to finish
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║     _____            __           __                                ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║       /___/                                                         ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║                                                                     ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║                                                                     ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  belonging to:                                                      ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║                                                                     ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  Chai Research Corp.                                                ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ║                                                                     ║
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
gryphe-tiamat-8b-1-2-lla-6673-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.
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Downloaded to shared memory in 17.468s
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: quantizing model to /dev/shm/model_cache
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  43%|████▎     | 125/291 [00:01<00:01, 124.69it/s]
Loading 0:  90%|█████████ | 262/291 [00:02<00:00, 131.88it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.25it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: quantized model in 17.957s
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Processed model Gryphe/Tiamat-8b-1.2-Llama-3-DPO in 36.616s
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: creating bucket guanaco-mkml-models
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/gryphe-tiamat-8b-1-2-lla-6673-v2
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/gryphe-tiamat-8b-1-2-lla-6673-v2/config.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/gryphe-tiamat-8b-1-2-lla-6673-v2/special_tokens_map.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/gryphe-tiamat-8b-1-2-lla-6673-v2/tokenizer_config.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/gryphe-tiamat-8b-1-2-lla-6673-v2/tokenizer.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/gryphe-tiamat-8b-1-2-lla-6673-v2/flywheel_model.0.safetensors
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
gryphe-tiamat-8b-1-2-lla-6673-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.
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer:   warnings.warn(
gryphe-tiamat-8b-1-2-lla-6673-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.
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer:   warnings.warn(
gryphe-tiamat-8b-1-2-lla-6673-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.
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer:   warnings.warn(
gryphe-tiamat-8b-1-2-lla-6673-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()
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Saving duration: 0.260s
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.955s
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: creating bucket guanaco-reward-models
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/tokenizer_config.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/config.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/merges.txt
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/special_tokens_map.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/vocab.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/tokenizer.json
gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/gryphe-tiamat-8b-1-2-lla-6673-v2_reward/reward.tensors
Job gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer completed after 64.45s with status: succeeded
Stopping job with name gryphe-tiamat-8b-1-2-lla-6673-v2-mkmlizer
Pipeline stage MKMLizer completed in 68.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service gryphe-tiamat-8b-1-2-lla-6673-v2
Waiting for inference service gryphe-tiamat-8b-1-2-lla-6673-v2 to be ready
Inference service gryphe-tiamat-8b-1-2-lla-6673-v2 ready after 40.53693437576294s
Pipeline stage ISVCDeployer completed in 47.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.060288906097412s
Received healthy response to inference request in 1.1705901622772217s
Received healthy response to inference request in 1.1934525966644287s
Received healthy response to inference request in 1.170745849609375s
Received healthy response to inference request in 1.1808347702026367s
5 requests
0 failed requests
5th percentile: 1.1706212997436523
10th percentile: 1.170652437210083
20th percentile: 1.1707147121429444
30th percentile: 1.1727636337280274
40th percentile: 1.176799201965332
50th percentile: 1.1808347702026367
60th percentile: 1.1858819007873536
70th percentile: 1.1909290313720704
80th percentile: 1.3668198585510256
90th percentile: 1.7135543823242188
95th percentile: 1.8869216442108152
99th percentile: 2.0256154537200928
mean time: 1.3551824569702149
Pipeline stage StressChecker completed in 7.40s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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 0.06s
gryphe-tiamat-8b-1-2-lla_6673_v2 status is now deployed due to DeploymentManager action
gryphe-tiamat-8b-1-2-lla_6673_v2 status is now inactive due to auto deactivation removed underperforming models
Pipeline stage ISVCDeleter completed in 5.01s
admin requested tearing down of gryphe-tiamat-8b-1-2-lla_6673_v2
Running pipeline stage MKMLModelDeleter
Running pipeline stage ISVCDeleter
Cleaning model data from S3
Checking if service gryphe-tiamat-8b-1-2-lla-6673-v2 is running
Cleaning model data from model cache
Deleting key grimjim-llama-3-experime-4405-v1/config.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v48/added_tokens.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-experime-4405-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v48/config.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v48/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-experime-4405-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-experime-4405-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-experime-4405-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key gryphe-mythomax-l2-13b-v48/special_tokens_map.json from bucket guanaco-mkml-models
Tearing down inference service gryphe-tiamat-8b-1-2-lla-6673-v2
Deleting key grimjim-llama-3-experime-4405-v1_reward/config.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v48/tokenizer.json from bucket guanaco-mkml-models
Toredown service gryphe-tiamat-8b-1-2-lla-6673-v2
Deleting key grimjim-llama-3-experime-4405-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v48/tokenizer.model from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-experime-4405-v1_reward/reward.tensors from bucket guanaco-reward-models
Pipeline stage ISVCDeleter completed in 4.34s
Deleting key gryphe-mythomax-l2-13b-v48/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-experime-4405-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Running pipeline stage MKMLModelDeleter
Cleaning model data from model cache
Deleting key grimjim-llama-3-experime-4405-v1_reward/tokenizer.json from bucket guanaco-reward-models
Cleaning model data from S3
Deleting key grimjim-llama-3-experime-4405-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v48_reward/config.json from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key grimjim-llama-3-experime-4405-v1_reward/vocab.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v48_reward/merges.txt from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2/config.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v48_reward/reward.tensors from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.49s
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v48_reward/special_tokens_map.json from bucket guanaco-reward-models
grimjim-llama-3-experime_4405_v1 status is now torndown due to DeploymentManager action
Deleting key gryphe-mythomax-l2-13b-v48_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v48_reward/vocab.json from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 7.26s
Cleaning model data from model cache
gryphe-mythomax-l2-13b_v48 status is now torndown due to DeploymentManager action
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key gryphe-tiamat-8b-1-2-lla-6673-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.70s
gryphe-tiamat-8b-1-2-lla_6673_v2 status is now torndown due to DeploymentManager action