submission_id: meseca-05062024-v1-qlora_2149_v1
developer_uid: nguyenzzz
best_of: 8
celo_rating: 1178.86
display_name: meseca-05062024-v1-qlora_2149_v1
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this fictional never-ending roleplay with {user_name}.\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: False
language_model: meseca/05062024-v1-qlora-merged
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: meseca/05062024-v1-qlora
model_name: meseca-05062024-v1-qlora_2149_v1
model_num_parameters: 8030261248.0
model_repo: meseca/05062024-v1-qlora-merged
model_size: 8B
num_battles: 17319
num_wins: 8734
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': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-06T10:32:21+00:00
us_pacific_date: 2024-06-06
win_ratio: 0.504301634043536
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-05062024-v1-qlora-2149-v1-mkmlizer
Waiting for job on meseca-05062024-v1-qlora-2149-v1-mkmlizer to finish
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║     _____            __           __                                ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║       /___/                                                         ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v1-qlora-2149-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-05062024-v1-qlora-2149-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.
meseca-05062024-v1-qlora-2149-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Downloaded to shared memory in 34.586s
meseca-05062024-v1-qlora-2149-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-05062024-v1-qlora-2149-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 201.69it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 190.73it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 204.72it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:02, 97.07it/s] 
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 123.63it/s]
Loading 0:  45%|████▌     | 131/291 [00:00<00:01, 136.99it/s]
Loading 0:  53%|█████▎    | 154/291 [00:01<00:00, 158.75it/s]
Loading 0:  60%|██████    | 175/291 [00:01<00:00, 170.49it/s]
Loading 0:  67%|██████▋   | 195/291 [00:01<00:00, 101.78it/s]
Loading 0:  75%|███████▌  | 219/291 [00:01<00:00, 124.31it/s]
Loading 0:  82%|████████▏ | 239/291 [00:01<00:00, 136.81it/s]
Loading 0:  91%|█████████ | 264/291 [00:01<00:00, 159.80it/s]
Loading 0:  98%|█████████▊| 285/291 [00:01<00:00, 170.33it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-05062024-v1-qlora-2149-v1-mkmlizer: quantized model in 17.375s
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Processed model meseca/05062024-v1-qlora-merged in 52.953s
meseca-05062024-v1-qlora-2149-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-05062024-v1-qlora-2149-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-05062024-v1-qlora-2149-v1
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-05062024-v1-qlora-2149-v1/config.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-05062024-v1-qlora-2149-v1/special_tokens_map.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-05062024-v1-qlora-2149-v1/tokenizer_config.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-05062024-v1-qlora-2149-v1/tokenizer.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-05062024-v1-qlora-2149-v1/flywheel_model.0.safetensors
meseca-05062024-v1-qlora-2149-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-05062024-v1-qlora-2149-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.
meseca-05062024-v1-qlora-2149-v1-mkmlizer:   warnings.warn(
meseca-05062024-v1-qlora-2149-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.
meseca-05062024-v1-qlora-2149-v1-mkmlizer:   warnings.warn(
meseca-05062024-v1-qlora-2149-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.
meseca-05062024-v1-qlora-2149-v1-mkmlizer:   warnings.warn(
meseca-05062024-v1-qlora-2149-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()
meseca-05062024-v1-qlora-2149-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Saving duration: 0.253s
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.046s
meseca-05062024-v1-qlora-2149-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-05062024-v1-qlora-2149-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-05062024-v1-qlora-2149-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/tokenizer_config.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/special_tokens_map.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/config.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/merges.txt
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/vocab.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/tokenizer.json
meseca-05062024-v1-qlora-2149-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-05062024-v1-qlora-2149-v1_reward/reward.tensors
Job meseca-05062024-v1-qlora-2149-v1-mkmlizer completed after 84.6s with status: succeeded
Stopping job with name meseca-05062024-v1-qlora-2149-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-05062024-v1-qlora-2149-v1
Waiting for inference service meseca-05062024-v1-qlora-2149-v1 to be ready
Inference service meseca-05062024-v1-qlora-2149-v1 ready after 30.181134939193726s
Pipeline stage ISVCDeployer completed in 37.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0508861541748047s
Received healthy response to inference request in 1.2733924388885498s
Received healthy response to inference request in 1.257951021194458s
Received healthy response to inference request in 1.2349419593811035s
Received healthy response to inference request in 1.2293965816497803s
5 requests
0 failed requests
5th percentile: 1.2305056571960449
10th percentile: 1.2316147327423095
20th percentile: 1.233832883834839
30th percentile: 1.2395437717437745
40th percentile: 1.2487473964691163
50th percentile: 1.257951021194458
60th percentile: 1.2641275882720948
70th percentile: 1.2703041553497314
80th percentile: 1.428891181945801
90th percentile: 1.7398886680603027
95th percentile: 1.8953874111175535
99th percentile: 2.0197864055633543
mean time: 1.4093136310577392
Pipeline stage StressChecker completed in 7.81s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
meseca-05062024-v1-qlora_2149_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
meseca-05062024-v1-qlora_2149_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-05062024-v1-qlora_2149_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-05062024-v1-qlora-2149-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-05062024-v1-qlora-2149-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-qlora-2149-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-qlora-2149-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-qlora-2149-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-qlora-2149-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-qlora-2149-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.46s
meseca-05062024-v1-qlora_2149_v1 status is now torndown due to DeploymentManager action