meseca-07062024-m1

developer_uid: nguyenzzz

submission_id: meseca-07062024-m1_v2

model_name: meseca-caspian-11_v1

model_group: meseca/07062024-m1

status: torndown

timestamp: 2024-06-15T14:55:11+00:00

num_battles: 18289

num_wins: 10315

celo_rating: 1212.29

family_friendly_score: 0.0

submission_type: basic

model_repo: meseca/07062024-m1

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: meseca-caspian-11_v1

is_internal_developer: False

language_model: meseca/07062024-m1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-15

win_ratio: 0.5640002187107004

generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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': '<|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.\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}

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 meseca-07062024-m1-v2-mkmlizer
Waiting for job on meseca-07062024-m1-v2-mkmlizer to finish
meseca-07062024-m1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-07062024-m1-v2-mkmlizer: ║     _____            __           __                                ║
meseca-07062024-m1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-07062024-m1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-07062024-m1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-07062024-m1-v2-mkmlizer: ║       /___/                                                         ║
meseca-07062024-m1-v2-mkmlizer: ║                                                                     ║
meseca-07062024-m1-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-07062024-m1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-07062024-m1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-07062024-m1-v2-mkmlizer: ║                                                                     ║
meseca-07062024-m1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-07062024-m1-v2-mkmlizer: ║  belonging to:                                                      ║
meseca-07062024-m1-v2-mkmlizer: ║                                                                     ║
meseca-07062024-m1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-07062024-m1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-07062024-m1-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-07062024-m1-v2-mkmlizer: ║                                                                     ║
meseca-07062024-m1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-07062024-m1-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.
meseca-07062024-m1-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-07062024-m1-v2-mkmlizer: Downloaded to shared memory in 46.792s
meseca-07062024-m1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-07062024-m1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-07062024-m1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 99.28it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 84.55it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 85.45it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 85.88it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 88.72it/s]
Loading 0:  21%|██▏       | 62/291 [00:00<00:02, 97.17it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:02, 102.30it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:03, 53.34it/s] 
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 64.62it/s]
Loading 0:  37%|███▋      | 107/291 [00:01<00:02, 69.66it/s]
Loading 0:  40%|████      | 117/291 [00:01<00:02, 75.38it/s]
Loading 0:  44%|████▎     | 127/291 [00:01<00:02, 79.57it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 81.53it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 81.28it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 82.42it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 82.03it/s]
Loading 0:  62%|██████▏   | 179/291 [00:02<00:01, 88.47it/s]
Loading 0:  65%|██████▍   | 189/291 [00:02<00:01, 52.23it/s]
Loading 0:  68%|██████▊   | 199/291 [00:02<00:01, 60.55it/s]
Loading 0:  71%|███████   | 207/291 [00:02<00:01, 64.12it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 73.23it/s]
Loading 0:  78%|███████▊  | 228/291 [00:03<00:00, 76.97it/s]
Loading 0:  81%|████████▏ | 237/291 [00:03<00:00, 78.99it/s]
Loading 0:  85%|████████▍ | 247/291 [00:03<00:00, 80.75it/s]
Loading 0:  88%|████████▊ | 257/291 [00:03<00:00, 85.48it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 100.93it/s]
Loading 0:  98%|█████████▊| 284/291 [00:03<00:00, 99.48it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-07062024-m1-v2-mkmlizer: quantized model in 25.735s
meseca-07062024-m1-v2-mkmlizer: Processed model meseca/07062024-m1 in 75.136s
meseca-07062024-m1-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-07062024-m1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-07062024-m1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-07062024-m1-v2
meseca-07062024-m1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-07062024-m1-v2/tokenizer_config.json
meseca-07062024-m1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-07062024-m1-v2/config.json
meseca-07062024-m1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-07062024-m1-v2/special_tokens_map.json
meseca-07062024-m1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-07062024-m1-v2/tokenizer.json
meseca-07062024-m1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-07062024-m1-v2/flywheel_model.0.safetensors
meseca-07062024-m1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-07062024-m1-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.
meseca-07062024-m1-v2-mkmlizer:   warnings.warn(
meseca-07062024-m1-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.
meseca-07062024-m1-v2-mkmlizer:   warnings.warn(
meseca-07062024-m1-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.
meseca-07062024-m1-v2-mkmlizer:   warnings.warn(
meseca-07062024-m1-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()
meseca-07062024-m1-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-07062024-m1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-07062024-m1-v2-mkmlizer: Saving duration: 0.491s
meseca-07062024-m1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 23.131s
meseca-07062024-m1-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-07062024-m1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-07062024-m1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-07062024-m1-v2_reward
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/special_tokens_map.json
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/config.json
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/tokenizer_config.json
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/merges.txt
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/tokenizer.json
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/vocab.json
meseca-07062024-m1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-07062024-m1-v2_reward/reward.tensors
Job meseca-07062024-m1-v2-mkmlizer completed after 115.12s with status: succeeded
Stopping job with name meseca-07062024-m1-v2-mkmlizer
Pipeline stage MKMLizer completed in 119.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-07062024-m1-v2
Waiting for inference service meseca-07062024-m1-v2 to be ready
Inference service meseca-07062024-m1-v2 ready after 100.50456309318542s
Pipeline stage ISVCDeployer completed in 108.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3260598182678223s
Received healthy response to inference request in 1.2898168563842773s
Received healthy response to inference request in 3.273167848587036s
Received healthy response to inference request in 1.3551669120788574s
Received healthy response to inference request in 4.522210597991943s
5 requests
0 failed requests
5th percentile: 1.3028868675231933
10th percentile: 1.3159568786621094
20th percentile: 1.3420969009399415
30th percentile: 1.5493454933166504
40th percentile: 1.9377026557922363
50th percentile: 2.3260598182678223
60th percentile: 2.7049030303955077
70th percentile: 3.083746242523193
80th percentile: 3.5229763984680176
90th percentile: 4.0225934982299805
95th percentile: 4.272402048110962
99th percentile: 4.472248888015747
mean time: 2.5532844066619873
Pipeline stage StressChecker completed in 13.37s
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
meseca-07062024-m1_v2 status is now deployed due to DeploymentManager action
meseca-07062024-m1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-07062024-m1_v2
Running pipeline stage ISVCDeleter
Checking if service meseca-07062024-m1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-07062024-m1-v2/config.json from bucket guanaco-mkml-models
Deleting key meseca-07062024-m1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-07062024-m1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-07062024-m1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-07062024-m1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-07062024-m1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-07062024-m1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-07062024-m1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-07062024-m1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-07062024-m1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-07062024-m1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-07062024-m1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.12s
meseca-07062024-m1_v2 status is now torndown due to DeploymentManager action