frank2030-hathor-stable-_8570

developer_uid: frank2030

submission_id: frank2030-hathor-stable-_8570_v1

model_name: frank2030-hathor-stable-_8570_v1

model_group: frank2030/Hathor_Stable-

status: torndown

timestamp: 2024-07-09T00:22:58+00:00

num_battles: 34197

num_wins: 18821

celo_rating: 1227.81

family_friendly_score: 0.0

submission_type: basic

model_repo: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-4k

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: frank2030-hathor-stable-_8570_v1

is_internal_developer: False

language_model: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-4k

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-08

win_ratio: 0.5503699154896629

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': "{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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name frank2030-hathor-stable-8570-v1-mkmlizer
Waiting for job on frank2030-hathor-stable-8570-v1-mkmlizer to finish
frank2030-hathor-stable-8570-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-8570-v1-mkmlizer: ║     _____            __           __                                ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║       /___/                                                         ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  https://mk1.ai                                                     ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  belonging to:                                                      ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  Chai Research Corp.                                                ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
frank2030-hathor-stable-8570-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-8570-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-8570-v1-mkmlizer: Downloaded to shared memory in 29.465s
frank2030-hathor-stable-8570-v1-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-8570-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-8570-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 9/291 [00:00<00:03, 89.66it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:02, 106.65it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:02, 98.31it/s] 
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 114.44it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:02, 107.91it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:01, 115.60it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:03, 59.43it/s] 
Loading 0:  34%|███▍      | 99/291 [00:01<00:02, 69.37it/s]
Loading 0:  38%|███▊      | 111/291 [00:01<00:02, 77.02it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:02, 80.00it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 83.33it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 97.87it/s]
Loading 0:  54%|█████▍    | 158/291 [00:01<00:01, 95.50it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:01, 104.71it/s]
Loading 0:  64%|██████▎   | 185/291 [00:02<00:00, 107.99it/s]
Loading 0:  68%|██████▊   | 197/291 [00:02<00:01, 63.51it/s] 
Loading 0:  71%|███████▏  | 208/291 [00:02<00:01, 71.69it/s]
Loading 0:  75%|███████▍  | 218/291 [00:02<00:00, 77.05it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 79.70it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 80.14it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 81.03it/s]
Loading 0:  88%|████████▊ | 256/291 [00:03<00:00, 81.43it/s]
Loading 0:  91%|█████████ | 265/291 [00:03<00:00, 81.80it/s]
Loading 0:  95%|█████████▍| 275/291 [00:03<00:00, 84.90it/s]
Loading 0:  98%|█████████▊| 285/291 [00:03<00:00, 88.75it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-8570-v1-mkmlizer: quantized model in 25.138s
frank2030-hathor-stable-8570-v1-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-4k in 54.604s
frank2030-hathor-stable-8570-v1-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-8570-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-8570-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-8570-v1
frank2030-hathor-stable-8570-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-8570-v1/config.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-8570-v1/special_tokens_map.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-8570-v1/tokenizer_config.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-8570-v1/tokenizer.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-8570-v1/flywheel_model.0.safetensors
frank2030-hathor-stable-8570-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-8570-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-hathor-stable-8570-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-8570-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
frank2030-hathor-stable-8570-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-8570-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-hathor-stable-8570-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-8570-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.
frank2030-hathor-stable-8570-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-8570-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()
frank2030-hathor-stable-8570-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-8570-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-8570-v1-mkmlizer: Saving duration: 0.455s
frank2030-hathor-stable-8570-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.995s
frank2030-hathor-stable-8570-v1-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-8570-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-8570-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/config.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/special_tokens_map.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/tokenizer_config.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/vocab.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/merges.txt
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/tokenizer.json
frank2030-hathor-stable-8570-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-8570-v1_reward/reward.tensors
Job frank2030-hathor-stable-8570-v1-mkmlizer completed after 85.15s with status: succeeded
Stopping job with name frank2030-hathor-stable-8570-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-8570-v1
Waiting for inference service frank2030-hathor-stable-8570-v1 to be ready
Inference service frank2030-hathor-stable-8570-v1 ready after 40.189990520477295s
Pipeline stage ISVCDeployer completed in 46.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0414175987243652s
Received healthy response to inference request in 1.2877616882324219s
Received healthy response to inference request in 1.250678539276123s
Received healthy response to inference request in 1.2651481628417969s
Received healthy response to inference request in 1.2632136344909668s
5 requests
0 failed requests
5th percentile: 1.2531855583190918
10th percentile: 1.2556925773620606
20th percentile: 1.260706615447998
30th percentile: 1.2636005401611328
40th percentile: 1.264374351501465
50th percentile: 1.2651481628417969
60th percentile: 1.274193572998047
70th percentile: 1.283238983154297
80th percentile: 1.4384928703308106
90th percentile: 1.739955234527588
95th percentile: 1.8906864166259765
99th percentile: 2.0112713623046874
mean time: 1.4216439247131347
Pipeline stage StressChecker completed in 7.85s
frank2030-hathor-stable-_8570_v1 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_8570_v1 status is now inactive due to auto deactivation removed underperforming models
frank2030-hathor-stable-_8570_v1 status is now deployed due to admin request
frank2030-hathor-stable-_8570_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of frank2030-hathor-stable-_8570_v1
Running pipeline stage ISVCDeleter
Checking if service frank2030-hathor-stable-8570-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.97s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-8570-v1/config.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-8570-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-8570-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-8570-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-8570-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-8570-v1_reward/config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-8570-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-8570-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-8570-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-8570-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-8570-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-8570-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
frank2030-hathor-stable-_8570_v1 status is now torndown due to DeploymentManager action