submission_id: frank2030-hathor-stable-_6120_v1
developer_uid: frank2030
best_of: 4
celo_rating: 1208.55
display_name: frank2030-hathor-stable-_6120_v1
family_friendly_score: 0.0
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}
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': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-2k
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: frank2030/Hathor_Stable-
model_name: frank2030-hathor-stable-_6120_v1
model_num_parameters: 8030261248.0
model_repo: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-2k
model_size: 8B
num_battles: 29090
num_wins: 15272
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: 2024-07-09T00:22:18+00:00
us_pacific_date: 2024-07-08
win_ratio: 0.5249914059814369
Resubmit model
Running pipeline stage MKMLizer
Starting job with name frank2030-hathor-stable-6120-v1-mkmlizer
Waiting for job on frank2030-hathor-stable-6120-v1-mkmlizer to finish
Stopping job with name frank2030-hathor-stable-6120-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name frank2030-hathor-stable-6120-v1-mkmlizer
Waiting for job on frank2030-hathor-stable-6120-v1-mkmlizer to finish
frank2030-hathor-stable-6120-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-6120-v1-mkmlizer: ║     _____            __           __                                ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║       /___/                                                         ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  https://mk1.ai                                                     ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  belonging to:                                                      ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  Chai Research Corp.                                                ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
frank2030-hathor-stable-6120-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-6120-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-6120-v1-mkmlizer: Downloaded to shared memory in 32.671s
frank2030-hathor-stable-6120-v1-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-6120-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-6120-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 109.51it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 122.67it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 118.87it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 119.23it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 122.69it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 119.80it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:03, 55.60it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 65.31it/s]
Loading 0:  40%|███▉      | 115/291 [00:01<00:02, 75.62it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 88.46it/s]
Loading 0:  48%|████▊     | 141/291 [00:01<00:01, 93.50it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 105.35it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:01, 103.41it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:01, 108.50it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 57.74it/s] 
Loading 0:  71%|███████   | 206/291 [00:02<00:01, 69.32it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 80.60it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 83.68it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 99.40it/s]
Loading 0:  89%|████████▊ | 258/291 [00:02<00:00, 101.54it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 111.34it/s]
Loading 0:  98%|█████████▊| 286/291 [00:03<00:00, 113.33it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-6120-v1-mkmlizer: quantized model in 29.455s
frank2030-hathor-stable-6120-v1-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-2k in 62.126s
frank2030-hathor-stable-6120-v1-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-6120-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-6120-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-6120-v1
frank2030-hathor-stable-6120-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-6120-v1/tokenizer_config.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-6120-v1/config.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-6120-v1/special_tokens_map.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-6120-v1/tokenizer.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-6120-v1/flywheel_model.0.safetensors
frank2030-hathor-stable-6120-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-6120-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-6120-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-6120-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-6120-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-6120-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-6120-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-6120-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-6120-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-6120-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-6120-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-6120-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-6120-v1-mkmlizer: Saving duration: 0.509s
frank2030-hathor-stable-6120-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.924s
frank2030-hathor-stable-6120-v1-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-6120-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-6120-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/config.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/special_tokens_map.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/merges.txt
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/tokenizer_config.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/vocab.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/tokenizer.json
frank2030-hathor-stable-6120-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-6120-v1_reward/reward.tensors
Job frank2030-hathor-stable-6120-v1-mkmlizer completed after 97.72s with status: succeeded
Stopping job with name frank2030-hathor-stable-6120-v1-mkmlizer
Pipeline stage MKMLizer completed in 100.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-6120-v1
Waiting for inference service frank2030-hathor-stable-6120-v1 to be ready
Inference service frank2030-hathor-stable-6120-v1 ready after 40.22138738632202s
Pipeline stage ISVCDeployer completed in 47.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.920332670211792s
Received healthy response to inference request in 1.1275458335876465s
Received healthy response to inference request in 1.124171257019043s
Received healthy response to inference request in 1.2149672508239746s
Received healthy response to inference request in 1.1202635765075684s
5 requests
0 failed requests
5th percentile: 1.1210451126098633
10th percentile: 1.1218266487121582
20th percentile: 1.123389720916748
30th percentile: 1.1248461723327636
40th percentile: 1.1261960029602052
50th percentile: 1.1275458335876465
60th percentile: 1.1625144004821777
70th percentile: 1.197482967376709
80th percentile: 1.3560403347015382
90th percentile: 1.638186502456665
95th percentile: 1.7792595863342284
99th percentile: 1.8921180534362794
mean time: 1.3014561176300048
Pipeline stage StressChecker completed in 7.26s
frank2030-hathor-stable-_6120_v1 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_6120_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of frank2030-hathor-stable-_6120_v1
Running pipeline stage ISVCDeleter
Checking if service frank2030-hathor-stable-6120-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-6120-v1/config.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-6120-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-6120-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-6120-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-6120-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-6120-v1_reward/config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-6120-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-6120-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-6120-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-6120-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-6120-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-6120-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.27s
frank2030-hathor-stable-_6120_v1 status is now torndown due to DeploymentManager action