developer_uid: frank2030
submission_id: frank2030-hathor-stable-_5038_v1
model_name: frank2030-hathor-stable-_5038_v1
model_group: frank2030/Hathor_Stable-
status: torndown
timestamp: 2024-07-09T00:21:50+00:00
num_battles: 32226
num_wins: 16383
celo_rating: 1197.48
family_friendly_score: 0.0
submission_type: basic
model_repo: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-1k
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: frank2030-hathor-stable-_5038_v1
is_internal_developer: False
language_model: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-1k
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-08
win_ratio: 0.5083783280580897
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}
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-5038-v1-mkmlizer
Waiting for job on frank2030-hathor-stable-5038-v1-mkmlizer to finish
frank2030-hathor-stable-5038-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-5038-v1-mkmlizer: ║     _____            __           __                                ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║       /___/                                                         ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  https://mk1.ai                                                     ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  belonging to:                                                      ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  Chai Research Corp.                                                ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
frank2030-hathor-stable-5038-v1-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-5038-v1-mkmlizer: Downloaded to shared memory in 26.245s
frank2030-hathor-stable-5038-v1-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-5038-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-5038-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 114.07it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:02, 120.92it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 124.29it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 117.66it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 122.35it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 117.63it/s]
Loading 0:  31%|███▏      | 91/291 [00:00<00:02, 73.25it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 80.90it/s]
Loading 0:  40%|███▉      | 116/291 [00:01<00:01, 91.46it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 100.28it/s]
Loading 0:  48%|████▊     | 141/291 [00:01<00:01, 101.68it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 112.88it/s]
Loading 0:  58%|█████▊    | 169/291 [00:01<00:01, 112.78it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 113.71it/s]
Loading 0:  66%|██████▋   | 193/291 [00:01<00:01, 78.37it/s] 
Loading 0:  71%|███████   | 206/291 [00:02<00:00, 88.91it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 96.57it/s]
Loading 0:  80%|████████  | 233/291 [00:02<00:00, 104.52it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 108.57it/s]
Loading 0:  89%|████████▉ | 260/291 [00:02<00:00, 113.98it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 115.51it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00,  7.81it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-5038-v1-mkmlizer: quantized model in 20.041s
frank2030-hathor-stable-5038-v1-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-1k in 46.286s
frank2030-hathor-stable-5038-v1-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-5038-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-5038-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v1
frank2030-hathor-stable-5038-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v1/tokenizer_config.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v1/special_tokens_map.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v1/config.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v1/tokenizer.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v1/flywheel_model.0.safetensors
frank2030-hathor-stable-5038-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-5038-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-5038-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-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-5038-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-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-5038-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-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-5038-v1-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-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-5038-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-5038-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-5038-v1-mkmlizer: Saving duration: 0.241s
frank2030-hathor-stable-5038-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.847s
frank2030-hathor-stable-5038-v1-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-5038-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-5038-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/config.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/special_tokens_map.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/merges.txt
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/tokenizer_config.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/vocab.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/tokenizer.json
frank2030-hathor-stable-5038-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-5038-v1_reward/reward.tensors
Job frank2030-hathor-stable-5038-v1-mkmlizer completed after 81.35s with status: succeeded
Stopping job with name frank2030-hathor-stable-5038-v1-mkmlizer
Pipeline stage MKMLizer completed in 82.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-5038-v1
Waiting for inference service frank2030-hathor-stable-5038-v1 to be ready
Inference service frank2030-hathor-stable-5038-v1 ready after 40.19451975822449s
Pipeline stage ISVCDeployer completed in 46.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9305360317230225s
Received healthy response to inference request in 1.1338555812835693s
Received healthy response to inference request in 1.1258137226104736s
Received healthy response to inference request in 1.1114933490753174s
Received healthy response to inference request in 1.1115319728851318s
5 requests
0 failed requests
5th percentile: 1.1115010738372804
10th percentile: 1.1115087985992431
20th percentile: 1.1115242481231689
30th percentile: 1.1143883228302003
40th percentile: 1.120101022720337
50th percentile: 1.1258137226104736
60th percentile: 1.129030466079712
70th percentile: 1.1322472095489502
80th percentile: 1.2931916713714602
90th percentile: 1.6118638515472412
95th percentile: 1.7711999416351316
99th percentile: 1.8986688137054444
mean time: 1.2826461315155029
Pipeline stage StressChecker completed in 7.27s
frank2030-hathor-stable-_5038_v1 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_5038_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of frank2030-hathor-stable-_5038_v1
Running pipeline stage ISVCDeleter
Checking if service frank2030-hathor-stable-5038-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-5038-v1/config.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-5038-v1_reward/config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.42s
frank2030-hathor-stable-_5038_v1 status is now torndown due to DeploymentManager action