developer_uid: frank2030
submission_id: frank2030-hathor-stable-_5038_v4
model_name: frank2030-hathor-stable-_5038_v4
model_group: frank2030/Hathor_Stable-
status: torndown
timestamp: 2024-07-09T00:24:40+00:00
num_battles: 29134
num_wins: 15797
celo_rating: 1220.09
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: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: frank2030-hathor-stable-_5038_v4
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: 0.5422187135305828
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-5038-v4-mkmlizer
Waiting for job on frank2030-hathor-stable-5038-v4-mkmlizer to finish
frank2030-hathor-stable-5038-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-5038-v4-mkmlizer: ║     _____            __           __                                ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║       /___/                                                         ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  https://mk1.ai                                                     ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  belonging to:                                                      ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  Chai Research Corp.                                                ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
frank2030-hathor-stable-5038-v4-mkmlizer: ║                                                                     ║
frank2030-hathor-stable-5038-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-5038-v4-mkmlizer: Downloaded to shared memory in 24.727s
frank2030-hathor-stable-5038-v4-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-5038-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-5038-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 111.24it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:02, 119.85it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 118.97it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 124.52it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 122.02it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 125.81it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 67.67it/s] 
Loading 0:  37%|███▋      | 107/291 [00:01<00:02, 79.17it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 88.96it/s]
Loading 0:  46%|████▌     | 134/291 [00:01<00:01, 97.91it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 104.59it/s]
Loading 0:  55%|█████▍    | 159/291 [00:01<00:01, 103.29it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:01, 109.30it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 73.24it/s] 
Loading 0:  68%|██████▊   | 197/291 [00:02<00:01, 76.67it/s]
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 86.83it/s]
Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 88.69it/s]
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 102.97it/s]
Loading 0:  86%|████████▌ | 249/291 [00:02<00:00, 102.54it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 110.90it/s]
Loading 0:  95%|█████████▍| 276/291 [00:02<00:00, 106.96it/s]
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00,  7.10it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-5038-v4-mkmlizer: quantized model in 24.374s
frank2030-hathor-stable-5038-v4-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-1k in 49.101s
frank2030-hathor-stable-5038-v4-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-5038-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-5038-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v4
frank2030-hathor-stable-5038-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v4/config.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v4/special_tokens_map.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v4/tokenizer_config.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v4/tokenizer.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-5038-v4/flywheel_model.0.safetensors
frank2030-hathor-stable-5038-v4-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-v4-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-5038-v4-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-v4-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-v4-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-v4-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-v4-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-v4-mkmlizer:   warnings.warn(
frank2030-hathor-stable-5038-v4-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-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-5038-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-5038-v4-mkmlizer: Saving duration: 0.405s
frank2030-hathor-stable-5038-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.181s
frank2030-hathor-stable-5038-v4-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-5038-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-5038-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/config.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/tokenizer_config.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/special_tokens_map.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/merges.txt
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/vocab.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/tokenizer.json
frank2030-hathor-stable-5038-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-5038-v4_reward/reward.tensors
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job frank2030-hathor-stable-5038-v4-mkmlizer completed after 84.61s with status: succeeded
Stopping job with name frank2030-hathor-stable-5038-v4-mkmlizer
Pipeline stage MKMLizer completed in 85.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-5038-v4
Waiting for inference service frank2030-hathor-stable-5038-v4 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service frank2030-hathor-stable-5038-v4 ready after 50.26046943664551s
Pipeline stage ISVCDeployer completed in 56.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.051008462905884s
Received healthy response to inference request in 1.280820369720459s
Received healthy response to inference request in 1.254441738128662s
Received healthy response to inference request in 1.2521278858184814s
Received healthy response to inference request in 1.2621934413909912s
5 requests
0 failed requests
5th percentile: 1.2525906562805176
10th percentile: 1.2530534267425537
20th percentile: 1.253978967666626
30th percentile: 1.2559920787811278
40th percentile: 1.2590927600860595
50th percentile: 1.2621934413909912
60th percentile: 1.2696442127227783
70th percentile: 1.2770949840545653
80th percentile: 1.434857988357544
90th percentile: 1.742933225631714
95th percentile: 1.8969708442687987
99th percentile: 2.0202009391784665
mean time: 1.4201183795928956
Pipeline stage StressChecker completed in 7.79s
frank2030-hathor-stable-_5038_v4 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_5038_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of frank2030-hathor-stable-_5038_v4
Running pipeline stage ISVCDeleter
Checking if service frank2030-hathor-stable-5038-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.94s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-5038-v4/config.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key frank2030-hathor-stable-5038-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key frank2030-hathor-stable-5038-v4_reward/config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key frank2030-hathor-stable-5038-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.64s
frank2030-hathor-stable-_5038_v4 status is now torndown due to DeploymentManager action