developer_uid: Hastagaras
submission_id: hastagaras-cokelat_v1
model_name: hastagaras-cokelat_v1
model_group: Hastagaras/Cokelat
status: torndown
timestamp: 2024-06-27T02:43:29+00:00
num_battles: 29726
num_wins: 15725
celo_rating: 1200.91
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Cokelat
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: hastagaras-cokelat_v1
is_internal_developer: False
language_model: Hastagaras/Cokelat
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-26
win_ratio: 0.5289981834084639
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|>{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n\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 hastagaras-cokelat-v1-mkmlizer
Waiting for job on hastagaras-cokelat-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
hastagaras-cokelat-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-cokelat-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-cokelat-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-cokelat-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-cokelat-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-cokelat-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-cokelat-v1-mkmlizer: ║                                                                     ║
hastagaras-cokelat-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-cokelat-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-cokelat-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-cokelat-v1-mkmlizer: ║                                                                     ║
hastagaras-cokelat-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-cokelat-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-cokelat-v1-mkmlizer: ║                                                                     ║
hastagaras-cokelat-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-cokelat-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-cokelat-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-cokelat-v1-mkmlizer: ║                                                                     ║
hastagaras-cokelat-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-cokelat-v1-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.
hastagaras-cokelat-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-cokelat-v1-mkmlizer: Downloaded to shared memory in 38.262s
hastagaras-cokelat-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-cokelat-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-cokelat-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 137.14it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 152.73it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 157.94it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 158.99it/s]
Loading 0:  29%|██▉       | 84/291 [00:00<00:02, 85.15it/s] 
Loading 0:  34%|███▍      | 99/291 [00:00<00:01, 98.01it/s]
Loading 0:  40%|███▉      | 116/291 [00:00<00:01, 113.42it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 119.37it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 132.69it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 142.36it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 95.11it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 103.20it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 116.96it/s]
Loading 0:  82%|████████▏ | 238/291 [00:01<00:00, 129.23it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 139.65it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 146.73it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.00it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-cokelat-v1-mkmlizer: quantized model in 22.774s
hastagaras-cokelat-v1-mkmlizer: Processed model Hastagaras/Cokelat in 63.550s
hastagaras-cokelat-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-cokelat-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-cokelat-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-cokelat-v1
hastagaras-cokelat-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-cokelat-v1/config.json
hastagaras-cokelat-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-cokelat-v1/special_tokens_map.json
hastagaras-cokelat-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-cokelat-v1/tokenizer.json
hastagaras-cokelat-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-cokelat-v1/tokenizer_config.json
hastagaras-cokelat-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-cokelat-v1/flywheel_model.0.safetensors
hastagaras-cokelat-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-cokelat-v1-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.
hastagaras-cokelat-v1-mkmlizer:   warnings.warn(
hastagaras-cokelat-v1-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.
hastagaras-cokelat-v1-mkmlizer:   warnings.warn(
hastagaras-cokelat-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.
hastagaras-cokelat-v1-mkmlizer:   warnings.warn(
hastagaras-cokelat-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()
hastagaras-cokelat-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-cokelat-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-cokelat-v1-mkmlizer: Saving duration: 0.409s
hastagaras-cokelat-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.211s
hastagaras-cokelat-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-cokelat-v1_reward/reward.tensors
Job hastagaras-cokelat-v1-mkmlizer completed after 93.33s with status: succeeded
Stopping job with name hastagaras-cokelat-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-cokelat-v1
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Waiting for inference service hastagaras-cokelat-v1 to be ready
Inference service hastagaras-cokelat-v1 ready after 30.161110877990723s
Pipeline stage ISVCDeployer completed in 36.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.165105104446411s
Received healthy response to inference request in 1.293250560760498s
Received healthy response to inference request in 1.2856106758117676s
Received healthy response to inference request in 1.312537431716919s
Received healthy response to inference request in 1.2654798030853271s
5 requests
0 failed requests
5th percentile: 1.2695059776306152
10th percentile: 1.2735321521759033
20th percentile: 1.2815845012664795
30th percentile: 1.2871386528015136
40th percentile: 1.290194606781006
50th percentile: 1.293250560760498
60th percentile: 1.3009653091430664
70th percentile: 1.3086800575256348
80th percentile: 1.4830509662628175
90th percentile: 1.8240780353546144
95th percentile: 1.9945915699005126
99th percentile: 2.131002397537231
mean time: 1.4643967151641846
Pipeline stage StressChecker completed in 7.97s
hastagaras-cokelat_v1 status is now deployed due to DeploymentManager action
hastagaras-cokelat_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-cokelat_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-cokelat-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-cokelat-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-cokelat-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-cokelat-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-cokelat-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-cokelat-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-cokelat-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-cokelat-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-cokelat-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-cokelat-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-cokelat-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-cokelat-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-cokelat-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
hastagaras-cokelat_v1 status is now torndown due to DeploymentManager action