submission_id: hastagaras-bebi-masuk-nelas_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1210.73
display_name: hastagaras-bebi-masuk-nelas_v1
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 65, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/BEBI-MASUK-NELAS
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Hastagaras/BEBI-MASUK-NE
model_name: hastagaras-bebi-masuk-nelas_v1
model_num_parameters: 8030261248.0
model_repo: Hastagaras/BEBI-MASUK-NELAS
model_size: 8B
num_battles: 35064
num_wins: 18688
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: 2024-07-09T22:52:42+00:00
us_pacific_date: 2024-07-09
win_ratio: 0.5329682865617157
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bebi-masuk-nelas-v1-mkmlizer
Waiting for job on hastagaras-bebi-masuk-nelas-v1-mkmlizer to finish
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║                                                                     ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║                                                                     ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║                                                                     ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ║                                                                     ║
hastagaras-bebi-masuk-nelas-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Downloaded to shared memory in 33.495s
hastagaras-bebi-masuk-nelas-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bebi-masuk-nelas-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 113.91it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 114.97it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 130.08it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:01, 128.17it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 126.96it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 130.48it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:03, 59.56it/s] 
Loading 0:  38%|███▊      | 111/291 [00:01<00:02, 75.96it/s]
Loading 0:  42%|████▏     | 123/291 [00:01<00:02, 83.11it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 96.10it/s]
Loading 0:  53%|█████▎    | 154/291 [00:01<00:01, 108.19it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:01, 107.57it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 114.61it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 60.88it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 76.22it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 90.55it/s]
Loading 0:  83%|████████▎ | 241/291 [00:02<00:00, 97.40it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 104.72it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 115.45it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00,  7.07it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bebi-masuk-nelas-v1-mkmlizer: quantized model in 28.642s
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Processed model Hastagaras/BEBI-MASUK-NELAS in 62.138s
hastagaras-bebi-masuk-nelas-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bebi-masuk-nelas-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bebi-masuk-nelas-v1
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-nelas-v1/special_tokens_map.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-nelas-v1/tokenizer_config.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-nelas-v1/config.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-nelas-v1/tokenizer.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bebi-masuk-nelas-v1/flywheel_model.0.safetensors
hastagaras-bebi-masuk-nelas-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bebi-masuk-nelas-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.
hastagaras-bebi-masuk-nelas-v1-mkmlizer:   warnings.warn(
hastagaras-bebi-masuk-nelas-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`.
hastagaras-bebi-masuk-nelas-v1-mkmlizer:   warnings.warn(
hastagaras-bebi-masuk-nelas-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.
hastagaras-bebi-masuk-nelas-v1-mkmlizer:   warnings.warn(
hastagaras-bebi-masuk-nelas-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-bebi-masuk-nelas-v1-mkmlizer:   warnings.warn(
hastagaras-bebi-masuk-nelas-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-bebi-masuk-nelas-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Saving duration: 0.501s
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.918s
hastagaras-bebi-masuk-nelas-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bebi-masuk-nelas-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bebi-masuk-nelas-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/config.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/special_tokens_map.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/merges.txt
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/tokenizer_config.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/vocab.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/tokenizer.json
hastagaras-bebi-masuk-nelas-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bebi-masuk-nelas-v1_reward/reward.tensors
Job hastagaras-bebi-masuk-nelas-v1-mkmlizer completed after 83.69s with status: succeeded
Stopping job with name hastagaras-bebi-masuk-nelas-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bebi-masuk-nelas-v1
Waiting for inference service hastagaras-bebi-masuk-nelas-v1 to be ready
Inference service hastagaras-bebi-masuk-nelas-v1 ready after 40.51714086532593s
Pipeline stage ISVCDeployer completed in 47.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9847118854522705s
Received healthy response to inference request in 1.3329575061798096s
Received healthy response to inference request in 1.3110651969909668s
Received healthy response to inference request in 1.2750613689422607s
Received healthy response to inference request in 1.3404948711395264s
5 requests
0 failed requests
5th percentile: 1.282262134552002
10th percentile: 1.2894629001617433
20th percentile: 1.3038644313812255
30th percentile: 1.3154436588287353
40th percentile: 1.3242005825042724
50th percentile: 1.3329575061798096
60th percentile: 1.3359724521636962
70th percentile: 1.338987398147583
80th percentile: 1.4693382740020753
90th percentile: 1.727025079727173
95th percentile: 1.8558684825897216
99th percentile: 1.9589432048797608
mean time: 1.4488581657409667
Pipeline stage StressChecker completed in 7.95s
hastagaras-bebi-masuk-nelas_v1 status is now deployed due to DeploymentManager action
hastagaras-bebi-masuk-nelas_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-bebi-masuk-nelas_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-bebi-masuk-nelas-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-bebi-masuk-nelas-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-bebi-masuk-nelas-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-bebi-masuk-nelas-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-bebi-masuk-nelas-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-bebi-masuk-nelas-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-bebi-masuk-nelas-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.35s
hastagaras-bebi-masuk-nelas_v1 status is now torndown due to DeploymentManager action