developer_uid: Hastagaras
submission_id: hastagaras-jamet-8b-l3-m_5621_v1
model_name: gf
model_group: Hastagaras/Jamet-8B-L3-M
status: torndown
timestamp: 2024-07-03T04:42:53+00:00
num_battles: 14390
num_wins: 7880
celo_rating: 1207.22
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Jamet-8B-L3-MK.VI-Base
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: gf
is_internal_developer: False
language_model: Hastagaras/Jamet-8B-L3-MK.VI-Base
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-02
win_ratio: 0.5476025017373176
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.065, '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|><|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}
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-jamet-8b-l3-m-5621-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Downloaded to shared memory in 22.449s
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 119.75it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 144.20it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 144.37it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:01, 141.35it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 145.97it/s]
Loading 0:  31%|███▏      | 91/291 [00:00<00:02, 75.15it/s] 
Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 84.31it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 102.13it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 117.57it/s]
Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 124.79it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:00, 127.93it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 84.72it/s] 
Loading 0:  69%|██████▉   | 201/291 [00:01<00:00, 93.62it/s]
Loading 0:  74%|███████▍  | 216/291 [00:02<00:00, 104.81it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 111.60it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 125.21it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 136.37it/s]
Loading 0:  96%|█████████▌| 279/291 [00:02<00:00, 138.89it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: quantized model in 23.760s
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.VI-Base in 46.209s
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5621-v1
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5621-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5621-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-5621-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-jamet-8b-l3-m-5621-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-5621-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-jamet-8b-l3-m-5621-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-5621-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-jamet-8b-l3-m-5621-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-5621-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-jamet-8b-l3-m-5621-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-5621-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-jamet-8b-l3-m-5621-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Saving duration: 0.403s
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.052s
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/config.json
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5621-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer completed after 73.61s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-5621-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-5621-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-5621-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-5621-v1 ready after 40.27778339385986s
Pipeline stage ISVCDeployer completed in 47.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0764598846435547s
Received healthy response to inference request in 1.3253800868988037s
Received healthy response to inference request in 1.3066868782043457s
Received healthy response to inference request in 1.2687833309173584s
Received healthy response to inference request in 1.338352918624878s
5 requests
0 failed requests
5th percentile: 1.2763640403747558
10th percentile: 1.2839447498321532
20th percentile: 1.2991061687469483
30th percentile: 1.3104255199432373
40th percentile: 1.3179028034210205
50th percentile: 1.3253800868988037
60th percentile: 1.3305692195892334
70th percentile: 1.335758352279663
80th percentile: 1.4859743118286135
90th percentile: 1.781217098236084
95th percentile: 1.9288384914398191
99th percentile: 2.0469356060028074
mean time: 1.463132619857788
Pipeline stage StressChecker completed in 8.05s
hastagaras-jamet-8b-l3-m_5621_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_5621_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jamet-8b-l3-m_5621_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jamet-8b-l3-m-5621-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.03s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-5621-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-5621-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.68s
hastagaras-jamet-8b-l3-m_5621_v1 status is now torndown due to DeploymentManager action