developer_uid: sao10k
submission_id: sao10k-l3-8b-chara-v1-alpha_v2
model_name: Chara-Names
model_group: Sao10K/L3-8B-Chara-v1-Al
status: torndown
timestamp: 2024-06-30T10:42:33+00:00
num_battles: 30597
num_wins: 14914
celo_rating: 1166.83
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-8B-Chara-v1-Alpha
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: Chara-Names
is_internal_developer: False
language_model: Sao10K/L3-8B-Chara-v1-Alpha
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-30
win_ratio: 0.4874334085041017
generation_params: {'temperature': 1.4, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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|>{bot_name}<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>{user_name}<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n', '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 sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer
Waiting for job on sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer to finish
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║       /___/                                                         ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-chara-v1-alpha-v2-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.
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Connection pool is full, discarding connection: %s
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 77.54it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 87.95it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 128.77it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: quantized model in 24.007s
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: Processed model Sao10K/L3-8B-Chara-v1-Alpha in 43.630s
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v2
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v2/special_tokens_map.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v2/config.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v2/tokenizer.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-chara-v1-alpha-v2/tokenizer_config.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-8b-chara-v1-alpha-v2-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.
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer:   warnings.warn(
sao10k-l3-8b-chara-v1-alpha-v2-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.
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer:   warnings.warn(
sao10k-l3-8b-chara-v1-alpha-v2-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.
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer:   warnings.warn(
sao10k-l3-8b-chara-v1-alpha-v2-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()
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: Saving duration: 0.422s
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.522s
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/tokenizer_config.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/config.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/special_tokens_map.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/vocab.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/merges.txt
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/tokenizer.json
sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-8b-chara-v1-alpha-v2_reward/reward.tensors
Job sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer completed after 72.68s with status: succeeded
Stopping job with name sao10k-l3-8b-chara-v1-alpha-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-8b-chara-v1-alpha-v2
Waiting for inference service sao10k-l3-8b-chara-v1-alpha-v2 to be ready
Inference service sao10k-l3-8b-chara-v1-alpha-v2 ready after 40.17597556114197s
Pipeline stage ISVCDeployer completed in 46.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.137608051300049s
Received healthy response to inference request in 1.302426815032959s
Received healthy response to inference request in 1.2958719730377197s
Received healthy response to inference request in 1.2693963050842285s
Received healthy response to inference request in 1.2987756729125977s
5 requests
0 failed requests
5th percentile: 1.2746914386749268
10th percentile: 1.279986572265625
20th percentile: 1.2905768394470214
30th percentile: 1.2964527130126953
40th percentile: 1.2976141929626466
50th percentile: 1.2987756729125977
60th percentile: 1.300236129760742
70th percentile: 1.3016965866088868
80th percentile: 1.4694630622863771
90th percentile: 1.803535556793213
95th percentile: 1.9705718040466307
99th percentile: 2.104200801849365
mean time: 1.4608157634735108
Pipeline stage StressChecker completed in 7.95s
sao10k-l3-8b-chara-v1-alpha_v2 status is now deployed due to DeploymentManager action
sao10k-l3-8b-chara-v1-alpha_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-8b-chara-v1-alpha_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-8b-chara-v1-alpha-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-8b-chara-v1-alpha-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-chara-v1-alpha-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.69s
sao10k-l3-8b-chara-v1-alpha_v2 status is now torndown due to DeploymentManager action