developer_uid: shiroe40
submission_id: cycy233-l3-base-v2-e3-0_v4
model_name: full_2
model_group: cycy233/L3-base-v2-e3.0
status: torndown
timestamp: 2024-07-04T10:19:27+00:00
num_battles: 13607
num_wins: 7063
celo_rating: 1195.75
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-base-v2-e3.0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: full_2
is_internal_developer: False
language_model: cycy233/L3-base-v2-e3.0
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-04
win_ratio: 0.5190710663629015
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, '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 cycy233-l3-base-v2-e3-0-v4-mkmlizer
Waiting for job on cycy233-l3-base-v2-e3-0-v4-mkmlizer to finish
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║       /___/                                                         ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║                                                                     ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║                                                                     ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║                                                                     ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ║                                                                     ║
cycy233-l3-base-v2-e3-0-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Downloaded to shared memory in 29.697s
cycy233-l3-base-v2-e3-0-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v2-e3-0-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 61.04it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 68.88it/s]
Loading 0:  99%|█████████▊| 287/291 [00:03<00:00, 103.06it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v2-e3-0-v4-mkmlizer: quantized model in 25.370s
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Processed model cycy233/L3-base-v2-e3.0 in 55.068s
cycy233-l3-base-v2-e3-0-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v2-e3-0-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v2-e3-0-v4
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e3-0-v4/config.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e3-0-v4/tokenizer_config.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e3-0-v4/special_tokens_map.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e3-0-v4/tokenizer.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v2-e3-0-v4/flywheel_model.0.safetensors
cycy233-l3-base-v2-e3-0-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v2-e3-0-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.
cycy233-l3-base-v2-e3-0-v4-mkmlizer:   warnings.warn(
cycy233-l3-base-v2-e3-0-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`.
cycy233-l3-base-v2-e3-0-v4-mkmlizer:   warnings.warn(
cycy233-l3-base-v2-e3-0-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.
cycy233-l3-base-v2-e3-0-v4-mkmlizer:   warnings.warn(
cycy233-l3-base-v2-e3-0-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.
cycy233-l3-base-v2-e3-0-v4-mkmlizer:   warnings.warn(
cycy233-l3-base-v2-e3-0-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()
cycy233-l3-base-v2-e3-0-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Saving duration: 0.446s
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.823s
cycy233-l3-base-v2-e3-0-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v2-e3-0-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v2-e3-0-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward/special_tokens_map.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward/merges.txt
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward/config.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward/tokenizer_config.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward/vocab.json
cycy233-l3-base-v2-e3-0-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v2-e3-0-v4_reward/tokenizer.json
Job cycy233-l3-base-v2-e3-0-v4-mkmlizer completed after 83.13s with status: succeeded
Stopping job with name cycy233-l3-base-v2-e3-0-v4-mkmlizer
Pipeline stage MKMLizer completed in 84.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v2-e3-0-v4
Waiting for inference service cycy233-l3-base-v2-e3-0-v4 to be ready
Connection pool is full, discarding connection: %s
Inference service cycy233-l3-base-v2-e3-0-v4 ready after 40.20450472831726s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.01583194732666s
Received healthy response to inference request in 1.2042269706726074s
Received healthy response to inference request in 1.2226474285125732s
Received healthy response to inference request in 1.2408034801483154s
Received healthy response to inference request in 1.1947526931762695s
5 requests
0 failed requests
5th percentile: 1.196647548675537
10th percentile: 1.1985424041748047
20th percentile: 1.20233211517334
30th percentile: 1.2079110622406006
40th percentile: 1.2152792453765868
50th percentile: 1.2226474285125732
60th percentile: 1.22990984916687
70th percentile: 1.237172269821167
80th percentile: 1.3958091735839846
90th percentile: 1.7058205604553223
95th percentile: 1.860826253890991
99th percentile: 1.9848308086395263
mean time: 1.3756525039672851
Pipeline stage StressChecker completed in 7.68s
cycy233-l3-base-v2-e3-0_v4 status is now deployed due to DeploymentManager action
cycy233-l3-base-v2-e3-0_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-base-v2-e3-0_v4
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-base-v2-e3-0-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-base-v2-e3-0-v4/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v2-e3-0-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v2-e3-0-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v2-e3-0-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v2-e3-0-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v2-e3-0-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.53s
cycy233-l3-base-v2-e3-0_v4 status is now torndown due to DeploymentManager action