developer_uid: sao10k
submission_id: sao10k-l3-rp-v5-1_v4
model_name: 5-1-Align
model_group: Sao10K/L3-RP-v5.1
status: torndown
timestamp: 2024-07-09T11:04:27+00:00
num_battles: 29469
num_wins: 12998
celo_rating: 1157.51
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-RP-v5.1
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/CHAI_alignment_reward_model
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 5-1-Align
is_internal_developer: False
language_model: Sao10K/L3-RP-v5.1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-09
win_ratio: 0.44107367063694053
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, '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 sao10k-l3-rp-v5-1-v4-mkmlizer
Waiting for job on sao10k-l3-rp-v5-1-v4-mkmlizer to finish
sao10k-l3-rp-v5-1-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-1-v4-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
sao10k-l3-rp-v5-1-v4-mkmlizer: Downloaded to shared memory in 24.095s
sao10k-l3-rp-v5-1-v4-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-1-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-1-v4-mkmlizer: quantized model in 24.523s
sao10k-l3-rp-v5-1-v4-mkmlizer: Processed model Sao10K/L3-RP-v5.1 in 48.618s
sao10k-l3-rp-v5-1-v4-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-1-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-1-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v4
sao10k-l3-rp-v5-1-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v4/config.json
sao10k-l3-rp-v5-1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v4/tokenizer_config.json
sao10k-l3-rp-v5-1-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v4/special_tokens_map.json
sao10k-l3-rp-v5-1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v4/tokenizer.json
sao10k-l3-rp-v5-1-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v4/flywheel_model.0.safetensors
sao10k-l3-rp-v5-1-v4-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
sao10k-l3-rp-v5-1-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.
sao10k-l3-rp-v5-1-v4-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-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`.
sao10k-l3-rp-v5-1-v4-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-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.
sao10k-l3-rp-v5-1-v4-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-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.
sao10k-l3-rp-v5-1-v4-mkmlizer:   warnings.warn(
Job sao10k-l3-rp-v5-1-v4-mkmlizer completed after 74.18s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-1-v4-mkmlizer
Pipeline stage MKMLizer completed in 75.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-1-v4
Waiting for inference service sao10k-l3-rp-v5-1-v4 to be ready
Inference service sao10k-l3-rp-v5-1-v4 ready after 40.419323682785034s
Pipeline stage ISVCDeployer completed in 47.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0438456535339355s
Received healthy response to inference request in 1.2960944175720215s
Received healthy response to inference request in 1.2507004737854004s
Received healthy response to inference request in 1.2418711185455322s
Received healthy response to inference request in 1.2671258449554443s
5 requests
0 failed requests
5th percentile: 1.2436369895935058
10th percentile: 1.2454028606414795
20th percentile: 1.2489346027374268
30th percentile: 1.253985548019409
40th percentile: 1.2605556964874267
50th percentile: 1.2671258449554443
60th percentile: 1.2787132740020752
70th percentile: 1.2903007030487061
80th percentile: 1.4456446647644043
90th percentile: 1.74474515914917
95th percentile: 1.8942954063415527
99th percentile: 2.013935604095459
mean time: 1.4199275016784667
Pipeline stage StressChecker completed in 7.77s
sao10k-l3-rp-v5-1_v4 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-1_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-1_v4
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-1-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-1-v4/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-1-v4_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.47s
sao10k-l3-rp-v5-1_v4 status is now torndown due to DeploymentManager action