developer_uid: zonemercy
submission_id: chaiml-augment-ensemble-_6303_v1
model_name: chaiml-augment-ensemble_v3
model_group: ChaiML/augment-ensemble-
status: torndown
timestamp: 2024-07-13T02:45:18+00:00
num_battles: 38104
num_wins: 22753
celo_rating: 1262.49
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/augment-ensemble-ep2lre5
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-augment-ensemble_v3
is_internal_developer: True
language_model: ChaiML/augment-ensemble-ep2lre5
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-12
win_ratio: 0.5971289103506193
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, '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 chaiml-augment-ensemble-6303-v1-mkmlizer
Waiting for job on chaiml-augment-ensemble-6303-v1-mkmlizer to finish
chaiml-augment-ensemble-6303-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-augment-ensemble-6303-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║       /___/                                                         ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-6303-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-augment-ensemble-6303-v1-mkmlizer: Downloaded to shared memory in 62.614s
chaiml-augment-ensemble-6303-v1-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-augment-ensemble-6303-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-augment-ensemble-6303-v1/flywheel_model.0.safetensors
chaiml-augment-ensemble-6303-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-augment-ensemble-6303-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.
chaiml-augment-ensemble-6303-v1-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-6303-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`.
chaiml-augment-ensemble-6303-v1-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-6303-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.
chaiml-augment-ensemble-6303-v1-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-6303-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.
chaiml-augment-ensemble-6303-v1-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-6303-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:07<00:07,  7.04s/it]
Downloading shards: 100%|██████████| 2/2 [00:10<00:00,  4.80s/it]
Downloading shards: 100%|██████████| 2/2 [00:10<00:00,  5.14s/it]
chaiml-augment-ensemble-6303-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.56it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.53it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.32it/s]
chaiml-augment-ensemble-6303-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-augment-ensemble-6303-v1-mkmlizer: Saving duration: 2.872s
chaiml-augment-ensemble-6303-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.602s
chaiml-augment-ensemble-6303-v1-mkmlizer: creating bucket guanaco-reward-models
chaiml-augment-ensemble-6303-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-augment-ensemble-6303-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/config.json
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/merges.txt
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/special_tokens_map.json
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/vocab.json
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/tokenizer.json
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/tokenizer_config.json
chaiml-augment-ensemble-6303-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-augment-ensemble-6303-v1_reward/reward.tensors
Job chaiml-augment-ensemble-6303-v1-mkmlizer completed after 135.17s with status: succeeded
Stopping job with name chaiml-augment-ensemble-6303-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-augment-ensemble-6303-v1
Waiting for inference service chaiml-augment-ensemble-6303-v1 to be ready
Inference service chaiml-augment-ensemble-6303-v1 ready after 40.19305086135864s
Pipeline stage ISVCDeployer completed in 47.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.312843084335327s
Received healthy response to inference request in 1.577221393585205s
Received healthy response to inference request in 1.5417490005493164s
Received healthy response to inference request in 1.508143424987793s
Received healthy response to inference request in 1.5807385444641113s
5 requests
0 failed requests
5th percentile: 1.5148645401000977
10th percentile: 1.5215856552124023
20th percentile: 1.5350278854370116
30th percentile: 1.5488434791564942
40th percentile: 1.5630324363708497
50th percentile: 1.577221393585205
60th percentile: 1.5786282539367675
70th percentile: 1.58003511428833
80th percentile: 1.7271594524383547
90th percentile: 2.020001268386841
95th percentile: 2.166422176361084
99th percentile: 2.2835589027404786
mean time: 1.7041390895843507
Pipeline stage StressChecker completed in 9.14s
chaiml-augment-ensemble-_6303_v1 status is now deployed due to DeploymentManager action
chaiml-augment-ensemble-_6303_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-augment-ensemble-_6303_v1
Running pipeline stage ISVCDeleter
Checking if service chaiml-augment-ensemble-6303-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-augment-ensemble-6303-v1/config.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-6303-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-6303-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-6303-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-6303-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-augment-ensemble-6303-v1_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-6303-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-6303-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-6303-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-6303-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-6303-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-6303-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.37s
chaiml-augment-ensemble-_6303_v1 status is now torndown due to DeploymentManager action