developer_uid: shiroe40
submission_id: cycy233-l3-e-v2-c1_v10
model_name: auto
model_group: cycy233/L3-e-v2-c1
status: torndown
timestamp: 2024-07-22T09:35:14+00:00
num_battles: 12741
num_wins: 7670
celo_rating: 1263.07
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-e-v2-c1
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-e-v2-c1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-22
win_ratio: 0.6019935640844518
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|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-e-v2-c1-v10-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v10-mkmlizer to finish
cycy233-l3-e-v2-c1-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v10-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  Version: 0.9.5.post3                                               ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v10-mkmlizer: Downloaded to shared memory in 22.856s
cycy233-l3-e-v2-c1-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpch33w0yb, device:0
cycy233-l3-e-v2-c1-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v10-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 123.39it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 142.96it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 140.26it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:01, 136.01it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 140.69it/s]
Loading 0:  31%|███▏      | 91/291 [00:00<00:02, 86.38it/s] 
Loading 0:  36%|███▌      | 104/291 [00:00<00:02, 92.89it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 108.10it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 119.53it/s]
Loading 0:  52%|█████▏    | 152/291 [00:01<00:01, 122.49it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 125.75it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 128.42it/s]
Loading 0:  67%|██████▋   | 195/291 [00:01<00:01, 87.49it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:01<00:00, 100.84it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 114.26it/s]
Loading 0:  83%|████████▎ | 242/291 [00:02<00:00, 118.67it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 123.04it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 132.78it/s]
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00,  9.03it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c1-v10-mkmlizer: quantized model in 22.086s
cycy233-l3-e-v2-c1-v10-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 44.943s
cycy233-l3-e-v2-c1-v10-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v10
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v10/config.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v10/special_tokens_map.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v10/tokenizer_config.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v10/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v10-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-e-v2-c1-v10-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-e-v2-c1-v10-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-e-v2-c1-v10-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v10-mkmlizer: Saving duration: 1.393s
cycy233-l3-e-v2-c1-v10-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.290s
cycy233-l3-e-v2-c1-v10-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/config.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/merges.txt
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/vocab.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/tokenizer.json
cycy233-l3-e-v2-c1-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v10_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v10-mkmlizer completed after 87.46s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v10-mkmlizer
Pipeline stage MKMLizer completed in 88.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v10
Waiting for inference service cycy233-l3-e-v2-c1-v10 to be ready
Inference service cycy233-l3-e-v2-c1-v10 ready after 51.8200888633728s
Pipeline stage ISVCDeployer completed in 54.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2134616374969482s
Received healthy response to inference request in 1.4963457584381104s
Received healthy response to inference request in 1.458838701248169s
Received healthy response to inference request in 1.4422636032104492s
Received healthy response to inference request in 1.3983850479125977s
5 requests
0 failed requests
5th percentile: 1.407160758972168
10th percentile: 1.4159364700317383
20th percentile: 1.433487892150879
30th percentile: 1.4455786228179932
40th percentile: 1.452208662033081
50th percentile: 1.458838701248169
60th percentile: 1.4738415241241456
70th percentile: 1.488844347000122
80th percentile: 1.639768934249878
90th percentile: 1.9266152858734131
95th percentile: 2.0700384616851806
99th percentile: 2.1847770023345947
mean time: 1.601858949661255
Pipeline stage StressChecker completed in 8.67s
cycy233-l3-e-v2-c1_v10 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v10
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v10 is running
Tearing down inference service cycy233-l3-e-v2-c1-v10
Service cycy233-l3-e-v2-c1-v10 has been torndown
Pipeline stage ISVCDeleter completed in 4.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v10/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v10_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.79s
cycy233-l3-e-v2-c1_v10 status is now torndown due to DeploymentManager action