developer_uid: shiroe40
submission_id: cycy233-l3-e-v2-c1_v5
model_name: auto
model_group: cycy233/L3-e-v2-c1
status: torndown
timestamp: 2024-07-20T03:00:08+00:00
num_battles: 9087
num_wins: 5310
celo_rating: 1260.56
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: 2024-07-19
win_ratio: 0.58435127104655
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': 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 cycy233-l3-e-v2-c1-v5-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v5-mkmlizer to finish
Failed to get response for submission neversleep-noromaid-v0_8068_v133: ('http://neversleep-noromaid-v0-8068-v133-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52798->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-l3-e-v2-c1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v5-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  Version: 0.9.5.post3                                               ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v5-mkmlizer: Downloaded to shared memory in 21.440s
cycy233-l3-e-v2-c1-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxvr658wy, device:0
cycy233-l3-e-v2-c1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 123.42it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 142.04it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 140.26it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:01, 134.27it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 138.95it/s]
Loading 0:  31%|███       | 90/291 [00:00<00:02, 83.77it/s] 
Loading 0:  35%|███▌      | 103/291 [00:00<00:02, 92.97it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:01, 108.06it/s]
Loading 0:  46%|████▌     | 133/291 [00:01<00:01, 113.17it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 118.65it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:00, 127.99it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 129.80it/s]
Loading 0:  67%|██████▋   | 194/291 [00:01<00:01, 84.32it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:01<00:00, 99.02it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 112.09it/s]
Loading 0:  83%|████████▎ | 242/291 [00:02<00:00, 117.20it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 121.88it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 131.26it/s]
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00,  8.98it/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-v5-mkmlizer: quantized model in 22.266s
cycy233-l3-e-v2-c1-v5-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 43.706s
cycy233-l3-e-v2-c1-v5-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v5
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v5/config.json
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v5/special_tokens_map.json
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v5/tokenizer_config.json
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v5/tokenizer.json
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v5/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v5-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v5-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-v5-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v5-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-v5-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v5-mkmlizer: Saving duration: 1.335s
cycy233-l3-e-v2-c1-v5-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.899s
cycy233-l3-e-v2-c1-v5-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v5_reward
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v5_reward/merges.txt
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v5_reward/vocab.json
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v5_reward/tokenizer.json
cycy233-l3-e-v2-c1-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v5_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v5-mkmlizer completed after 98.42s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v5-mkmlizer
Pipeline stage MKMLizer completed in 99.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v5
Waiting for inference service cycy233-l3-e-v2-c1-v5 to be ready
Inference service cycy233-l3-e-v2-c1-v5 ready after 40.78987097740173s
Pipeline stage ISVCDeployer completed in 43.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.294834852218628s
Received healthy response to inference request in 1.4787540435791016s
Received healthy response to inference request in 1.4553649425506592s
Received healthy response to inference request in 1.4311282634735107s
Received healthy response to inference request in 1.5025546550750732s
5 requests
0 failed requests
5th percentile: 1.4359755992889405
10th percentile: 1.4408229351043702
20th percentile: 1.4505176067352294
30th percentile: 1.4600427627563477
40th percentile: 1.4693984031677245
50th percentile: 1.4787540435791016
60th percentile: 1.4882742881774902
70th percentile: 1.4977945327758788
80th percentile: 1.6610106945037844
90th percentile: 1.9779227733612061
95th percentile: 2.136378812789917
99th percentile: 2.2631436443328856
mean time: 1.6325273513793945
Pipeline stage StressChecker completed in 8.87s
cycy233-l3-e-v2-c1_v5 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v5
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v5 is running
Tearing down inference service cycy233-l3-e-v2-c1-v5
Service cycy233-l3-e-v2-c1-v5 has been torndown
Pipeline stage ISVCDeleter completed in 5.50s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v5/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v5_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.98s
cycy233-l3-e-v2-c1_v5 status is now torndown due to DeploymentManager action