developer_uid: shiroe40
submission_id: cycy233-l3-e-v0-c4_v1
model_name: auto
model_group: cycy233/L3-e-v0-c4
status: torndown
timestamp: 2024-07-18T02:30:11+00:00
num_battles: 16810
num_wins: 7680
celo_rating: 1157.53
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-e-v0-c4
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-v0-c4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-17
win_ratio: 0.45687091017251635
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, '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': "<|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-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-e-v0-c4-v1-mkmlizer to finish
cycy233-l3-e-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v0-c4-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  Version: 0.9.5.post3                                               ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v0-c4-v1-mkmlizer: Downloaded to shared memory in 42.038s
cycy233-l3-e-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd_j5di2h, device:0
cycy233-l3-e-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v0-c4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 117.98it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 113.35it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 124.35it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:01, 119.80it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 125.31it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 122.22it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:03, 56.41it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 64.45it/s]
Loading 0:  40%|███▉      | 116/291 [00:01<00:02, 76.72it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 87.32it/s]
Loading 0:  48%|████▊     | 141/291 [00:01<00:01, 92.46it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 105.50it/s]
Loading 0:  58%|█████▊    | 169/291 [00:01<00:01, 108.99it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 110.38it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 53.30it/s] 
Loading 0:  71%|███████   | 206/291 [00:02<00:01, 65.02it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 76.62it/s]
Loading 0:  80%|████████  | 234/291 [00:02<00:00, 88.95it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 96.12it/s]
Loading 0:  89%|████████▉ | 260/291 [00:02<00:00, 104.10it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 110.35it/s]
Loading 0:  98%|█████████▊| 286/291 [00:03<00:00, 114.00it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v0-c4-v1-mkmlizer: quantized model in 29.099s
cycy233-l3-e-v0-c4-v1-mkmlizer: Processed model cycy233/L3-e-v0-c4 in 71.138s
cycy233-l3-e-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v1
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v1/config.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v1/tokenizer_config.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-e-v0-c4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v0-c4-v1-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-v0-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v0-c4-v1-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-v0-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v0-c4-v1-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-v0-c4-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v0-c4-v1-mkmlizer: Saving duration: 2.233s
cycy233-l3-e-v0-c4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.894s
cycy233-l3-e-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/config.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/merges.txt
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/vocab.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/tokenizer.json
cycy233-l3-e-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-e-v0-c4-v1-mkmlizer completed after 128.05s with status: succeeded
Stopping job with name cycy233-l3-e-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 129.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v0-c4-v1
Waiting for inference service cycy233-l3-e-v0-c4-v1 to be ready
Inference service cycy233-l3-e-v0-c4-v1 ready after 60.92861890792847s
Pipeline stage ISVCDeployer completed in 62.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.246389627456665s
Received healthy response to inference request in 1.543222188949585s
Received healthy response to inference request in 1.4635059833526611s
Received healthy response to inference request in 1.4146368503570557s
Received healthy response to inference request in 1.5723066329956055s
5 requests
0 failed requests
5th percentile: 1.4244106769561768
10th percentile: 1.4341845035552978
20th percentile: 1.45373215675354
30th percentile: 1.4794492244720459
40th percentile: 1.5113357067108155
50th percentile: 1.543222188949585
60th percentile: 1.554855966567993
70th percentile: 1.5664897441864014
80th percentile: 1.7071232318878176
90th percentile: 1.9767564296722413
95th percentile: 2.111573028564453
99th percentile: 2.219426307678223
mean time: 1.6480122566223145
Pipeline stage StressChecker completed in 8.93s
cycy233-l3-e-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-e-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v0-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v0-c4-v1 is running
Tearing down inference service cycy233-l3-e-v0-c4-v1
Service cycy233-l3-e-v0-c4-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v0-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v0-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v0-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v0-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v0-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v0-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v0-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v0-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v0-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v0-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v0-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v0-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.31s
cycy233-l3-e-v0-c4_v1 status is now torndown due to DeploymentManager action