developer_uid: shiroe40
submission_id: cycy233-l3-e-v2-c4_v3
model_name: auto
model_group: cycy233/L3-e-v2-c4
status: torndown
timestamp: 2024-07-20T03:00:57+00:00
num_battles: 8792
num_wins: 4874
celo_rating: 1241.96
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-e-v2-c4
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-e-v2-c4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-19
win_ratio: 0.5543676069153776
generation_params: {'temperature': 0.6, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-c4-v3-mkmlizer
Waiting for job on cycy233-l3-e-v2-c4-v3-mkmlizer to finish
cycy233-l3-e-v2-c4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c4-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  Version: 0.9.5.post3                                               ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c4-v3-mkmlizer: Downloaded to shared memory in 22.760s
cycy233-l3-e-v2-c4-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkb20f_xr, device:0
cycy233-l3-e-v2-c4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c4-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 121.10it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 140.84it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 139.10it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:01, 131.97it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 139.54it/s]
Loading 0:  31%|███       | 90/291 [00:00<00:02, 84.68it/s] 
Loading 0:  35%|███▌      | 103/291 [00:00<00:02, 93.60it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:01, 108.55it/s]
Loading 0:  46%|████▌     | 134/291 [00:01<00:01, 115.15it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 119.93it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:00, 128.03it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 130.52it/s]
Loading 0:  67%|██████▋   | 194/291 [00:01<00:01, 87.29it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:01<00:00, 102.42it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 115.67it/s]
Loading 0:  83%|████████▎ | 242/291 [00:02<00:00, 121.25it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 125.29it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 132.65it/s]
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00,  9.08it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c4-v3-mkmlizer: quantized model in 21.968s
cycy233-l3-e-v2-c4-v3-mkmlizer: Processed model cycy233/L3-e-v2-c4 in 44.729s
cycy233-l3-e-v2-c4-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v3
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v3/config.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v3/special_tokens_map.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v3/tokenizer_config.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v3/tokenizer.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v3/flywheel_model.0.safetensors
cycy233-l3-e-v2-c4-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c4-v3-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-c4-v3-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v3-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-c4-v3-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v3-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-c4-v3-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c4-v3-mkmlizer: Saving duration: 1.369s
cycy233-l3-e-v2-c4-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.675s
cycy233-l3-e-v2-c4-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c4-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c4-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/config.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/special_tokens_map.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/tokenizer_config.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/merges.txt
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/vocab.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/tokenizer.json
cycy233-l3-e-v2-c4-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v3_reward/reward.tensors
Job cycy233-l3-e-v2-c4-v3-mkmlizer completed after 89.73s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c4-v3-mkmlizer
Pipeline stage MKMLizer completed in 91.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c4-v3
Waiting for inference service cycy233-l3-e-v2-c4-v3 to be ready
Inference service cycy233-l3-e-v2-c4-v3 ready after 40.774163484573364s
Pipeline stage ISVCDeployer completed in 43.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2060554027557373s
Received healthy response to inference request in 1.1521682739257812s
Received healthy response to inference request in 1.037562608718872s
Received healthy response to inference request in 1.1383452415466309s
Received healthy response to inference request in 1.1705703735351562s
5 requests
0 failed requests
5th percentile: 1.0577191352844237
10th percentile: 1.0778756618499756
20th percentile: 1.1181887149810792
30th percentile: 1.1411098480224608
40th percentile: 1.146639060974121
50th percentile: 1.1521682739257812
60th percentile: 1.1595291137695312
70th percentile: 1.1668899536132813
80th percentile: 1.3776673793792726
90th percentile: 1.791861391067505
95th percentile: 1.998958396911621
99th percentile: 2.164636001586914
mean time: 1.3409403800964355
Pipeline stage StressChecker completed in 7.34s
cycy233-l3-e-v2-c4_v3 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c4_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c4_v3
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c4-v3 is running
Tearing down inference service cycy233-l3-e-v2-c4-v3
Service cycy233-l3-e-v2-c4-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.49s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.33s
cycy233-l3-e-v2-c4_v3 status is now torndown due to DeploymentManager action