developer_uid: sao10k
submission_id: sao10k-l3-rp-v2-1_v1
model_name: L3-RP-v2-Test1
model_group: Sao10K/L3-RP-v2.1
status: torndown
timestamp: 2024-05-19T11:20:49+00:00
num_battles: 22466
num_wins: 11701
celo_rating: 1190.68
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-RP-v2.1
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: L3-RP-v2-Test1
is_internal_developer: False
language_model: Sao10K/L3-RP-v2.1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-19
win_ratio: 0.5208314786788926
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, '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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v2-1-v1-mkmlizer
Waiting for job on sao10k-l3-rp-v2-1-v1-mkmlizer to finish
sao10k-l3-rp-v2-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v2-1-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v2-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v2-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
sao10k-l3-rp-v2-1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v2-1-v1-mkmlizer: Downloaded to shared memory in 27.206s
sao10k-l3-rp-v2-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v2-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v2-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<09:43,  2.02s/it]
Loading 0:   5%|▍         | 14/291 [00:04<01:00,  4.57it/s]
Loading 0:  11%|█         | 31/291 [00:04<00:21, 12.24it/s]
Loading 0:  17%|█▋        | 50/291 [00:04<00:10, 23.29it/s]
Loading 0:  22%|██▏       | 65/291 [00:04<00:08, 27.36it/s]
Loading 0:  30%|██▉       | 86/291 [00:04<00:04, 42.94it/s]
Loading 0:  37%|███▋      | 108/291 [00:04<00:02, 62.24it/s]
Loading 0:  45%|████▍     | 130/291 [00:05<00:01, 83.27it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:01, 99.67it/s]
Loading 0:  57%|█████▋    | 167/291 [00:05<00:01, 75.69it/s]
Loading 0:  64%|██████▍   | 186/291 [00:05<00:01, 92.27it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:00, 118.47it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:00, 133.28it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 156.31it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 101.24it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v2-1-v1-mkmlizer: quantized model in 17.403s
sao10k-l3-rp-v2-1-v1-mkmlizer: Processed model Sao10K/L3-RP-v2.1 in 45.568s
sao10k-l3-rp-v2-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v2-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v2-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v1
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v1/tokenizer_config.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v1/special_tokens_map.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v1/config.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v1/tokenizer.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v1/flywheel_model.0.safetensors
sao10k-l3-rp-v2-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-rp-v2-1-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v2-1-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.
sao10k-l3-rp-v2-1-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v2-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
sao10k-l3-rp-v2-1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v2-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v2-1-v1-mkmlizer: Saving duration: 0.224s
sao10k-l3-rp-v2-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.551s
sao10k-l3-rp-v2-1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v2-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v2-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/special_tokens_map.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/config.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/tokenizer_config.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/merges.txt
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/vocab.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/tokenizer.json
sao10k-l3-rp-v2-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v1_reward/reward.tensors
Job sao10k-l3-rp-v2-1-v1-mkmlizer completed after 73.42s with status: succeeded
Stopping job with name sao10k-l3-rp-v2-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v2-1-v1
Waiting for inference service sao10k-l3-rp-v2-1-v1 to be ready
Inference service sao10k-l3-rp-v2-1-v1 ready after 40.205565452575684s
Pipeline stage ISVCDeployer completed in 47.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.069438934326172s
Received healthy response to inference request in 1.1555240154266357s
Received healthy response to inference request in 1.170849084854126s
Received healthy response to inference request in 1.1577482223510742s
Received healthy response to inference request in 1.1429896354675293s
5 requests
0 failed requests
5th percentile: 1.1454965114593505
10th percentile: 1.148003387451172
20th percentile: 1.1530171394348145
30th percentile: 1.1559688568115234
40th percentile: 1.156858539581299
50th percentile: 1.1577482223510742
60th percentile: 1.1629885673522948
70th percentile: 1.1682289123535157
80th percentile: 1.3505670547485353
90th percentile: 1.7100029945373536
95th percentile: 1.8897209644317625
99th percentile: 2.03349534034729
mean time: 1.3393099784851075
Pipeline stage StressChecker completed in 7.40s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
sao10k-l3-rp-v2-1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v2-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v2-1_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v2-1-v1 is running
Tearing down inference service sao10k-l3-rp-v2-1-v1
Toredown service sao10k-l3-rp-v2-1-v1
Pipeline stage ISVCDeleter completed in 3.61s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-1-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.85s
sao10k-l3-rp-v2-1_v1 status is now torndown due to DeploymentManager action