sao10k-l3-rp-v5-1

developer_uid: sao10k

submission_id: sao10k-l3-rp-v5-1_v5

model_name: RP-v5-Expr2

model_group: Sao10K/L3-RP-v5.1

status: torndown

timestamp: 2024-07-09T12:12:49+00:00

num_battles: 30302

num_wins: 16111

celo_rating: 1220.18

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/L3-RP-v5.1

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: RP-v5-Expr2

is_internal_developer: False

language_model: Sao10K/L3-RP-v5.1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-09

win_ratio: 0.5316810771566233

generation_params: {'temperature': 1.4, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, '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 sao10k-l3-rp-v5-1-v5-mkmlizer
Waiting for job on sao10k-l3-rp-v5-1-v5-mkmlizer to finish
sao10k-l3-rp-v5-1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-1-v5-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v5-1-v5-mkmlizer: Downloaded to shared memory in 25.354s
sao10k-l3-rp-v5-1-v5-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-1-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:28,  2.38s/it]
Loading 0:   5%|▍         | 14/291 [00:04<01:11,  3.89it/s]
Loading 0:   9%|▉         | 27/291 [00:04<00:29,  8.90it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:15, 15.77it/s]
Loading 0:  19%|█▊        | 54/291 [00:05<00:09, 23.81it/s]
Loading 0:  23%|██▎       | 66/291 [00:05<00:08, 25.56it/s]
Loading 0:  26%|██▋       | 77/291 [00:05<00:06, 32.82it/s]
Loading 0:  31%|███       | 90/291 [00:05<00:04, 43.92it/s]
Loading 0:  35%|███▌      | 103/291 [00:05<00:03, 56.07it/s]
Loading 0:  39%|███▉      | 114/291 [00:06<00:02, 64.32it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:01, 81.73it/s]
Loading 0:  49%|████▉     | 143/291 [00:06<00:01, 89.59it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 100.86it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:01, 64.89it/s] 
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 77.60it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 82.50it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 98.80it/s]
Loading 0:  77%|███████▋  | 224/291 [00:07<00:00, 103.39it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 111.92it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 113.08it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 119.66it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 70.36it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v5-1-v5-mkmlizer: quantized model in 24.106s
sao10k-l3-rp-v5-1-v5-mkmlizer: Processed model Sao10K/L3-RP-v5.1 in 49.461s
sao10k-l3-rp-v5-1-v5-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v5
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v5/config.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v5/tokenizer_config.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v5/special_tokens_map.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v5/tokenizer.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-1-v5/flywheel_model.0.safetensors
sao10k-l3-rp-v5-1-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v5-1-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-rp-v5-1-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
sao10k-l3-rp-v5-1-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-v5-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-rp-v5-1-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-v5-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-v5-1-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-1-v5-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-v5-1-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v5-1-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v5-1-v5-mkmlizer: Saving duration: 0.397s
sao10k-l3-rp-v5-1-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.345s
sao10k-l3-rp-v5-1-v5-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v5-1-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v5-1-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/config.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/tokenizer_config.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/special_tokens_map.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/merges.txt
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/vocab.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/tokenizer.json
sao10k-l3-rp-v5-1-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v5-1-v5_reward/reward.tensors
Job sao10k-l3-rp-v5-1-v5-mkmlizer completed after 84.14s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-1-v5-mkmlizer
Pipeline stage MKMLizer completed in 85.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-1-v5
Waiting for inference service sao10k-l3-rp-v5-1-v5 to be ready
Inference service sao10k-l3-rp-v5-1-v5 ready after 61.49643397331238s
Pipeline stage ISVCDeployer completed in 68.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.142378807067871s
Received healthy response to inference request in 1.3257653713226318s
Received healthy response to inference request in 1.3443706035614014s
Received healthy response to inference request in 1.2937936782836914s
Received healthy response to inference request in 1.3405468463897705s
5 requests
0 failed requests
5th percentile: 1.3001880168914794
10th percentile: 1.3065823554992675
20th percentile: 1.3193710327148438
30th percentile: 1.3287216663360595
40th percentile: 1.334634256362915
50th percentile: 1.3405468463897705
60th percentile: 1.342076349258423
70th percentile: 1.3436058521270753
80th percentile: 1.5039722442626955
90th percentile: 1.8231755256652833
95th percentile: 1.982777166366577
99th percentile: 2.110458478927612
mean time: 1.4893710613250732
Pipeline stage StressChecker completed in 8.22s
sao10k-l3-rp-v5-1_v5 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-1_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-1_v5
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-1-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-1-v5/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-1-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-1-v5_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-1-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.57s
sao10k-l3-rp-v5-1_v5 status is now torndown due to DeploymentManager action