developer_uid: sao10k
submission_id: sao10k-l3-rp-v5-3_v1
model_name: rp-5-3-expr1
model_group: Sao10K/L3-RP-v5.3
status: torndown
timestamp: 2024-07-10T06:10:15+00:00
num_battles: 31019
num_wins: 16985
celo_rating: 1221.03
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-RP-v5.3
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-5-3-expr1
is_internal_developer: False
language_model: Sao10K/L3-RP-v5.3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-09
win_ratio: 0.5475676198459009
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|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 sao10k-l3-rp-v5-3-v1-mkmlizer
Waiting for job on sao10k-l3-rp-v5-3-v1-mkmlizer to finish
sao10k-l3-rp-v5-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-3-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v5-3-v1-mkmlizer: Downloaded to shared memory in 71.008s
sao10k-l3-rp-v5-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:17,  2.76s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:22,  3.38it/s]
Loading 0:  10%|▉         | 29/291 [00:05<00:30,  8.47it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:18, 13.73it/s]
Loading 0:  20%|█▉        | 57/291 [00:05<00:10, 22.98it/s]
Loading 0:  24%|██▍       | 70/291 [00:06<00:09, 24.15it/s]
Loading 0:  29%|██▉       | 85/291 [00:06<00:05, 34.47it/s]
Loading 0:  33%|███▎      | 97/291 [00:06<00:04, 43.09it/s]
Loading 0:  38%|███▊      | 112/291 [00:06<00:03, 56.89it/s]
Loading 0:  43%|████▎     | 125/291 [00:06<00:02, 67.50it/s]
Loading 0:  48%|████▊     | 139/291 [00:06<00:01, 80.40it/s]
Loading 0:  52%|█████▏    | 152/291 [00:07<00:01, 87.79it/s]
Loading 0:  57%|█████▋    | 166/291 [00:07<00:02, 54.92it/s]
Loading 0:  61%|██████    | 177/291 [00:07<00:01, 62.32it/s]
Loading 0:  66%|██████▋   | 193/291 [00:07<00:01, 78.96it/s]
Loading 0:  70%|███████   | 205/291 [00:07<00:00, 86.27it/s]
Loading 0:  76%|███████▌  | 220/291 [00:07<00:00, 99.50it/s]
Loading 0:  80%|████████  | 233/291 [00:08<00:00, 102.93it/s]
Loading 0:  85%|████████▍ | 247/291 [00:08<00:00, 111.90it/s]
Loading 0:  89%|████████▉ | 260/291 [00:08<00:00, 114.68it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 63.90it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:08<00:00, 71.31it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v5-3-v1-mkmlizer: quantized model in 28.702s
sao10k-l3-rp-v5-3-v1-mkmlizer: Processed model Sao10K/L3-RP-v5.3 in 99.711s
sao10k-l3-rp-v5-3-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-3-v1
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-3-v1/config.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-3-v1/special_tokens_map.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-3-v1/tokenizer_config.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-3-v1/tokenizer.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-3-v1/flywheel_model.0.safetensors
sao10k-l3-rp-v5-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v5-3-v1-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-v5-3-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-3-v1-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-v5-3-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-3-v1-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-v5-3-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-3-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-v5-3-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-3-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-v5-3-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v5-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v5-3-v1-mkmlizer: Saving duration: 0.515s
sao10k-l3-rp-v5-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.005s
sao10k-l3-rp-v5-3-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v5-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v5-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/config.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/special_tokens_map.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/tokenizer_config.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/merges.txt
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/vocab.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/tokenizer.json
sao10k-l3-rp-v5-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v5-3-v1_reward/reward.tensors
Job sao10k-l3-rp-v5-3-v1-mkmlizer completed after 124.45s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-3-v1
Waiting for inference service sao10k-l3-rp-v5-3-v1 to be ready
Inference service sao10k-l3-rp-v5-3-v1 ready after 40.17597007751465s
Pipeline stage ISVCDeployer completed in 47.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.048448324203491s
Received healthy response to inference request in 1.335026502609253s
Received healthy response to inference request in 1.2987184524536133s
Received healthy response to inference request in 1.2821903228759766s
Received healthy response to inference request in 1.334845781326294s
5 requests
0 failed requests
5th percentile: 1.2854959487915039
10th percentile: 1.2888015747070312
20th percentile: 1.295412826538086
30th percentile: 1.3059439182281494
40th percentile: 1.3203948497772218
50th percentile: 1.334845781326294
60th percentile: 1.3349180698394776
70th percentile: 1.3349903583526612
80th percentile: 1.4777108669281007
90th percentile: 1.763079595565796
95th percentile: 1.9057639598846434
99th percentile: 2.0199114513397216
mean time: 1.4598458766937257
Pipeline stage StressChecker completed in 7.97s
sao10k-l3-rp-v5-3_v1 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-3_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-3-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.59s
sao10k-l3-rp-v5-3_v1 status is now torndown due to DeploymentManager action