submission_id: sao10k-l3-rp-v4-2_v4
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v4.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.12, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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: {'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}
timestamp: 2024-06-10T09:35:25+00:00
model_name: V4-Expr1-Beta
model_eval_status: success
model_group: Sao10K/L3-RP-v4.2
num_battles: 12446
num_wins: 7150
celo_rating: 1233.04
propriety_score: 0.6663101604278074
propriety_total_count: 935.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: V4-Expr1-Beta
ineligible_reason: propriety_total_count < 5000
language_model: Sao10K/L3-RP-v4.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5744817612084204
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v4-2-v4-mkmlizer
Waiting for job on sao10k-l3-rp-v4-2-v4-mkmlizer to finish
sao10k-l3-rp-v4-2-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ║ ║
sao10k-l3-rp-v4-2-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v4-2-v4-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-v4-2-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v4-2-v4-mkmlizer: Downloaded to shared memory in 31.566s
sao10k-l3-rp-v4-2-v4-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v4-2-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v4-2-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:56, 2.27s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.38it/s] Loading 0: 11%|█ | 32/291 [00:04<00:22, 11.28it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.57it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.27it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.32it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.51it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 62.82it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 78.64it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 94.31it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 70.98it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 86.02it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 100.33it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 113.50it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 125.09it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 134.68it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 86.18it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 93.64it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v4-2-v4-mkmlizer: quantized model in 23.357s
sao10k-l3-rp-v4-2-v4-mkmlizer: Processed model Sao10K/L3-RP-v4.2 in 57.628s
sao10k-l3-rp-v4-2-v4-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v4-2-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v4-2-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v4-2-v4
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-2-v4/tokenizer_config.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-2-v4/config.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-2-v4/special_tokens_map.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-2-v4/tokenizer.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v4-2-v4/flywheel_model.0.safetensors
sao10k-l3-rp-v4-2-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v4-2-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-rp-v4-2-v4-mkmlizer: warnings.warn(
sao10k-l3-rp-v4-2-v4-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-v4-2-v4-mkmlizer: warnings.warn(
sao10k-l3-rp-v4-2-v4-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-v4-2-v4-mkmlizer: warnings.warn(
sao10k-l3-rp-v4-2-v4-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-v4-2-v4-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v4-2-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v4-2-v4-mkmlizer: Saving duration: 0.426s
sao10k-l3-rp-v4-2-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.322s
sao10k-l3-rp-v4-2-v4-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v4-2-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v4-2-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/tokenizer_config.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/config.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/merges.txt
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/special_tokens_map.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/vocab.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/tokenizer.json
sao10k-l3-rp-v4-2-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v4-2-v4_reward/reward.tensors
Job sao10k-l3-rp-v4-2-v4-mkmlizer completed after 83.03s with status: succeeded
Stopping job with name sao10k-l3-rp-v4-2-v4-mkmlizer
Pipeline stage MKMLizer completed in 86.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v4-2-v4
Waiting for inference service sao10k-l3-rp-v4-2-v4 to be ready
Inference service sao10k-l3-rp-v4-2-v4 ready after 50.24802613258362s
Pipeline stage ISVCDeployer completed in 57.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 19.589051246643066s
Received healthy response to inference request in 1.3640918731689453s
Received healthy response to inference request in 1.330610752105713s
Received healthy response to inference request in 1.3455805778503418s
Received healthy response to inference request in 1.3651385307312012s
5 requests
0 failed requests
5th percentile: 1.3336047172546386
10th percentile: 1.3365986824035645
20th percentile: 1.342586612701416
30th percentile: 1.3492828369140626
40th percentile: 1.356687355041504
50th percentile: 1.3640918731689453
60th percentile: 1.3645105361938477
70th percentile: 1.36492919921875
80th percentile: 5.009921073913578
90th percentile: 12.299486160278322
95th percentile: 15.94426870346069
99th percentile: 18.86009473800659
mean time: 4.998894596099854
Pipeline stage StressChecker completed in 25.66s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
sao10k-l3-rp-v4-2_v4 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v4-2_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics