submission_id: sao10k-l3-rp-v3-3_v1
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v3.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.12, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 60, '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: 2024-06-04T17:06:18+00:00
model_name: V3-Expr2-Alpha
model_eval_status: success
model_group: Sao10K/L3-RP-v3.3
num_battles: 19318
num_wins: 10496
celo_rating: 1213.52
safety_score: 0.97
propriety_score: 0.6605504587155964
propriety_total_count: 436.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: V3-Expr2-Alpha
ineligible_reason: propriety_total_count < 5000
language_model: Sao10K/L3-RP-v3.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5433274666114505
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v3-3-v1-mkmlizer
Waiting for job on sao10k-l3-rp-v3-3-v1-mkmlizer to finish
sao10k-l3-rp-v3-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v3-3-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-v3-3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v3-3-v1-mkmlizer: Downloaded to shared memory in 32.804s
sao10k-l3-rp-v3-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v3-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v3-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:02, 2.29s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.34it/s] Loading 0: 11%|█ | 32/291 [00:04<00:23, 11.18it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.44it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.22it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.41it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.88it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 63.54it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 79.81it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 95.85it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.81it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 90.44it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 105.38it/s] Loading 0: 75%|███████▍ | 217/291 [00:06<00:00, 114.37it/s] Loading 0: 80%|███████▉ | 232/291 [00:06<00:00, 121.29it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 130.06it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 85.31it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 100.07it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v3-3-v1-mkmlizer: quantized model in 23.480s
sao10k-l3-rp-v3-3-v1-mkmlizer: Processed model Sao10K/L3-RP-v3.3 in 58.883s
sao10k-l3-rp-v3-3-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v3-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v3-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v1
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v1/config.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v1/special_tokens_map.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v1/tokenizer_config.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v1/tokenizer.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v1/flywheel_model.0.safetensors
sao10k-l3-rp-v3-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v3-3-v1-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-v3-3-v1-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-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-v3-3-v1-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-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-v3-3-v1-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-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-v3-3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v3-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v3-3-v1-mkmlizer: Saving duration: 0.397s
sao10k-l3-rp-v3-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.279s
sao10k-l3-rp-v3-3-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v3-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v3-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/config.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/special_tokens_map.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/tokenizer_config.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/vocab.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/merges.txt
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/tokenizer.json
sao10k-l3-rp-v3-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v1_reward/reward.tensors
Job sao10k-l3-rp-v3-3-v1-mkmlizer completed after 93.54s with status: succeeded
Stopping job with name sao10k-l3-rp-v3-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v3-3-v1
Waiting for inference service sao10k-l3-rp-v3-3-v1 to be ready
Inference service sao10k-l3-rp-v3-3-v1 ready after 30.28642249107361s
Pipeline stage ISVCDeployer completed in 37.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1189887523651123s
Received healthy response to inference request in 1.313499927520752s
Received healthy response to inference request in 1.294382095336914s
Received healthy response to inference request in 1.2592389583587646s
Received healthy response to inference request in 1.336704969406128s
5 requests
0 failed requests
5th percentile: 1.2662675857543946
10th percentile: 1.2732962131500245
20th percentile: 1.2873534679412841
30th percentile: 1.2982056617736817
40th percentile: 1.3058527946472167
50th percentile: 1.313499927520752
60th percentile: 1.3227819442749023
70th percentile: 1.3320639610290528
80th percentile: 1.4931617259979248
90th percentile: 1.8060752391815187
95th percentile: 1.9625319957733154
99th percentile: 2.087697401046753
mean time: 1.4645629405975342
Pipeline stage StressChecker completed in 8.30s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
sao10k-l3-rp-v3-3_v1 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v3-3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics