submission_id: sao10k-l3-rp-v3-1_v1
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v3.1
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'], '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: 2024-06-04T06:10:02+00:00
model_name: V3-1-Test-1
model_eval_status: success
model_group: Sao10K/L3-RP-v3.1
num_battles: 32292
num_wins: 18301
celo_rating: 1214.72
propriety_score: 0.6353240152477764
propriety_total_count: 787.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: V3-1-Test-1
ineligible_reason: propriety_total_count < 800
language_model: Sao10K/L3-RP-v3.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-03
win_ratio: 0.5667347949956646
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v3-1-v1-mkmlizer
Waiting for job on sao10k-l3-rp-v3-1-v1-mkmlizer to finish
sao10k-l3-rp-v3-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ║ ║
sao10k-l3-rp-v3-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v3-1-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-v3-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v3-1-v1-mkmlizer: Downloaded to shared memory in 32.597s
sao10k-l3-rp-v3-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v3-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v3-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:25, 2.79s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.34it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:34, 7.69it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:18, 13.37it/s] Loading 0: 18%|█▊ | 51/291 [00:06<00:12, 19.09it/s] Loading 0: 21%|██ | 61/291 [00:06<00:11, 19.59it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:07, 29.87it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:05, 37.73it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 53.47it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 69.59it/s] Loading 0: 46%|████▋ | 135/291 [00:07<00:01, 81.81it/s] Loading 0: 52%|█████▏ | 150/291 [00:07<00:01, 93.96it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 60.78it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 66.38it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 81.24it/s] Loading 0: 70%|███████ | 205/291 [00:07<00:00, 87.82it/s] Loading 0: 76%|███████▌ | 221/291 [00:08<00:00, 99.31it/s] Loading 0: 81%|████████ | 236/291 [00:08<00:00, 110.59it/s] Loading 0: 86%|████████▌ | 249/291 [00:08<00:00, 109.84it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 120.39it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 62.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v3-1-v1-mkmlizer: quantized model in 21.729s
sao10k-l3-rp-v3-1-v1-mkmlizer: Processed model Sao10K/L3-RP-v3.1 in 55.621s
sao10k-l3-rp-v3-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v3-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v3-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v3-1-v1
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-1-v1/tokenizer_config.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-1-v1/special_tokens_map.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-1-v1/config.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-1-v1/tokenizer.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v3-1-v1/flywheel_model.0.safetensors
sao10k-l3-rp-v3-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v3-1-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-v3-1-v1-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-1-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-v3-1-v1-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-1-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-v3-1-v1-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-1-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-v3-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v3-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v3-1-v1-mkmlizer: Saving duration: 0.298s
sao10k-l3-rp-v3-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.048s
sao10k-l3-rp-v3-1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v3-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v3-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/special_tokens_map.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/config.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/merges.txt
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/vocab.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/tokenizer_config.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/tokenizer.json
sao10k-l3-rp-v3-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v3-1-v1_reward/reward.tensors
Job sao10k-l3-rp-v3-1-v1-mkmlizer completed after 82.93s with status: succeeded
Stopping job with name sao10k-l3-rp-v3-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v3-1-v1
Waiting for inference service sao10k-l3-rp-v3-1-v1 to be ready
Inference service sao10k-l3-rp-v3-1-v1 ready after 40.2431001663208s
Pipeline stage ISVCDeployer completed in 46.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1295971870422363s
Received healthy response to inference request in 1.3467233180999756s
Received healthy response to inference request in 1.2942113876342773s
Received healthy response to inference request in 1.249391794204712s
Received healthy response to inference request in 1.3877599239349365s
5 requests
0 failed requests
5th percentile: 1.258355712890625
10th percentile: 1.267319631576538
20th percentile: 1.2852474689483642
30th percentile: 1.304713773727417
40th percentile: 1.3257185459136962
50th percentile: 1.3467233180999756
60th percentile: 1.36313796043396
70th percentile: 1.3795526027679443
80th percentile: 1.5361273765563965
90th percentile: 1.8328622817993165
95th percentile: 1.9812297344207763
99th percentile: 2.099923696517944
mean time: 1.4815367221832276
Pipeline stage StressChecker completed in 8.23s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
sao10k-l3-rp-v3-1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v3-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics