submission_id: sao10k-l3-rp-v3-3_v2
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v3.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, '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: 2024-06-05T04:51:54+00:00
model_name: V3-Expr2-Beta
model_eval_status: success
model_group: Sao10K/L3-RP-v3.3
num_battles: 12445
num_wins: 6960
celo_rating: 1220.51
safety_score: 0.97
propriety_score: 0.6501240694789082
propriety_total_count: 403.0
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-Beta
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: 0.5592607472880675
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v3-3-v2-mkmlizer
Waiting for job on sao10k-l3-rp-v3-3-v2-mkmlizer to finish
sao10k-l3-rp-v3-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v3-3-v2-mkmlizer: Downloaded to shared memory in 15.221s
sao10k-l3-rp-v3-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v3-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v3-3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:23, 1.95s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:33, 7.89it/s] Loading 0: 15%|█▌ | 45/291 [00:04<00:13, 18.06it/s] Loading 0: 21%|██▏ | 62/291 [00:04<00:09, 24.05it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 39.05it/s] Loading 0: 36%|███▌ | 105/291 [00:04<00:03, 53.97it/s] Loading 0: 45%|████▍ | 130/291 [00:04<00:02, 76.80it/s] Loading 0: 52%|█████▏ | 150/291 [00:04<00:01, 93.84it/s] Loading 0: 58%|█████▊ | 170/291 [00:05<00:01, 79.98it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 101.96it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 118.02it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 142.58it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 153.00it/s] Loading 0: 96%|█████████▌| 278/291 [00:05<00:00, 106.34it/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-v2-mkmlizer: quantized model in 16.553s
sao10k-l3-rp-v3-3-v2-mkmlizer: Processed model Sao10K/L3-RP-v3.3 in 32.672s
sao10k-l3-rp-v3-3-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v3-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v3-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v2
sao10k-l3-rp-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v2/config.json
sao10k-l3-rp-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v2/tokenizer_config.json
sao10k-l3-rp-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v2/special_tokens_map.json
sao10k-l3-rp-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v2/tokenizer.json
sao10k-l3-rp-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v2/flywheel_model.0.safetensors
sao10k-l3-rp-v3-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v3-3-v2-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-v2-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-v2-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-v2-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-v2-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-v2-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v3-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v3-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v2_reward/reward.tensors
Job sao10k-l3-rp-v3-3-v2-mkmlizer completed after 205.3s with status: succeeded
Stopping job with name sao10k-l3-rp-v3-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 209.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v3-3-v2
Waiting for inference service sao10k-l3-rp-v3-3-v2 to be ready
Inference service sao10k-l3-rp-v3-3-v2 ready after 40.21952223777771s
Pipeline stage ISVCDeployer completed in 47.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1765410900115967s
Received healthy response to inference request in 1.3205149173736572s
Received healthy response to inference request in 1.28910231590271s
Received healthy response to inference request in 1.2538814544677734s
Received healthy response to inference request in 1.342820644378662s
5 requests
0 failed requests
5th percentile: 1.2609256267547608
10th percentile: 1.267969799041748
20th percentile: 1.2820581436157226
30th percentile: 1.2953848361968994
40th percentile: 1.3079498767852784
50th percentile: 1.3205149173736572
60th percentile: 1.3294372081756591
70th percentile: 1.338359498977661
80th percentile: 1.5095647335052491
90th percentile: 1.843052911758423
95th percentile: 2.0097970008850097
99th percentile: 2.1431922721862793
mean time: 1.47657208442688
Pipeline stage StressChecker completed in 8.00s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
sao10k-l3-rp-v3-3_v2 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v3-3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics