submission_id: sao10k-l3-rp-v2-1_v2
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v2.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.8, 'min_p': 0.05, 'top_k': 50, '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': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.', 'prompt_template': '\n{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: 2024-05-19T11:22:12+00:00
model_name: L3-RP-v2-Test1
model_eval_status: success
model_group: Sao10K/L3-RP-v2.1
num_battles: 21813
num_wins: 11772
celo_rating: 1202.17
safety_score: 0.97
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: L3-RP-v2-Test1
ineligible_reason: propriety_total_count < 5000
language_model: Sao10K/L3-RP-v2.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-19
win_ratio: 0.5396781735662219
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v2-1-v2-mkmlizer
Waiting for job on sao10k-l3-rp-v2-1-v2-mkmlizer to finish
sao10k-l3-rp-v2-1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ║ ║
sao10k-l3-rp-v2-1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v2-1-v2-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-v2-1-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v2-1-v2-mkmlizer: Downloaded to shared memory in 15.825s
sao10k-l3-rp-v2-1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v2-1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v2-1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:33, 1.98s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:36, 7.42it/s] Loading 0: 14%|█▍ | 41/291 [00:04<00:15, 16.03it/s] Loading 0: 21%|██ | 60/291 [00:04<00:10, 22.79it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 38.59it/s] Loading 0: 36%|███▌ | 104/291 [00:04<00:03, 52.28it/s] Loading 0: 43%|████▎ | 124/291 [00:04<00:02, 69.22it/s] Loading 0: 51%|█████ | 148/291 [00:04<00:01, 92.53it/s] Loading 0: 58%|█████▊ | 168/291 [00:05<00:01, 75.80it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 99.50it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 114.23it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 137.41it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 148.41it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 94.68it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v2-1-v2-mkmlizer: quantized model in 17.293s
sao10k-l3-rp-v2-1-v2-mkmlizer: Processed model Sao10K/L3-RP-v2.1 in 34.143s
sao10k-l3-rp-v2-1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v2-1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v2
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v2/config.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v2/tokenizer_config.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v2/special_tokens_map.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v2/tokenizer.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v2-1-v2/flywheel_model.0.safetensors
sao10k-l3-rp-v2-1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v2-1-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-v2-1-v2-mkmlizer: warnings.warn(
sao10k-l3-rp-v2-1-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-v2-1-v2-mkmlizer: warnings.warn(
sao10k-l3-rp-v2-1-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-v2-1-v2-mkmlizer: warnings.warn(
sao10k-l3-rp-v2-1-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-v2-1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v2-1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v2-1-v2-mkmlizer: Saving duration: 0.225s
sao10k-l3-rp-v2-1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.226s
sao10k-l3-rp-v2-1-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v2-1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v2-1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/config.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/tokenizer_config.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/special_tokens_map.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/merges.txt
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/vocab.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/tokenizer.json
sao10k-l3-rp-v2-1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v2-1-v2_reward/reward.tensors
Job sao10k-l3-rp-v2-1-v2-mkmlizer completed after 62.46s with status: succeeded
Stopping job with name sao10k-l3-rp-v2-1-v2-mkmlizer
Pipeline stage MKMLizer completed in 64.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v2-1-v2
Waiting for inference service sao10k-l3-rp-v2-1-v2 to be ready
Inference service sao10k-l3-rp-v2-1-v2 ready after 40.2092399597168s
Pipeline stage ISVCDeployer completed in 46.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1207332611083984s
Received healthy response to inference request in 1.1772739887237549s
Received healthy response to inference request in 1.1302900314331055s
Received healthy response to inference request in 1.1824758052825928s
Received healthy response to inference request in 1.1587510108947754s
5 requests
0 failed requests
5th percentile: 1.1359822273254394
10th percentile: 1.1416744232177733
20th percentile: 1.1530588150024415
30th percentile: 1.1624556064605713
40th percentile: 1.169864797592163
50th percentile: 1.1772739887237549
60th percentile: 1.17935471534729
70th percentile: 1.1814354419708253
80th percentile: 1.370127296447754
90th percentile: 1.7454302787780762
95th percentile: 1.9330817699432372
99th percentile: 2.083202962875366
mean time: 1.3539048194885255
Pipeline stage StressChecker completed in 7.38s
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-v2-1_v2 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v2-1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics