submission_id: saishf-sovlish-maid-l3-8b_v3
developer_uid: saishf
status: inactive
model_repo: saishf/SOVLish-Maid-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': '\n\nExample conversation:\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", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-16T14:51:09+00:00
model_name: saishf-sovlish-maid-l3-8b_v3
model_eval_status: success
model_group: saishf/SOVLish-Maid-L3-8
num_battles: 10663
num_wins: 5431
celo_rating: 1181.17
safety_score: 0.89
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: saishf-sovlish-maid-l3-8b_v3
ineligible_reason: propriety_total_count < 5000
language_model: saishf/SOVLish-Maid-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-16
win_ratio: 0.5093313326455969
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-sovlish-maid-l3-8b-v3-mkmlizer
Waiting for job on saishf-sovlish-maid-l3-8b-v3-mkmlizer to finish
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ _____ __ __ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ /___/ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ Version: 0.8.14 ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ https://mk1.ai ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ belonging to: ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ Chai Research Corp. ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-sovlish-maid-l3-8b-v3-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.
saishf-sovlish-maid-l3-8b-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Downloaded to shared memory in 29.842s
saishf-sovlish-maid-l3-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:45, 2.24s/it] Loading 0: 7%|▋ | 20/291 [00:04<00:45, 6.01it/s] Loading 0: 14%|█▍ | 41/291 [00:04<00:19, 13.08it/s] Loading 0: 21%|██ | 60/291 [00:05<00:10, 22.12it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 32.84it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 45.61it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 60.38it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 55.90it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 73.53it/s] Loading 0: 60%|██████ | 175/291 [00:05<00:01, 99.32it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:00, 115.12it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:00, 89.21it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 105.75it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 131.58it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 141.36it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
saishf-sovlish-maid-l3-8b-v3-mkmlizer: quantized model in 18.333s
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Processed model saishf/SOVLish-Maid-L3-8B in 49.323s
saishf-sovlish-maid-l3-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-sovlish-maid-l3-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v3
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v3/special_tokens_map.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v3/tokenizer_config.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v3/config.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v3/tokenizer.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v3/flywheel_model.0.safetensors
saishf-sovlish-maid-l3-8b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-sovlish-maid-l3-8b-v3-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.
saishf-sovlish-maid-l3-8b-v3-mkmlizer: warnings.warn(
saishf-sovlish-maid-l3-8b-v3-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.
saishf-sovlish-maid-l3-8b-v3-mkmlizer: warnings.warn(
saishf-sovlish-maid-l3-8b-v3-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.
saishf-sovlish-maid-l3-8b-v3-mkmlizer: warnings.warn(
saishf-sovlish-maid-l3-8b-v3-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()
saishf-sovlish-maid-l3-8b-v3-mkmlizer: return self.fget.__get__(instance, owner)()
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Saving duration: 0.247s
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.308s
saishf-sovlish-maid-l3-8b-v3-mkmlizer: creating bucket guanaco-reward-models
saishf-sovlish-maid-l3-8b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-sovlish-maid-l3-8b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/special_tokens_map.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/merges.txt
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/vocab.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/tokenizer_config.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/config.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/tokenizer.json
saishf-sovlish-maid-l3-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v3_reward/reward.tensors
Job saishf-sovlish-maid-l3-8b-v3-mkmlizer completed after 73.02s with status: succeeded
Stopping job with name saishf-sovlish-maid-l3-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service saishf-sovlish-maid-l3-8b-v3
Waiting for inference service saishf-sovlish-maid-l3-8b-v3 to be ready
Inference service saishf-sovlish-maid-l3-8b-v3 ready after 40.257883071899414s
Pipeline stage ISVCDeployer completed in 46.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3187551498413086s
Received healthy response to inference request in 1.337242603302002s
Received healthy response to inference request in 1.2974064350128174s
Received healthy response to inference request in 1.2632980346679688s
Received healthy response to inference request in 1.351560354232788s
5 requests
0 failed requests
5th percentile: 1.2701197147369385
10th percentile: 1.2769413948059083
20th percentile: 1.2905847549438476
30th percentile: 1.3053736686706543
40th percentile: 1.3213081359863281
50th percentile: 1.337242603302002
60th percentile: 1.3429697036743165
70th percentile: 1.348696804046631
80th percentile: 1.5449993133544924
90th percentile: 1.9318772315979005
95th percentile: 2.1253161907196043
99th percentile: 2.280067358016968
mean time: 1.513652515411377
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
saishf-sovlish-maid-l3-8b_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
saishf-sovlish-maid-l3-8b_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics