submission_id: saishf-sovlish-maid-l3-8b_v2
developer_uid: saishf
status: inactive
model_repo: saishf/SOVLish-Maid-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, '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': "{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}
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: 2024-05-10T03:02:30+00:00
model_name: saishf-sovlish-maid-l3-8b_v1
model_eval_status: success
double_thumbs_up: 416
thumbs_up: 544
thumbs_down: 287
num_battles: 27333
num_wins: 14103
celo_rating: 1176.69
entertaining: 7.0
stay_in_character: 8.48
user_preference: 7.16
safety_score: 0.89
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_v1
double_thumbs_up_ratio: 0.33360064153969526
feedback_count: 1247
ineligible_reason: None
language_model: saishf/SOVLish-Maid-L3-8B
model_score: 7.546666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4362469927826784
thumbs_down_ratio: 0.2301523656776263
thumbs_up_ratio: 0.7698476343223737
us_pacific_date: 2024-05-09
win_ratio: 0.5159697069476457
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-sovlish-maid-l3-8b-v2-mkmlizer
Waiting for job on saishf-sovlish-maid-l3-8b-v2-mkmlizer to finish
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ _____ __ __ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ /___/ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ Version: 0.8.10 ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ belonging to: ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ Chai Research Corp. ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ║ ║
saishf-sovlish-maid-l3-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-sovlish-maid-l3-8b-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.
saishf-sovlish-maid-l3-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Downloaded to shared memory in 67.210s
saishf-sovlish-maid-l3-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:02, 2.29s/it] Loading 0: 36%|███▌ | 105/291 [00:05<00:07, 24.74it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:02, 41.65it/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-v2-mkmlizer: quantized model in 20.777s
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Processed model saishf/SOVLish-Maid-L3-8B in 88.926s
saishf-sovlish-maid-l3-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-sovlish-maid-l3-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v2
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v2/config.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v2/special_tokens_map.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v2/tokenizer_config.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v2/tokenizer.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/saishf-sovlish-maid-l3-8b-v2/flywheel_model.0.safetensors
saishf-sovlish-maid-l3-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-sovlish-maid-l3-8b-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.
saishf-sovlish-maid-l3-8b-v2-mkmlizer: warnings.warn(
saishf-sovlish-maid-l3-8b-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.
saishf-sovlish-maid-l3-8b-v2-mkmlizer: warnings.warn(
saishf-sovlish-maid-l3-8b-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.
saishf-sovlish-maid-l3-8b-v2-mkmlizer: warnings.warn(
saishf-sovlish-maid-l3-8b-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()
saishf-sovlish-maid-l3-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Saving duration: 0.242s
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.479s
saishf-sovlish-maid-l3-8b-v2-mkmlizer: creating bucket guanaco-reward-models
saishf-sovlish-maid-l3-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-sovlish-maid-l3-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/config.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/special_tokens_map.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/merges.txt
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/vocab.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/tokenizer_config.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/tokenizer.json
saishf-sovlish-maid-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-sovlish-maid-l3-8b-v2_reward/reward.tensors
Job saishf-sovlish-maid-l3-8b-v2-mkmlizer completed after 124.45s with status: succeeded
Stopping job with name saishf-sovlish-maid-l3-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 129.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service saishf-sovlish-maid-l3-8b-v2
Waiting for inference service saishf-sovlish-maid-l3-8b-v2 to be ready
Inference service saishf-sovlish-maid-l3-8b-v2 ready after 40.23395013809204s
Pipeline stage ISVCDeployer completed in 47.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.152648448944092s
Received healthy response to inference request in 1.26084303855896s
Received healthy response to inference request in 1.2447888851165771s
Received healthy response to inference request in 1.2431657314300537s
Received healthy response to inference request in 1.2229523658752441s
5 requests
0 failed requests
5th percentile: 1.226995038986206
10th percentile: 1.231037712097168
20th percentile: 1.2391230583190918
30th percentile: 1.2434903621673583
40th percentile: 1.2441396236419677
50th percentile: 1.2447888851165771
60th percentile: 1.2512105464935304
70th percentile: 1.2576322078704834
80th percentile: 1.4392041206359865
90th percentile: 1.7959262847900392
95th percentile: 1.9742873668670653
99th percentile: 2.1169762325286863
mean time: 1.4248796939849853
Pipeline stage StressChecker completed in 7.74s
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
saishf-sovlish-maid-l3-8b_v2 status is now deployed due to DeploymentManager action
saishf-sovlish-maid-l3-8b_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics