submission_id: saishf-kitty-cat-sovl-8b_5545_v1
developer_uid: saishf
status: torndown
model_repo: saishf/Kitty-Cat-SOVL-8B-L3-V1
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': "<|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: 2024-05-13T12:28:45+00:00
model_name: saishf-kitty-cat-sovl-8b_5545_v1
model_eval_status: success
model_group: saishf/Kitty-Cat-SOVL-8B
num_battles: 20580
num_wins: 10515
celo_rating: 1176.83
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-kitty-cat-sovl-8b_5545_v1
ineligible_reason: propriety_total_count < 800
language_model: saishf/Kitty-Cat-SOVL-8B-L3-V1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-13
win_ratio: 0.510932944606414
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer
Waiting for job on saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer to finish
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ _____ __ __ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ /___/ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ Version: 0.8.10 ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ belonging to: ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ Chai Research Corp. ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ║ ║
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-kitty-cat-sovl-8b-5545-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.
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Downloaded to shared memory in 28.674s
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:41, 2.01s/it] Loading 0: 42%|████▏ | 122/291 [00:05<00:05, 30.65it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 60.64it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: quantized model in 17.503s
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Processed model saishf/Kitty-Cat-SOVL-8B-L3-V1 in 47.228s
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: creating bucket guanaco-mkml-models
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-kitty-cat-sovl-8b-5545-v1
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-kitty-cat-sovl-8b-5545-v1/config.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-kitty-cat-sovl-8b-5545-v1/special_tokens_map.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-kitty-cat-sovl-8b-5545-v1/tokenizer_config.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-kitty-cat-sovl-8b-5545-v1/tokenizer.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/saishf-kitty-cat-sovl-8b-5545-v1/flywheel_model.0.safetensors
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-kitty-cat-sovl-8b-5545-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.
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: warnings.warn(
saishf-kitty-cat-sovl-8b-5545-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.
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: warnings.warn(
saishf-kitty-cat-sovl-8b-5545-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.
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: warnings.warn(
saishf-kitty-cat-sovl-8b-5545-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()
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: return self.fget.__get__(instance, owner)()
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Saving duration: 0.242s
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.615s
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: creating bucket guanaco-reward-models
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/special_tokens_map.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/config.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/tokenizer_config.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/merges.txt
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/vocab.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/tokenizer.json
saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-kitty-cat-sovl-8b-5545-v1_reward/reward.tensors
Job saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer completed after 73.88s with status: succeeded
Stopping job with name saishf-kitty-cat-sovl-8b-5545-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service saishf-kitty-cat-sovl-8b-5545-v1
Waiting for inference service saishf-kitty-cat-sovl-8b-5545-v1 to be ready
Inference service saishf-kitty-cat-sovl-8b-5545-v1 ready after 30.195254802703857s
Pipeline stage ISVCDeployer completed in 37.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.165952682495117s
Received healthy response to inference request in 1.3329923152923584s
Received healthy response to inference request in 1.3147287368774414s
Received healthy response to inference request in 1.258986234664917s
Received healthy response to inference request in 1.344771385192871s
5 requests
0 failed requests
5th percentile: 1.270134735107422
10th percentile: 1.2812832355499268
20th percentile: 1.3035802364349365
30th percentile: 1.3183814525604247
40th percentile: 1.3256868839263916
50th percentile: 1.3329923152923584
60th percentile: 1.3377039432525635
70th percentile: 1.3424155712127686
80th percentile: 1.5090076446533205
90th percentile: 1.8374801635742188
95th percentile: 2.001716423034668
99th percentile: 2.1331054306030275
mean time: 1.483486270904541
Pipeline stage StressChecker completed in 8.03s
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
saishf-kitty-cat-sovl-8b_5545_v1 status is now deployed due to DeploymentManager action
saishf-kitty-cat-sovl-8b_5545_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of saishf-kitty-cat-sovl-8b_5545_v1
Running pipeline stage ISVCDeleter
Checking if service saishf-kitty-cat-sovl-8b-5545-v1 is running
Tearing down inference service saishf-kitty-cat-sovl-8b-5545-v1
Toredown service saishf-kitty-cat-sovl-8b-5545-v1
Pipeline stage ISVCDeleter completed in 6.75s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key saishf-kitty-cat-sovl-8b-5545-v1/config.json from bucket guanaco-mkml-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/config.json from bucket guanaco-reward-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key saishf-kitty-cat-sovl-8b-5545-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.13s
saishf-kitty-cat-sovl-8b_5545_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics