submission_id: cycy233-misllm-v4-3_v3
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v4.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, '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': True}
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': True}
timestamp: 2024-05-20T16:22:01+00:00
model_name: rolej
model_eval_status: success
model_group: cycy233/misllm_v4.3
num_battles: 17515
num_wins: 8865
celo_rating: 1178.05
safety_score: 0.93
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rolej
ineligible_reason: propriety_total_count < 5000
language_model: cycy233/misllm_v4.3
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-20
win_ratio: 0.5061375963459892
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v4-3-v3-mkmlizer
Waiting for job on cycy233-misllm-v4-3-v3-mkmlizer to finish
cycy233-misllm-v4-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v4-3-v3-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ /___/ ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ belonging to: ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v4-3-v3-mkmlizer: ║ ║
cycy233-misllm-v4-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v4-3-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.
cycy233-misllm-v4-3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v4-3-v3-mkmlizer: Downloaded to shared memory in 21.389s
cycy233-misllm-v4-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v4-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v4-3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 107.81it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 123.50it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 97.35it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v4-3-v3-mkmlizer: quantized model in 10.240s
cycy233-misllm-v4-3-v3-mkmlizer: Processed model cycy233/misllm_v4.3 in 32.512s
cycy233-misllm-v4-3-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v4-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v4-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3
cycy233-misllm-v4-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3/config.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3/tokenizer_config.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3/tokenizer.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3/special_tokens_map.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3/tokenizer.model
cycy233-misllm-v4-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v4-3-v3/flywheel_model.0.safetensors
cycy233-misllm-v4-3-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.
cycy233-misllm-v4-3-v3-mkmlizer: warnings.warn(
cycy233-misllm-v4-3-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()
cycy233-misllm-v4-3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v4-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v4-3-v3-mkmlizer: Saving duration: 0.220s
cycy233-misllm-v4-3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.633s
cycy233-misllm-v4-3-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v4-3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v4-3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/config.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/special_tokens_map.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/tokenizer_config.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/merges.txt
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/vocab.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/tokenizer.json
cycy233-misllm-v4-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v4-3-v3_reward/reward.tensors
Job cycy233-misllm-v4-3-v3-mkmlizer completed after 52.42s with status: succeeded
Stopping job with name cycy233-misllm-v4-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 56.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v4-3-v3
Waiting for inference service cycy233-misllm-v4-3-v3 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service cycy233-misllm-v4-3-v3 ready after 30.182430505752563s
Pipeline stage ISVCDeployer completed in 38.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0846283435821533s
Received healthy response to inference request in 0.926255464553833s
Received healthy response to inference request in 1.0905170440673828s
Received healthy response to inference request in 0.878223180770874s
Received healthy response to inference request in 1.1689448356628418s
5 requests
0 failed requests
5th percentile: 0.8878296375274658
10th percentile: 0.8974360942840576
20th percentile: 0.9166490077972412
30th percentile: 0.959107780456543
40th percentile: 1.0248124122619628
50th percentile: 1.0905170440673828
60th percentile: 1.1218881607055664
70th percentile: 1.15325927734375
80th percentile: 1.3520815372467043
90th percentile: 1.7183549404144287
95th percentile: 1.9014916419982908
99th percentile: 2.048001003265381
mean time: 1.229713773727417
Pipeline stage StressChecker completed in 6.77s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v4-3_v3 status is now deployed due to DeploymentManager action
cycy233-misllm-v4-3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics