developer_uid: shiroe40
submission_id: cycy233-misllm-v3-3_v2
model_name: basei
model_group: cycy233/misllm_v3.3
status: torndown
timestamp: 2024-05-18T00:16:52+00:00
num_battles: 25700
num_wins: 12221
celo_rating: 1155.58
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v3.3
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: basei
is_internal_developer: False
language_model: cycy233/misllm_v3.3
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-17
win_ratio: 0.4755252918287938
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': False}
model_eval_status: success
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v3-3-v2-mkmlizer
Waiting for job on cycy233-misllm-v3-3-v2-mkmlizer to finish
cycy233-misllm-v3-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v3-3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ /___/ ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ belonging to: ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v3-3-v2-mkmlizer: ║ ║
cycy233-misllm-v3-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v3-3-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.
cycy233-misllm-v3-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v3-3-v2-mkmlizer: Downloaded to shared memory in 13.704s
cycy233-misllm-v3-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v3-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v3-3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 82.15it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 83.05it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 73.71it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v3-3-v2-mkmlizer: quantized model in 11.919s
cycy233-misllm-v3-3-v2-mkmlizer: Processed model cycy233/misllm_v3.3 in 26.647s
cycy233-misllm-v3-3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v3-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v3-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2
cycy233-misllm-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2/config.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2/tokenizer.model
cycy233-misllm-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2/tokenizer_config.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2/tokenizer.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2/special_tokens_map.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v3-3-v2/flywheel_model.0.safetensors
cycy233-misllm-v3-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v3-3-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.
cycy233-misllm-v3-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v3-3-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.
cycy233-misllm-v3-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v3-3-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.
cycy233-misllm-v3-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v3-3-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()
cycy233-misllm-v3-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v3-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v3-3-v2-mkmlizer: Saving duration: 0.263s
cycy233-misllm-v3-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.345s
cycy233-misllm-v3-3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v3-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v3-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/tokenizer_config.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/special_tokens_map.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/config.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/merges.txt
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/vocab.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/tokenizer.json
cycy233-misllm-v3-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v3-3-v2_reward/reward.tensors
Job cycy233-misllm-v3-3-v2-mkmlizer completed after 52.7s with status: succeeded
Stopping job with name cycy233-misllm-v3-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 57.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v3-3-v2
Waiting for inference service cycy233-misllm-v3-3-v2 to be ready
Inference service cycy233-misllm-v3-3-v2 ready after 30.1807062625885s
Pipeline stage ISVCDeployer completed in 38.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.975224256515503s
Received healthy response to inference request in 1.1805179119110107s
Received healthy response to inference request in 1.1632282733917236s
Received healthy response to inference request in 1.172346591949463s
Received healthy response to inference request in 0.9658520221710205s
5 requests
0 failed requests
5th percentile: 1.0053272724151612
10th percentile: 1.0448025226593018
20th percentile: 1.123753023147583
30th percentile: 1.1650519371032715
40th percentile: 1.1686992645263672
50th percentile: 1.172346591949463
60th percentile: 1.175615119934082
70th percentile: 1.1788836479187013
80th percentile: 1.3394591808319094
90th percentile: 1.657341718673706
95th percentile: 1.8162829875946043
99th percentile: 1.943436002731323
mean time: 1.2914338111877441
Pipeline stage StressChecker completed in 7.13s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
cycy233-misllm-v3-3_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v3-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v3-3_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v3-3-v2 is running
Tearing down inference service cycy233-misllm-v3-3-v2
Toredown service cycy233-misllm-v3-3-v2
Pipeline stage ISVCDeleter completed in 5.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v3-3-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-3-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v3-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.62s
cycy233-misllm-v3-3_v2 status is now torndown due to DeploymentManager action