developer_uid: shiroe40
submission_id: cycy233-misllm-v3-1_v1
model_name: base
model_group: cycy233/misllm_v3.1
status: torndown
timestamp: 2024-05-16T15:50:31+00:00
num_battles: 11522
num_wins: 5266
celo_rating: 1140.07
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v3.1
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7241732096.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: base
is_internal_developer: False
language_model: cycy233/misllm_v3.1
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-16
win_ratio: 0.4570387085575421
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': 4, '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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v3-1-v1-mkmlizer
Waiting for job on cycy233-misllm-v3-1-v1-mkmlizer to finish
cycy233-misllm-v3-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v3-1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v3-1-v1-mkmlizer: ║ ║
cycy233-misllm-v3-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v3-1-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.
cycy233-misllm-v3-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v3-1-v1-mkmlizer: Downloaded to shared memory in 36.504s
cycy233-misllm-v3-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v3-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v3-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:01, 96.68it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 107.48it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 89.04it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v3-1-v1-mkmlizer: quantized model in 11.313s
cycy233-misllm-v3-1-v1-mkmlizer: Processed model cycy233/misllm_v3.1 in 48.752s
cycy233-misllm-v3-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v3-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1
cycy233-misllm-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1/config.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1/special_tokens_map.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1/tokenizer_config.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1/tokenizer.model
cycy233-misllm-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1/tokenizer.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v3-1-v1/flywheel_model.0.safetensors
cycy233-misllm-v3-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v3-1-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.
cycy233-misllm-v3-1-v1-mkmlizer: warnings.warn(
cycy233-misllm-v3-1-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.
cycy233-misllm-v3-1-v1-mkmlizer: warnings.warn(
cycy233-misllm-v3-1-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.
cycy233-misllm-v3-1-v1-mkmlizer: warnings.warn(
cycy233-misllm-v3-1-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()
cycy233-misllm-v3-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v3-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v3-1-v1-mkmlizer: Saving duration: 0.294s
cycy233-misllm-v3-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.326s
cycy233-misllm-v3-1-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v3-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v3-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/config.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/special_tokens_map.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/tokenizer_config.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/merges.txt
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/vocab.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/tokenizer.json
cycy233-misllm-v3-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v3-1-v1_reward/reward.tensors
Job cycy233-misllm-v3-1-v1-mkmlizer completed after 114.79s with status: succeeded
Stopping job with name cycy233-misllm-v3-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v3-1-v1
Waiting for inference service cycy233-misllm-v3-1-v1 to be ready
Inference service cycy233-misllm-v3-1-v1 ready after 30.216310024261475s
Pipeline stage ISVCDeployer completed in 35.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9414451122283936s
Received healthy response to inference request in 0.9823250770568848s
Received healthy response to inference request in 1.069629192352295s
Received healthy response to inference request in 1.0488064289093018s
Received healthy response to inference request in 1.1014089584350586s
5 requests
0 failed requests
5th percentile: 0.9956213474273682
10th percentile: 1.0089176177978516
20th percentile: 1.0355101585388184
30th percentile: 1.0529709815979005
40th percentile: 1.0613000869750977
50th percentile: 1.069629192352295
60th percentile: 1.0823410987854003
70th percentile: 1.095053005218506
80th percentile: 1.2694161891937257
90th percentile: 1.6054306507110596
95th percentile: 1.7734378814697265
99th percentile: 1.9078436660766602
mean time: 1.2287229537963866
Pipeline stage StressChecker completed in 7.76s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.08s
cycy233-misllm-v3-1_v1 status is now deployed due to DeploymentManager action
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
cycy233-misllm-v3-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v3-1_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v3-1-v1 is running
Tearing down inference service cycy233-misllm-v3-1-v1
Toredown service cycy233-misllm-v3-1-v1
Pipeline stage ISVCDeleter completed in 3.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v3-1-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-1-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v3-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v3-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v3-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.87s
cycy233-misllm-v3-1_v1 status is now torndown due to DeploymentManager action