developer_uid: shiroe40
submission_id: cycy233-misllm-v9-1-1_v1
model_name: base
model_group: cycy233/misllm_v9.1.1
status: torndown
timestamp: 2024-06-20T02:34:07+00:00
num_battles: 19143
num_wins: 9566
celo_rating: 1192.15
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v9.1.1
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
is_internal_developer: False
language_model: cycy233/misllm_v9.1.1
model_size: 7B
ranking_group: single
us_pacific_date: 2024-06-19
win_ratio: 0.4997126887112783
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': True}
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': True, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v9-1-1-v1-mkmlizer
Waiting for job on cycy233-misllm-v9-1-1-v1-mkmlizer to finish
cycy233-misllm-v9-1-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ║ ║
cycy233-misllm-v9-1-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v9-1-1-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-v9-1-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v9-1-1-v1-mkmlizer: Downloaded to shared memory in 31.886s
cycy233-misllm-v9-1-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v9-1-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v9-1-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 94.41it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 104.27it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 81.74it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v9-1-1-v1-mkmlizer: quantized model in 16.071s
cycy233-misllm-v9-1-1-v1-mkmlizer: Processed model cycy233/misllm_v9.1.1 in 50.394s
cycy233-misllm-v9-1-1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v9-1-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v9-1-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v9-1-1-v1
cycy233-misllm-v9-1-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v9-1-1-v1/config.json
cycy233-misllm-v9-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v9-1-1-v1/tokenizer_config.json
cycy233-misllm-v9-1-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v9-1-1-v1/special_tokens_map.json
cycy233-misllm-v9-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v9-1-1-v1/tokenizer.model
cycy233-misllm-v9-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v9-1-1-v1/tokenizer.json
cycy233-misllm-v9-1-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v9-1-1-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-v9-1-1-v1-mkmlizer: warnings.warn(
cycy233-misllm-v9-1-1-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-v9-1-1-v1-mkmlizer: warnings.warn(
cycy233-misllm-v9-1-1-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-v9-1-1-v1-mkmlizer: warnings.warn(
cycy233-misllm-v9-1-1-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-v9-1-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v9-1-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v9-1-1-v1-mkmlizer: Saving duration: 0.671s
cycy233-misllm-v9-1-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.601s
cycy233-misllm-v9-1-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v9-1-1-v1_reward/reward.tensors
Job cycy233-misllm-v9-1-1-v1-mkmlizer completed after 82.73s with status: succeeded
Stopping job with name cycy233-misllm-v9-1-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v9-1-1-v1
Waiting for inference service cycy233-misllm-v9-1-1-v1 to be ready
Inference service cycy233-misllm-v9-1-1-v1 ready after 40.2714524269104s
Pipeline stage ISVCDeployer completed in 47.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1505303382873535s
Received healthy response to inference request in 1.0399267673492432s
Received healthy response to inference request in 1.1576120853424072s
Received healthy response to inference request in 0.929861307144165s
Received healthy response to inference request in 0.8947417736053467s
5 requests
0 failed requests
5th percentile: 0.9017656803131103
10th percentile: 0.908789587020874
20th percentile: 0.9228374004364014
30th percentile: 0.9518743991851807
40th percentile: 0.9959005832672119
50th percentile: 1.0399267673492432
60th percentile: 1.0870008945465088
70th percentile: 1.1340750217437745
80th percentile: 1.3561957359313968
90th percentile: 1.7533630371093751
95th percentile: 1.951946687698364
99th percentile: 2.1108136081695554
mean time: 1.234534454345703
Pipeline stage StressChecker completed in 7.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-misllm-v9-1-1_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v9-1-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v9-1-1_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v9-1-1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v9-1-1-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-1-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-1-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-1-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-1-1-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v9-1-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v9-1-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-1-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-1-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-1-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-1-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-1-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v9-1-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.67s
cycy233-misllm-v9-1-1_v1 status is now torndown due to DeploymentManager action