developer_uid: shiroe40
submission_id: cycy233-misllm-v1-4_v1
model_name: base_v1
model_group: cycy233/misllm_v1.4
status: torndown
timestamp: 2024-05-12T00:30:56+00:00
num_battles: 14698
num_wins: 7348
celo_rating: 1162.22
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v1.4
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: base_v1
is_internal_developer: False
language_model: cycy233/misllm_v1.4
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-11
win_ratio: 0.4999319635324534
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-v1-4-v1-mkmlizer
Waiting for job on cycy233-misllm-v1-4-v1-mkmlizer to finish
cycy233-misllm-v1-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v1-4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ Version: 0.8.10 ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v1-4-v1-mkmlizer: ║ ║
cycy233-misllm-v1-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v1-4-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-v1-4-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v1-4-v1-mkmlizer: Downloaded to shared memory in 23.539s
cycy233-misllm-v1-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v1-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v1-4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 80.97it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 93.63it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 77.34it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v1-4-v1-mkmlizer: quantized model in 12.308s
cycy233-misllm-v1-4-v1-mkmlizer: Processed model cycy233/misllm_v1.4 in 36.755s
cycy233-misllm-v1-4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v1-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v1-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1
cycy233-misllm-v1-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1/tokenizer_config.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1/config.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1/tokenizer.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1/special_tokens_map.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1/tokenizer.model
cycy233-misllm-v1-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v1-4-v1/flywheel_model.0.safetensors
cycy233-misllm-v1-4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v1-4-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-v1-4-v1-mkmlizer: warnings.warn(
cycy233-misllm-v1-4-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-v1-4-v1-mkmlizer: warnings.warn(
cycy233-misllm-v1-4-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-v1-4-v1-mkmlizer: warnings.warn(
cycy233-misllm-v1-4-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-v1-4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v1-4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v1-4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v1-4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/special_tokens_map.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/config.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/tokenizer_config.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/merges.txt
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/vocab.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/tokenizer.json
cycy233-misllm-v1-4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v1-4-v1_reward/reward.tensors
Job cycy233-misllm-v1-4-v1-mkmlizer completed after 73.89s with status: succeeded
Stopping job with name cycy233-misllm-v1-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v1-4-v1
Waiting for inference service cycy233-misllm-v1-4-v1 to be ready
Inference service cycy233-misllm-v1-4-v1 ready after 30.19163227081299s
Pipeline stage ISVCDeployer completed in 37.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9778165817260742s
Received healthy response to inference request in 1.1666908264160156s
Received healthy response to inference request in 1.1846718788146973s
Received healthy response to inference request in 1.1554765701293945s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.0984599590301514s
Received healthy response to inference request in 1.192284345626831s
Received healthy response to inference request in 1.1771695613861084s
Received healthy response to inference request in 1.1813123226165771s
Received healthy response to inference request in 1.168837070465088s
5 requests
0 failed requests
5th percentile: 1.1125353813171386
10th percentile: 1.126610803604126
20th percentile: 1.1547616481781007
30th percentile: 1.170503568649292
40th percentile: 1.1738365650177003
50th percentile: 1.1771695613861084
60th percentile: 1.178826665878296
70th percentile: 1.1804837703704834
80th percentile: 1.183506727218628
90th percentile: 1.1878955364227295
95th percentile: 1.1900899410247803
99th percentile: 1.191845464706421
mean time: 1.1636126518249512
Pipeline stage StressChecker completed in 32.16s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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 0.07s
cycy233-misllm-v1-4_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v1-4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v1-4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v1-4-v1 is running
Tearing down inference service cycy233-misllm-v1-4-v1
Toredown service cycy233-misllm-v1-4-v1
Pipeline stage ISVCDeleter completed in 3.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v1-4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v1-4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v1-4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v1-4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v1-4-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v1-4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v1-4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v1-4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v1-4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v1-4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v1-4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v1-4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v1-4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.88s
cycy233-misllm-v1-4_v1 status is now torndown due to DeploymentManager action