submission_id: cycy233-misllm-v5-4_v5
developer_uid: shiroe40
best_of: 16
celo_rating: 1182.47
display_name: inference_test_true
family_friendly_score: 0.0
formatter: {'memory_template': "### Instruction\nYou are a creative agent roleplaying as a character called {bot_name}. Stay true to the persona given, reply with long and descriptive sentences. Do not be repetitive. This is {bot_name}'s persona:\n{memory}", 'prompt_template': "### Input:\n # {bot_name}'s example conversation: \n{prompt}\n### Response: \n# Based on {bot_name}'s persona and the example conversation, please complete the following actual conversation as the Assistant (as {bot_name}) :\n", 'bot_template': '### {bot_name}: {message}\n', 'user_template': '### {user_name}: {message}\n', 'response_template': '### {bot_name}:', 'truncate_by_message': True}
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}
is_internal_developer: False
language_model: cycy233/misllm_v5.4
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_eval_status: success
model_group: cycy233/misllm_v5.4
model_name: inference_test_true
model_num_parameters: 7241732096.0
model_repo: cycy233/misllm_v5.4
model_size: 7B
num_battles: 12690
num_wins: 6403
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-24T04:00:57+00:00
us_pacific_date: 2024-05-23
win_ratio: 0.5045705279747833
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v5-4-v5-mkmlizer
Waiting for job on cycy233-misllm-v5-4-v5-mkmlizer to finish
cycy233-misllm-v5-4-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v5-4-v5-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ /___/ ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ belonging to: ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v5-4-v5-mkmlizer: ║ ║
cycy233-misllm-v5-4-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v5-4-v5-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-v5-4-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v5-4-v5-mkmlizer: Downloaded to shared memory in 34.683s
cycy233-misllm-v5-4-v5-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-4-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-4-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 77.30it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 84.40it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 74.11it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-4-v5-mkmlizer: quantized model in 15.356s
cycy233-misllm-v5-4-v5-mkmlizer: Processed model cycy233/misllm_v5.4 in 52.349s
cycy233-misllm-v5-4-v5-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-4-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-4-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5
cycy233-misllm-v5-4-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5/config.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5/tokenizer_config.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5/tokenizer.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5/special_tokens_map.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5/tokenizer.model
cycy233-misllm-v5-4-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-4-v5/flywheel_model.0.safetensors
cycy233-misllm-v5-4-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v5-4-v5-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-v5-4-v5-mkmlizer: warnings.warn(
cycy233-misllm-v5-4-v5-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-v5-4-v5-mkmlizer: warnings.warn(
cycy233-misllm-v5-4-v5-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-v5-4-v5-mkmlizer: warnings.warn(
cycy233-misllm-v5-4-v5-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-v5-4-v5-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-4-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-4-v5-mkmlizer: Saving duration: 0.495s
cycy233-misllm-v5-4-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.749s
cycy233-misllm-v5-4-v5-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-4-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-4-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/config.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/merges.txt
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/special_tokens_map.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/tokenizer_config.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/vocab.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/tokenizer.json
cycy233-misllm-v5-4-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-4-v5_reward/reward.tensors
Job cycy233-misllm-v5-4-v5-mkmlizer completed after 93.48s with status: succeeded
Stopping job with name cycy233-misllm-v5-4-v5-mkmlizer
Pipeline stage MKMLizer completed in 98.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-4-v5
Waiting for inference service cycy233-misllm-v5-4-v5 to be ready
Inference service cycy233-misllm-v5-4-v5 ready after 30.153342485427856s
Pipeline stage ISVCDeployer completed in 37.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9331562519073486s
Received healthy response to inference request in 1.0662004947662354s
Received healthy response to inference request in 1.109919548034668s
Received healthy response to inference request in 1.0738716125488281s
Received healthy response to inference request in 1.1556429862976074s
5 requests
0 failed requests
5th percentile: 1.067734718322754
10th percentile: 1.0692689418792725
20th percentile: 1.0723373889923096
30th percentile: 1.0810811996459961
40th percentile: 1.095500373840332
50th percentile: 1.109919548034668
60th percentile: 1.1282089233398438
70th percentile: 1.1464982986450196
80th percentile: 1.3111456394195558
90th percentile: 1.6221509456634522
95th percentile: 1.7776535987854003
99th percentile: 1.902055721282959
mean time: 1.2677581787109375
Pipeline stage StressChecker completed in 7.03s
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 0.06s
cycy233-misllm-v5-4_v5 status is now deployed due to DeploymentManager action
cycy233-misllm-v5-4_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-4_v5
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-4-v5 is running
Tearing down inference service cycy233-misllm-v5-4-v5
Toredown service cycy233-misllm-v5-4-v5
Pipeline stage ISVCDeleter completed in 4.70s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-4-v5/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v5/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-4-v5_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.00s
cycy233-misllm-v5-4_v5 status is now torndown due to DeploymentManager action