cycy233-misllm-v5-1

developer_uid: shiroe40

submission_id: cycy233-misllm-v5-1_v1

model_name: base

model_group: cycy233/misllm_v5.1

status: torndown

timestamp: 2024-05-23T00:13:50+00:00

num_battles: 15546

num_wins: 7606

celo_rating: 1175.85

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/misllm_v5.1

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

is_internal_developer: False

language_model: cycy233/misllm_v5.1

model_size: 7B

ranking_group: single

us_pacific_date: 2024-05-22

win_ratio: 0.4892576868647884

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}

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': True, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v5-1-v1-mkmlizer
Waiting for job on cycy233-misllm-v5-1-v1-mkmlizer to finish
cycy233-misllm-v5-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v5-1-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v5-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v5-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v5-1-v1-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v5-1-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v5-1-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v5-1-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v5-1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v5-1-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v5-1-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-v5-1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v5-1-v1-mkmlizer: Downloaded to shared memory in 28.173s
cycy233-misllm-v5-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 85.65it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 93.19it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 79.57it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-1-v1-mkmlizer: quantized model in 13.677s
cycy233-misllm-v5-1-v1-mkmlizer: Processed model cycy233/misllm_v5.1 in 43.010s
cycy233-misllm-v5-1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1
cycy233-misllm-v5-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1/tokenizer.model
cycy233-misllm-v5-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1/config.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1/tokenizer_config.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1/special_tokens_map.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1/tokenizer.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-1-v1/flywheel_model.0.safetensors
cycy233-misllm-v5-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v5-1-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-v5-1-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v5-1-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-v5-1-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v5-1-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-v5-1-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v5-1-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-v5-1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-1-v1-mkmlizer: Saving duration: 0.243s
cycy233-misllm-v5-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.683s
cycy233-misllm-v5-1-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/tokenizer_config.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/merges.txt
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/config.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/special_tokens_map.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/vocab.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/tokenizer.json
cycy233-misllm-v5-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-1-v1_reward/reward.tensors
Failed to get response for submission blend_nalib_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Job cycy233-misllm-v5-1-v1-mkmlizer completed after 72.94s with status: succeeded
Stopping job with name cycy233-misllm-v5-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-1-v1
Waiting for inference service cycy233-misllm-v5-1-v1 to be ready
Failed to get response for submission blend_hatal_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission blend_nalib_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission blend_pobil_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission blend_kepik_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service cycy233-misllm-v5-1-v1 ready after 40.24353766441345s
Pipeline stage ISVCDeployer completed in 48.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.675894021987915s
Received healthy response to inference request in 0.9576570987701416s
Received healthy response to inference request in 1.1323726177215576s
Received healthy response to inference request in 1.0036520957946777s
Received healthy response to inference request in 1.0340821743011475s
5 requests
0 failed requests
5th percentile: 0.9668560981750488
10th percentile: 0.976055097579956
20th percentile: 0.9944530963897705
30th percentile: 1.0097381114959716
40th percentile: 1.0219101428985595
50th percentile: 1.0340821743011475
60th percentile: 1.0733983516693115
70th percentile: 1.1127145290374756
80th percentile: 1.2410768985748293
90th percentile: 1.4584854602813722
95th percentile: 1.5671897411346434
99th percentile: 1.6541531658172608
mean time: 1.160731601715088
Pipeline stage StressChecker completed in 6.43s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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-v5-1_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v5-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-1_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-1-v1 is running
Tearing down inference service cycy233-misllm-v5-1-v1
Toredown service cycy233-misllm-v5-1-v1
Pipeline stage ISVCDeleter completed in 4.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-1-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-1-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.51s
cycy233-misllm-v5-1_v1 status is now torndown due to DeploymentManager action