developer_uid: Hastagaras
submission_id: hastagaras-test-gmn-cld_v1
model_name: hastagaras-test-gmn-cld_v1
model_group: Hastagaras/Test-GMN-CLD
status: torndown
timestamp: 2024-04-26T13:34:44+00:00
num_battles: 7858
num_wins: 4033
celo_rating: 1159.05
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Test-GMN-CLD
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-test-gmn-cld_v1
is_internal_developer: False
language_model: Hastagaras/Test-GMN-CLD
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-26
win_ratio: 0.5132349198269279
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': 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 hastagaras-test-gmn-cld-v1-mkmlizer
Waiting for job on hastagaras-test-gmn-cld-v1-mkmlizer to finish
hastagaras-test-gmn-cld-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-test-gmn-cld-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║                                                                     ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║                                                                     ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║                                                                     ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-test-gmn-cld-v1-mkmlizer: ║                                                                     ║
hastagaras-test-gmn-cld-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-test-gmn-cld-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.
hastagaras-test-gmn-cld-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-test-gmn-cld-v1-mkmlizer: Downloaded to shared memory in 28.461s
hastagaras-test-gmn-cld-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-test-gmn-cld-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-test-gmn-cld-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:40,  2.22s/it]
Loading 0:  26%|██▋       | 77/291 [00:05<00:11, 18.60it/s]
Loading 0:  55%|█████▍    | 159/291 [00:06<00:03, 34.85it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 46.92it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-test-gmn-cld-v1-mkmlizer: quantized model in 20.067s
hastagaras-test-gmn-cld-v1-mkmlizer: Processed model Hastagaras/Test-GMN-CLD in 50.080s
hastagaras-test-gmn-cld-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-test-gmn-cld-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-test-gmn-cld-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-test-gmn-cld-v1
hastagaras-test-gmn-cld-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-v1/special_tokens_map.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-v1/config.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-v1/tokenizer_config.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-v1/tokenizer.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-test-gmn-cld-v1/flywheel_model.0.safetensors
hastagaras-test-gmn-cld-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-test-gmn-cld-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.
hastagaras-test-gmn-cld-v1-mkmlizer:   warnings.warn(
hastagaras-test-gmn-cld-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.
hastagaras-test-gmn-cld-v1-mkmlizer:   warnings.warn(
hastagaras-test-gmn-cld-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.
hastagaras-test-gmn-cld-v1-mkmlizer:   warnings.warn(
hastagaras-test-gmn-cld-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()
hastagaras-test-gmn-cld-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-test-gmn-cld-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-test-gmn-cld-v1-mkmlizer: Saving duration: 0.279s
hastagaras-test-gmn-cld-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.686s
hastagaras-test-gmn-cld-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-test-gmn-cld-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-test-gmn-cld-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/config.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/tokenizer_config.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/special_tokens_map.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/merges.txt
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/vocab.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/tokenizer.json
hastagaras-test-gmn-cld-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-test-gmn-cld-v1_reward/reward.tensors
Job hastagaras-test-gmn-cld-v1-mkmlizer completed after 73.26s with status: succeeded
Stopping job with name hastagaras-test-gmn-cld-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-test-gmn-cld-v1
Waiting for inference service hastagaras-test-gmn-cld-v1 to be ready
Inference service hastagaras-test-gmn-cld-v1 ready after 30.206136226654053s
Pipeline stage ISVCDeployer completed in 38.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.111323833465576s
Received healthy response to inference request in 1.2587618827819824s
Received healthy response to inference request in 1.242974042892456s
Received healthy response to inference request in 1.2486042976379395s
Received healthy response to inference request in 1.2987771034240723s
5 requests
0 failed requests
5th percentile: 1.2441000938415527
10th percentile: 1.2452261447906494
20th percentile: 1.2474782466888428
30th percentile: 1.250635814666748
40th percentile: 1.2546988487243653
50th percentile: 1.2587618827819824
60th percentile: 1.2747679710388184
70th percentile: 1.2907740592956543
80th percentile: 1.4612864494323732
90th percentile: 1.7863051414489748
95th percentile: 1.9488144874572753
99th percentile: 2.078821964263916
mean time: 1.4320882320404054
Pipeline stage StressChecker completed in 7.91s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-test-gmn-cld_v1 status is now deployed due to DeploymentManager action
hastagaras-test-gmn-cld_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-test-gmn-cld_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-test-gmn-cld-v1 is running
Tearing down inference service hastagaras-test-gmn-cld-v1
Toredown service hastagaras-test-gmn-cld-v1
Pipeline stage ISVCDeleter completed in 7.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-test-gmn-cld-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-test-gmn-cld-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.96s
hastagaras-test-gmn-cld_v1 status is now torndown due to DeploymentManager action