developer_uid: Hastagaras
submission_id: hastagaras-markites-2_v1
model_name: mari-kita-tesss
model_group: Hastagaras/Markites-2
status: torndown
timestamp: 2024-05-17T04:27:32+00:00
num_battles: 20017
num_wins: 10485
celo_rating: 1187.77
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Markites-2
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: mari-kita-tesss
is_internal_developer: False
language_model: Hastagaras/Markites-2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-16
win_ratio: 0.5238047659489434
generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, '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-markites-2-v1-mkmlizer
Waiting for job on hastagaras-markites-2-v1-mkmlizer to finish
hastagaras-markites-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-markites-2-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-markites-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-markites-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-markites-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-markites-2-v1-mkmlizer: ║ /___/ ║
hastagaras-markites-2-v1-mkmlizer: ║ ║
hastagaras-markites-2-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-markites-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-markites-2-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-markites-2-v1-mkmlizer: ║ ║
hastagaras-markites-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-markites-2-v1-mkmlizer: ║ belonging to: ║
hastagaras-markites-2-v1-mkmlizer: ║ ║
hastagaras-markites-2-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-markites-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-markites-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-markites-2-v1-mkmlizer: ║ ║
hastagaras-markites-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-markites-2-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-markites-2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-markites-2-v1-mkmlizer: Downloaded to shared memory in 30.590s
hastagaras-markites-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-markites-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-markites-2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:42, 2.01s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:36, 7.32it/s] Loading 0: 14%|█▍ | 42/291 [00:04<00:15, 16.26it/s] Loading 0: 21%|██ | 60/291 [00:04<00:10, 22.80it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 38.77it/s] Loading 0: 36%|███▌ | 104/291 [00:04<00:03, 52.66it/s] Loading 0: 42%|████▏ | 121/291 [00:04<00:02, 62.05it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:01, 77.97it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:01, 97.28it/s] Loading 0: 61%|██████ | 177/291 [00:05<00:01, 75.86it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:00, 102.31it/s] Loading 0: 76%|███████▋ | 222/291 [00:05<00:00, 119.35it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 144.99it/s] Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 100.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-markites-2-v1-mkmlizer: quantized model in 17.219s
hastagaras-markites-2-v1-mkmlizer: Processed model Hastagaras/Markites-2 in 48.749s
hastagaras-markites-2-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-markites-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-markites-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-markites-2-v1
hastagaras-markites-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-markites-2-v1/config.json
hastagaras-markites-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-markites-2-v1/tokenizer.json
hastagaras-markites-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-markites-2-v1/special_tokens_map.json
hastagaras-markites-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-markites-2-v1/tokenizer_config.json
hastagaras-markites-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-markites-2-v1/flywheel_model.0.safetensors
hastagaras-markites-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-markites-2-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-markites-2-v1-mkmlizer: warnings.warn(
hastagaras-markites-2-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-markites-2-v1-mkmlizer: warnings.warn(
hastagaras-markites-2-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-markites-2-v1-mkmlizer: warnings.warn(
hastagaras-markites-2-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-markites-2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-markites-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-markites-2-v1-mkmlizer: Saving duration: 0.218s
hastagaras-markites-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.159s
hastagaras-markites-2-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-markites-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-markites-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-markites-2-v1_reward
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/config.json
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/special_tokens_map.json
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/merges.txt
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/tokenizer_config.json
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/vocab.json
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/tokenizer.json
hastagaras-markites-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-markites-2-v1_reward/reward.tensors
Job hastagaras-markites-2-v1-mkmlizer completed after 73.29s with status: succeeded
Stopping job with name hastagaras-markites-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-markites-2-v1
Waiting for inference service hastagaras-markites-2-v1 to be ready
Inference service hastagaras-markites-2-v1 ready after 190.9547257423401s
Pipeline stage ISVCDeployer completed in 198.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.103222370147705s
Received healthy response to inference request in 1.2365286350250244s
Received healthy response to inference request in 1.163926362991333s
Received healthy response to inference request in 1.249922513961792s
Received healthy response to inference request in 1.2651758193969727s
5 requests
0 failed requests
5th percentile: 1.1784468173980713
10th percentile: 1.1929672718048097
20th percentile: 1.222008180618286
30th percentile: 1.2392074108123778
40th percentile: 1.244564962387085
50th percentile: 1.249922513961792
60th percentile: 1.2560238361358642
70th percentile: 1.2621251583099364
80th percentile: 1.4327851295471192
90th percentile: 1.7680037498474122
95th percentile: 1.9356130599975585
99th percentile: 2.0697005081176756
mean time: 1.4037551403045654
Pipeline stage StressChecker completed in 7.66s
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 0.07s
hastagaras-markites-2_v1 status is now deployed due to DeploymentManager action
hastagaras-markites-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-markites-2_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-markites-2-v1 is running
Tearing down inference service hastagaras-markites-2-v1
Toredown service hastagaras-markites-2-v1
Pipeline stage ISVCDeleter completed in 4.53s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-markites-2-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-markites-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.14s
hastagaras-markites-2_v1 status is now torndown due to DeploymentManager action