developer_uid: Hastagaras
submission_id: hastagaras-parung-macet_v1
model_name: 1
model_group: Hastagaras/Parung-macet
status: torndown
timestamp: 2024-06-28T01:29:17+00:00
num_battles: 20262
num_wins: 10694
celo_rating: 1202.13
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Parung-macet
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: 1
is_internal_developer: False
language_model: Hastagaras/Parung-macet
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-27
win_ratio: 0.527786003356036
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|>{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}<|eot_id|>\n', 'user_template': '{user_name}: {message}<|eot_id|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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-parung-macet-v1-mkmlizer
Waiting for job on hastagaras-parung-macet-v1-mkmlizer to finish
hastagaras-parung-macet-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-parung-macet-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-parung-macet-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-parung-macet-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-parung-macet-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-parung-macet-v1-mkmlizer: ║ /___/ ║
hastagaras-parung-macet-v1-mkmlizer: ║ ║
hastagaras-parung-macet-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-parung-macet-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-parung-macet-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-parung-macet-v1-mkmlizer: ║ ║
hastagaras-parung-macet-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-parung-macet-v1-mkmlizer: ║ belonging to: ║
hastagaras-parung-macet-v1-mkmlizer: ║ ║
hastagaras-parung-macet-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-parung-macet-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-parung-macet-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-parung-macet-v1-mkmlizer: ║ ║
hastagaras-parung-macet-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-parung-macet-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-parung-macet-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-parung-macet-v1-mkmlizer: Downloaded to shared memory in 37.040s
hastagaras-parung-macet-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-parung-macet-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-parung-macet-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 112.82it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 135.88it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 133.98it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 134.00it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 140.89it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 74.15it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 84.34it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 99.77it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 105.52it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 112.71it/s] Loading 0: 56%|█████▌ | 162/291 [00:01<00:01, 119.49it/s] Loading 0: 61%|██████ | 177/291 [00:01<00:00, 127.38it/s] Loading 0: 66%|██████▌ | 191/291 [00:01<00:01, 78.35it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 84.20it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 99.34it/s] Loading 0: 79%|███████▉ | 231/291 [00:02<00:00, 103.37it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 112.96it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 122.31it/s] Loading 0: 96%|█████████▌| 278/291 [00:02<00:00, 123.14it/s] Loading 0: 100%|██████████| 291/291 [00:08<00:00, 7.92it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-parung-macet-v1-mkmlizer: quantized model in 23.940s
hastagaras-parung-macet-v1-mkmlizer: Processed model Hastagaras/Parung-macet in 63.530s
hastagaras-parung-macet-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-parung-macet-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-parung-macet-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-parung-macet-v1
hastagaras-parung-macet-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-parung-macet-v1/tokenizer_config.json
hastagaras-parung-macet-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-parung-macet-v1/special_tokens_map.json
hastagaras-parung-macet-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-parung-macet-v1/config.json
hastagaras-parung-macet-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-parung-macet-v1/tokenizer.json
hastagaras-parung-macet-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-parung-macet-v1/flywheel_model.0.safetensors
hastagaras-parung-macet-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-parung-macet-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-parung-macet-v1-mkmlizer: warnings.warn(
hastagaras-parung-macet-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-parung-macet-v1-mkmlizer: warnings.warn(
hastagaras-parung-macet-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-parung-macet-v1-mkmlizer: warnings.warn(
hastagaras-parung-macet-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-parung-macet-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-parung-macet-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-parung-macet-v1-mkmlizer: Saving duration: 0.400s
hastagaras-parung-macet-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.800s
hastagaras-parung-macet-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-parung-macet-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-parung-macet-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/special_tokens_map.json
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/config.json
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/tokenizer_config.json
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/vocab.json
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/merges.txt
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/tokenizer.json
hastagaras-parung-macet-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-parung-macet-v1_reward/reward.tensors
Job hastagaras-parung-macet-v1-mkmlizer completed after 94.14s with status: succeeded
Stopping job with name hastagaras-parung-macet-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-parung-macet-v1
Waiting for inference service hastagaras-parung-macet-v1 to be ready
Inference service hastagaras-parung-macet-v1 ready after 50.258317708969116s
Pipeline stage ISVCDeployer completed in 57.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2431859970092773s
Received healthy response to inference request in 1.4331881999969482s
Received healthy response to inference request in 1.26704740524292s
Received healthy response to inference request in 1.2639515399932861s
Received healthy response to inference request in 1.2792580127716064s
5 requests
0 failed requests
5th percentile: 1.264570713043213
10th percentile: 1.2651898860931396
20th percentile: 1.2664282321929932
30th percentile: 1.2694895267486572
40th percentile: 1.2743737697601318
50th percentile: 1.2792580127716064
60th percentile: 1.3408300876617432
70th percentile: 1.4024021625518799
80th percentile: 1.5951877593994142
90th percentile: 1.9191868782043457
95th percentile: 2.0811864376068114
99th percentile: 2.210786085128784
mean time: 1.4973262310028077
Pipeline stage StressChecker completed in 8.26s
hastagaras-parung-macet_v1 status is now deployed due to DeploymentManager action
hastagaras-parung-macet_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-parung-macet_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-parung-macet-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-parung-macet-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-parung-macet-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-parung-macet-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-parung-macet-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-parung-macet-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-parung-macet-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-parung-macet-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-parung-macet-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-parung-macet-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-parung-macet-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-parung-macet-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-parung-macet-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.40s
hastagaras-parung-macet_v1 status is now torndown due to DeploymentManager action