developer_uid: Hastagaras
submission_id: hastagaras-rebahan-8b-l3_2243_v1
model_name: 1
model_group: Hastagaras/Rebahan-8B-L3
status: torndown
timestamp: 2024-06-20T00:51:21+00:00
num_battles: 33524
num_wins: 20226
celo_rating: 1225.28
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Rebahan-8B-L3-MK.II-RP
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/Rebahan-8B-L3-MK.II-RP
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-19
win_ratio: 0.6033289583581911
generation_params: {'temperature': 0.95, 'top_p': 1.0, '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|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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-rebahan-8b-l3-2243-v1-mkmlizer
Waiting for job on hastagaras-rebahan-8b-l3-2243-v1-mkmlizer to finish
Stopping job with name hastagaras-rebahan-8b-l3-2243-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-rebahan-8b-l3-2243-v1-mkmlizer
Waiting for job on hastagaras-rebahan-8b-l3-2243-v1-mkmlizer to finish
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ /___/ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ belonging to: ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Downloaded to shared memory in 30.743s
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 126.46it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.58it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.49it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 160.97it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 82.80it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 100.03it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 115.13it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 127.43it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 136.63it/s] Loading 0: 59%|█████▉ | 172/291 [00:01<00:00, 140.85it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 87.71it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 96.28it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 111.00it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 124.72it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 134.68it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 143.71it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.99it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: quantized model in 22.898s
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Processed model Hastagaras/Rebahan-8B-L3-MK.II-RP in 56.226s
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v1
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v1/config.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v1/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v1/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v1/tokenizer.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v1/flywheel_model.0.safetensors
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v1-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v1-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v1-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Saving duration: 0.409s
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.333s
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/config.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/merges.txt
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/vocab.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/tokenizer.json
hastagaras-rebahan-8b-l3-2243-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v1_reward/reward.tensors
Job hastagaras-rebahan-8b-l3-2243-v1-mkmlizer completed after 85.12s with status: succeeded
Stopping job with name hastagaras-rebahan-8b-l3-2243-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-rebahan-8b-l3-2243-v1
Waiting for inference service hastagaras-rebahan-8b-l3-2243-v1 to be ready
Inference service hastagaras-rebahan-8b-l3-2243-v1 ready after 40.35787034034729s
Pipeline stage ISVCDeployer completed in 48.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1254827976226807s
Received healthy response to inference request in 1.3323776721954346s
Received healthy response to inference request in 1.3118386268615723s
Received healthy response to inference request in 1.2574434280395508s
Received healthy response to inference request in 1.354679822921753s
5 requests
0 failed requests
5th percentile: 1.268322467803955
10th percentile: 1.2792015075683594
20th percentile: 1.300959587097168
30th percentile: 1.3159464359283448
40th percentile: 1.3241620540618897
50th percentile: 1.3323776721954346
60th percentile: 1.3412985324859619
70th percentile: 1.3502193927764892
80th percentile: 1.5088404178619386
90th percentile: 1.8171616077423096
95th percentile: 1.971322202682495
99th percentile: 2.0946506786346437
mean time: 1.4763644695281983
Pipeline stage StressChecker completed in 8.08s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
hastagaras-rebahan-8b-l3_2243_v1 status is now deployed due to DeploymentManager action
hastagaras-rebahan-8b-l3_2243_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-rebahan-8b-l3_2243_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-rebahan-8b-l3-2243-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.79s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-rebahan-8b-l3-2243-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-rebahan-8b-l3-2243-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.71s
hastagaras-rebahan-8b-l3_2243_v1 status is now torndown due to DeploymentManager action