submission_id: hastagaras-llama-3-8b-healah_v4
developer_uid: Hastagaras
best_of: 16
celo_rating: 1203.98
display_name: matapancing
family_friendly_score: 0.0
formatter: {'memory_template': "<|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': True}
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 85, 'presence_penalty': 0.42, 'frequency_penalty': 0.35, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/Llama-3-8B-Healah
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Llama-3-8B-He
model_name: matapancing
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Llama-3-8B-Healah
model_size: 8B
num_battles: 20675
num_wins: 11402
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-20T06:36:54+00:00
us_pacific_date: 2024-05-19
win_ratio: 0.5514873035066505
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-healah-v4-mkmlizer
Waiting for job on hastagaras-llama-3-8b-healah-v4-mkmlizer to finish
hastagaras-llama-3-8b-healah-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-healah-v4-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-llama-3-8b-healah-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-healah-v4-mkmlizer: Downloaded to shared memory in 20.165s
hastagaras-llama-3-8b-healah-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 127.86it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 152.56it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 156.47it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 158.62it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 80.51it/s] Loading 0: 34%|███▍ | 99/291 [00:00<00:02, 93.96it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 102.57it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 117.34it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 129.10it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 129.61it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 86.82it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 95.76it/s] Loading 0: 75%|███████▍ | 217/291 [00:01<00:00, 108.26it/s] Loading 0: 79%|███████▉ | 231/291 [00:02<00:00, 113.82it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 124.73it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 134.97it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 140.57it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-healah-v4-mkmlizer: quantized model in 17.832s
hastagaras-llama-3-8b-healah-v4-mkmlizer: Processed model Hastagaras/Llama-3-8B-Healah in 38.926s
hastagaras-llama-3-8b-healah-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-healah-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-healah-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v4
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v4/tokenizer_config.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v4/config.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v4/special_tokens_map.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v4/tokenizer.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v4/flywheel_model.0.safetensors
hastagaras-llama-3-8b-healah-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-healah-v4-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-llama-3-8b-healah-v4-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-v4-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-llama-3-8b-healah-v4-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-v4-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-llama-3-8b-healah-v4-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-v4-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-llama-3-8b-healah-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-healah-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-healah-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-healah-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/config.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/tokenizer_config.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/special_tokens_map.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/merges.txt
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/vocab.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/tokenizer.json
hastagaras-llama-3-8b-healah-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v4_reward/reward.tensors
Job hastagaras-llama-3-8b-healah-v4-mkmlizer completed after 62.72s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-healah-v4-mkmlizer
Pipeline stage MKMLizer completed in 65.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-healah-v4
Waiting for inference service hastagaras-llama-3-8b-healah-v4 to be ready
Inference service hastagaras-llama-3-8b-healah-v4 ready after 30.165820360183716s
Pipeline stage ISVCDeployer completed in 36.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2288615703582764s
Received healthy response to inference request in 1.3255760669708252s
Received healthy response to inference request in 1.3087215423583984s
Received healthy response to inference request in 1.2962048053741455s
Received healthy response to inference request in 1.3258411884307861s
5 requests
0 failed requests
5th percentile: 1.298708152770996
10th percentile: 1.3012115001678466
20th percentile: 1.306218194961548
30th percentile: 1.3120924472808837
40th percentile: 1.3188342571258544
50th percentile: 1.3255760669708252
60th percentile: 1.3256821155548095
70th percentile: 1.3257881641387939
80th percentile: 1.5064452648162843
90th percentile: 1.8676534175872803
95th percentile: 2.0482574939727782
99th percentile: 2.192740755081177
mean time: 1.4970410346984864
Pipeline stage StressChecker completed in 8.10s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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-llama-3-8b-healah_v4 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-healah_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-healah_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-healah-v4 is running
Tearing down inference service hastagaras-llama-3-8b-healah-v4
Toredown service hastagaras-llama-3-8b-healah-v4
Pipeline stage ISVCDeleter completed in 3.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-healah-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-healah-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-healah-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-healah-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-healah-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-healah-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-healah-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-healah-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-healah-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-healah-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-healah-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-healah-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.76s
hastagaras-llama-3-8b-healah_v4 status is now torndown due to DeploymentManager action