submission_id: hastagaras-llama-3-8b-healah_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Llama-3-8B-Healah
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, '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': "<|start_header_id|>system<|end_header_id|>\n\nYou are `{bot_name}` and engage in a Roleplay with `{user_name}`.\n\nOnly write {bot_name}'s next response with action and dialogue based on the provided context.\n\nYour persona as {bot_name}: {memory}\n\n", 'prompt_template': 'Your example message as {bot_name}: {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: {'memory_template': "{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{bot_name}: {prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-05-08T15:55:01+00:00
model_name: hastagaras-llama-3-8b-healah
model_eval_status: success
double_thumbs_up: 154
thumbs_up: 200
thumbs_down: 100
num_battles: 14915
num_wins: 7712
celo_rating: 1181.14
entertaining: 6.9
stay_in_character: 8.54
user_preference: 7.26
safety_score: 0.88
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-llama-3-8b-healah
double_thumbs_up_ratio: 0.3392070484581498
feedback_count: 454
ineligible_reason: None
language_model: Hastagaras/Llama-3-8B-Healah
model_score: 7.566666666666666
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.44052863436123346
thumbs_down_ratio: 0.22026431718061673
thumbs_up_ratio: 0.7797356828193832
us_pacific_date: 2024-05-08
win_ratio: 0.517063359034529
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-healah-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-healah-v1-mkmlizer to finish
hastagaras-llama-3-8b-healah-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-healah-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-llama-3-8b-healah-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-healah-v1-mkmlizer: Downloaded to shared memory in 31.312s
hastagaras-llama-3-8b-healah-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 129.92it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 136.38it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 28.95it/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-v1-mkmlizer: quantized model in 17.426s
hastagaras-llama-3-8b-healah-v1-mkmlizer: Processed model Hastagaras/Llama-3-8B-Healah in 49.806s
hastagaras-llama-3-8b-healah-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-healah-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-healah-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v1
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v1/special_tokens_map.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v1/tokenizer_config.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v1/config.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v1/tokenizer.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-healah-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-healah-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-llama-3-8b-healah-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-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-llama-3-8b-healah-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-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-llama-3-8b-healah-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-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-llama-3-8b-healah-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-healah-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-healah-v1-mkmlizer: Saving duration: 0.236s
hastagaras-llama-3-8b-healah-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.107s
hastagaras-llama-3-8b-healah-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-healah-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-healah-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/config.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/vocab.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/merges.txt
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/tokenizer.json
hastagaras-llama-3-8b-healah-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-healah-v1-mkmlizer completed after 73.24s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-healah-v1-mkmlizer
Pipeline stage MKMLizer completed in 79.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-healah-v1
Waiting for inference service hastagaras-llama-3-8b-healah-v1 to be ready
Inference service hastagaras-llama-3-8b-healah-v1 ready after 30.188705444335938s
Pipeline stage ISVCDeployer completed in 38.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2163827419281006s
Received healthy response to inference request in 1.2865464687347412s
Received healthy response to inference request in 1.2617502212524414s
Received healthy response to inference request in 1.3600974082946777s
Received healthy response to inference request in 1.2988512516021729s
5 requests
0 failed requests
5th percentile: 1.2667094707489013
10th percentile: 1.2716687202453614
20th percentile: 1.2815872192382813
30th percentile: 1.2890074253082275
40th percentile: 1.2939293384552002
50th percentile: 1.2988512516021729
60th percentile: 1.3233497142791748
70th percentile: 1.3478481769561768
80th percentile: 1.5313544750213626
90th percentile: 1.8738686084747316
95th percentile: 2.0451256752014157
99th percentile: 2.1821313285827637
mean time: 1.4847256183624267
Pipeline stage StressChecker completed in 8.04s
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-llama-3-8b-healah_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-healah_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics