submission_id: nousresearch-meta-llama_4941_v50
developer_uid: Meliodia
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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}
reward_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}
timestamp: 2024-04-29T19:13:51+00:00
model_name: NousL3-8B-Instruct
model_eval_status: success
double_thumbs_up: 68
thumbs_up: 145
thumbs_down: 96
num_battles: 7145
num_wins: 3765
celo_rating: 1177.11
entertaining: 7.1
stay_in_character: 8.54
user_preference: 7.36
safety_score: 0.95
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: NousL3-8B-Instruct
double_thumbs_up_ratio: 0.22006472491909385
feedback_count: 309
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_score: 7.666666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4692556634304207
thumbs_down_ratio: 0.3106796116504854
thumbs_up_ratio: 0.6893203883495146
us_pacific_date: 2024-04-29
win_ratio: 0.5269419174247726
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v50-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v50-mkmlizer to finish
nousresearch-meta-llama-4941-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v50-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ Version: 0.8.10 ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v50-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v50-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.
nousresearch-meta-llama-4941-v50-mkmlizer: warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-4941-v50-mkmlizer: Downloaded to shared memory in 24.108s
nousresearch-meta-llama-4941-v50-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v50-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 112.43it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 120.37it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v50-mkmlizer: quantized model in 17.785s
nousresearch-meta-llama-4941-v50-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 42.980s
nousresearch-meta-llama-4941-v50-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v50
nousresearch-meta-llama-4941-v50-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v50/config.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v50/special_tokens_map.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v50/tokenizer_config.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v50/tokenizer.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v50/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v50-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v50-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.
nousresearch-meta-llama-4941-v50-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v50-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.
nousresearch-meta-llama-4941-v50-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v50-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.
nousresearch-meta-llama-4941-v50-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v50-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()
nousresearch-meta-llama-4941-v50-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v50-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v50-mkmlizer: Saving duration: 0.242s
nousresearch-meta-llama-4941-v50-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.962s
nousresearch-meta-llama-4941-v50-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v50-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v50-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward
nousresearch-meta-llama-4941-v50-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward/config.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward/merges.txt
nousresearch-meta-llama-4941-v50-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward/vocab.json
nousresearch-meta-llama-4941-v50-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v50_reward/tokenizer.json
Job nousresearch-meta-llama-4941-v50-mkmlizer completed after 74.02s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v50-mkmlizer
Pipeline stage MKMLizer completed in 77.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v50
Waiting for inference service nousresearch-meta-llama-4941-v50 to be ready
Inference service nousresearch-meta-llama-4941-v50 ready after 30.19818902015686s
Pipeline stage ISVCDeployer completed in 37.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2331953048706055s
Received healthy response to inference request in 1.2529737949371338s
Received healthy response to inference request in 1.2620301246643066s
Received healthy response to inference request in 1.2720365524291992s
Received healthy response to inference request in 1.2471249103546143s
5 requests
0 failed requests
5th percentile: 1.2482946872711183
10th percentile: 1.249464464187622
20th percentile: 1.2518040180206298
30th percentile: 1.2547850608825684
40th percentile: 1.2584075927734375
50th percentile: 1.2620301246643066
60th percentile: 1.2660326957702637
70th percentile: 1.2700352668762207
80th percentile: 1.4642683029174806
90th percentile: 1.848731803894043
95th percentile: 2.040963554382324
99th percentile: 2.1947489547729493
mean time: 1.4534721374511719
Pipeline stage StressChecker completed in 7.87s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
nousresearch-meta-llama_4941_v50 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v50 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics