submission_id: nousresearch-meta-llama_4941_v52
developer_uid: zonemercy
status: rejected
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': '### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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: 2024-05-02T22:19:46+00:00
model_name: nousresearch-meta-llama_4941_v52
model_eval_status: success
double_thumbs_up: 70
thumbs_up: 94
thumbs_down: 56
num_battles: 4944
num_wins: 2547
celo_rating: 1179.88
entertaining: 7.34
stay_in_character: 8.5
user_preference: 7.58
safety_score: 0.97
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v52
double_thumbs_up_ratio: 0.3181818181818182
feedback_count: 220
ineligible_reason: model is not deployable
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_score: 7.8066666666666675
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.42727272727272725
thumbs_down_ratio: 0.2545454545454545
thumbs_up_ratio: 0.7454545454545455
us_pacific_date: 2024-05-02
win_ratio: 0.5151699029126213
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v52-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v52-mkmlizer to finish
nousresearch-meta-llama-4941-v52-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v52-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ Version: 0.8.10 ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v52-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v52-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v52-mkmlizer: Downloaded to shared memory in 12.892s
nousresearch-meta-llama-4941-v52-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v52-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v52-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 142.75it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 37.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v52-mkmlizer: quantized model in 16.850s
nousresearch-meta-llama-4941-v52-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 30.777s
nousresearch-meta-llama-4941-v52-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v52-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v52-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v52
nousresearch-meta-llama-4941-v52-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v52/config.json
nousresearch-meta-llama-4941-v52-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v52/special_tokens_map.json
nousresearch-meta-llama-4941-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v52/tokenizer_config.json
nousresearch-meta-llama-4941-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v52/tokenizer.json
nousresearch-meta-llama-4941-v52-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v52/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v52-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v52-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-v52-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v52-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-v52-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v52-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-v52-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v52-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-v52-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v52-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v52-mkmlizer: Saving duration: 1.534s
nousresearch-meta-llama-4941-v52-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.724s
Job nousresearch-meta-llama-4941-v52-mkmlizer completed after 291.69s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v52-mkmlizer
Pipeline stage MKMLizer completed in 301.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.17s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v52
Waiting for inference service nousresearch-meta-llama-4941-v52 to be ready
Inference service nousresearch-meta-llama-4941-v52 ready after 30.235023498535156s
Pipeline stage ISVCDeployer completed in 39.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3531124591827393s
Received healthy response to inference request in 1.3704397678375244s
Received healthy response to inference request in 1.2471849918365479s
Received healthy response to inference request in 1.2703368663787842s
Received healthy response to inference request in 1.2571139335632324s
5 requests
0 failed requests
5th percentile: 1.2491707801818848
10th percentile: 1.2511565685272217
20th percentile: 1.2551281452178955
30th percentile: 1.2597585201263428
40th percentile: 1.2650476932525634
50th percentile: 1.2703368663787842
60th percentile: 1.3103780269622802
70th percentile: 1.3504191875457763
80th percentile: 1.5669743061065675
90th percentile: 1.9600433826446535
95th percentile: 2.156577920913696
99th percentile: 2.3138055515289304
mean time: 1.4996376037597656
Pipeline stage StressChecker completed in 8.54s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
nousresearch-meta-llama_4941_v52 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v52 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.

Usage Metrics

Latency Metrics