patch-reward-model-v2

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6882
• Accuracy: 0.56
• F1: 0.0
• Auc: 0.5191

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Auc
0.7096	1.0	25	0.6882	0.56	0.0	0.5191
0.6851	2.0	50	0.6858	0.56	0.0	0.5199
0.6961	3.0	75	0.6859	0.56	0.0	0.5463
0.6915	4.0	100	0.6858	0.56	0.0	0.5548
0.6936	5.0	125	0.6859	0.56	0.0	0.5548

Framework versions

• Transformers 5.8.0
• Pytorch 2.11.0+cu130
• Datasets 4.8.5
• Tokenizers 0.22.2

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

• Try ML Intern: https://smolagents-ml-intern.hf.space
• Source code: https://github.com/huggingface/ml-intern

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'narcolepticchicken/patch-reward-model-v2'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

For non-causal architectures, replace AutoModelForCausalLM with the appropriate AutoModel class.