model_google_gemma_2_2b_d_political_bias_political_bias_ep_1_a_sqn_a_b_p_100_5_v_7

This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9495
• Balanced Accuracy: 0.7250
• Accuracy: 0.7251
• F1 Micro: 0.7251
• F1 Macro: 0.7250

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Balanced Accuracy	Accuracy	F1 Micro	F1 Macro
0.7596	1.0	73	0.5565	0.7020	0.7019	0.7019	0.7018
0.2993	2.0	146	0.7352	0.6991	0.6985	0.6985	0.6941
0.0907	3.0	219	0.9495	0.7250	0.7251	0.7251	0.7250

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1