Llama-3.2-1B-Instruct-classifier

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2160
• Accuracy: 0.9308
• F1: 0.8621

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0	0	1.0194	0.4524	0.3310
No log	0.2020	79	0.3185	0.8804	0.7508
No log	0.4041	158	0.2728	0.8948	0.7989
No log	0.6061	237	0.2436	0.9006	0.8110
No log	0.8082	316	0.2251	0.8963	0.7895
No log	1.0102	395	0.2713	0.8905	0.81
No log	1.2123	474	0.3203	0.9020	0.8162
0.3016	1.4143	553	0.2289	0.9164	0.8324
0.3016	1.6164	632	0.2306	0.9280	0.8641
0.3016	1.8184	711	0.2160	0.9308	0.8621

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2