intent_model_v3

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0022
• Precision: 1.0

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision
No log	1.0	6	0.5620	0.0
No log	2.0	12	0.3912	0.0
No log	3.0	18	0.3001	0.0
No log	4.0	24	0.1519	1.0
No log	5.0	30	0.0541	1.0
No log	6.0	36	0.1028	1.0
No log	7.0	42	0.0160	1.0
No log	8.0	48	0.0221	1.0
No log	9.0	54	0.0201	1.0
No log	10.0	60	0.0073	1.0
No log	11.0	66	0.0057	1.0
No log	12.0	72	0.0070	1.0
No log	13.0	78	0.0033	1.0
No log	14.0	84	0.0033	1.0
No log	15.0	90	0.0038	1.0
No log	16.0	96	0.0022	1.0
No log	17.0	102	0.0018	1.0
No log	18.0	108	0.0020	1.0
No log	19.0	114	0.0022	1.0
No log	20.0	120	0.0022	1.0

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0