decathlon-intent-bert

This model is a fine-tuned version of classla/bcms-bertic on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2932
• Accuracy: 0.5
• F1 Macro: 0.4317

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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
No log	1.0	7	1.3753	0.375	0.3100
No log	2.0	14	1.3609	0.4167	0.3519
No log	3.0	21	1.3301	0.4583	0.4000
No log	4.0	28	1.3113	0.4583	0.4054
No log	5.0	35	1.3028	0.5	0.4460
No log	6.0	42	1.2932	0.5	0.4317

Framework versions

• Transformers 5.10.2
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2