t2e-classifier-v4

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6437
• Micro F1: 0.4083
• Macro F1: 0.3539
• Accuracy: 0.8996
• Val Loss: 0.2668

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: 64
• eval_batch_size: 64
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Micro F1	Macro F1	Accuracy	Val Loss
0.7681	1.0	679	0.7440	0.3036	0.2623	0.8338	0.4174
0.6421	2.0	1358	0.6650	0.3618	0.3182	0.8746	0.3234
0.5187	3.0	2037	0.6302	0.3708	0.3205	0.8807	0.3096
0.4718	4.0	2716	0.6347	0.3974	0.3437	0.8943	0.2801
0.4331	5.0	3395	0.6437	0.4083	0.3539	0.8996	0.2668

Framework versions

• Transformers 4.51.1
• Pytorch 2.2.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.0