metadata

library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: >-
      jackmedda/answerdotai-ModernBERT-base_finetuned_augmented_augmented_qwen2.5_32b
    results: []

jackmedda/answerdotai-ModernBERT-base_finetuned_augmented_augmented_qwen2.5_32b

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

Loss: 0.9726
Accuracy: 0.8235
F1: 0.8929
Precision: 0.8333
Recall: 0.9615

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: 4
eval_batch_size: 4
seed: 42
optimizer: Use 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.3934	1.0	46	2.0022	0.7	0.8235	0.7	1.0
0.3095	2.0	92	1.9761	0.7	0.8235	0.7	1.0
0.1648	3.0	138	2.3052	0.7	0.8235	0.7	1.0
0.1827	4.0	184	0.7148	0.8	0.875	0.7778	1.0
0.0662	5.0	230	1.6868	0.7	0.8235	0.7	1.0
0.0011	6.0	276	0.5374	0.9	0.9333	0.875	1.0
0.0016	7.0	322	0.4706	0.9	0.9333	0.875	1.0
0.0001	8.0	368	0.3350	0.9	0.9333	0.875	1.0
0.0	9.0	414	0.6715	0.9	0.9333	0.875	1.0
0.0	10.0	460	0.6828	0.9	0.9333	0.875	1.0
0.0	11.0	506	0.6747	0.9	0.9333	0.875	1.0
0.0	12.0	552	0.6715	0.9	0.9333	0.875	1.0
0.0	13.0	598	0.6698	0.9	0.9333	0.875	1.0
0.0	14.0	644	0.6742	0.9	0.9333	0.875	1.0

Framework versions

Transformers 4.48.3
Pytorch 2.3.0+cu121
Datasets 3.2.0
Tokenizers 0.21.0