model_2_stage3-seed_123

This model is a fine-tuned version of maud-dr/model_2_stage2-seed_42 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9828
• Precision: 0.6416
• Recall: 0.6329
• F1: 0.6372

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 123
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.3227	1.0	745	0.8746	0.6085	0.6126	0.6105
0.237	2.0	1490	1.1767	0.5567	0.7185	0.6273
0.1778	3.0	2235	0.9108	0.6499	0.6396	0.6447
0.0908	4.0	2980	1.3926	0.6295	0.5856	0.6068
0.0664	5.0	3725	1.4232	0.6008	0.6374	0.6186
0.0568	6.0	4470	1.2964	0.6189	0.6329	0.6258
0.0513	7.0	5215	1.7220	0.6994	0.5450	0.6127
0.0642	8.0	5960	1.6545	0.6360	0.6374	0.6367
0.0291	9.0	6705	1.7990	0.6	0.6824	0.6386
0.0149	10.0	7450	1.8379	0.6276	0.6149	0.6212
0.0105	11.0	8195	1.7437	0.6331	0.6374	0.6352
0.0134	12.0	8940	1.9164	0.6315	0.6329	0.6322
0.0132	13.0	9685	1.9616	0.6368	0.6396	0.6382
0.0237	14.0	10430	1.8826	0.6478	0.6171	0.6321
0.0032	15.0	11175	1.9828	0.6416	0.6329	0.6372

Framework versions

• Transformers 4.52.0.dev0
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1