README.md

metadata

library_name: transformers
license: apache-2.0
base_model: maud-dr/model_2_stage2-seed_42
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: model_2_stage3-seed_42
    results: []

model_2_stage3-seed_42

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: 1.8972
• Precision: 0.6325
• Recall: 0.6396
• F1: 0.6361

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: 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.4847	1.0	745	0.4469	0.7088	0.5811	0.6386
0.364	2.0	1490	0.4663	0.7057	0.5563	0.6222
0.3553	3.0	2235	0.5744	0.6390	0.6937	0.6652
0.228	4.0	2980	1.1159	0.6452	0.6104	0.6273
0.1557	5.0	3725	1.3220	0.6505	0.5450	0.5931
0.1563	6.0	4470	1.1941	0.6569	0.6081	0.6316
0.0574	7.0	5215	1.2020	0.6256	0.6396	0.6325
0.0786	8.0	5960	1.6463	0.6063	0.6486	0.6268
0.0702	9.0	6705	1.4346	0.6733	0.6126	0.6415
0.0635	10.0	7450	1.6357	0.6191	0.6554	0.6368
0.0474	11.0	8195	1.7221	0.6667	0.5676	0.6131
0.0368	12.0	8940	1.7971	0.6276	0.6149	0.6212
0.0209	13.0	9685	1.8271	0.6225	0.6351	0.6288
0.0316	14.0	10430	1.8204	0.6313	0.6171	0.6241
0.0058	15.0	11175	1.8972	0.6325	0.6396	0.6361

Framework versions

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