Modelpublic

maud-dr/model_2_stage2-seed_2025

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes10downloads

Model Card

model2stage2-seed_2025

This model is a fine-tuned version of maud-dr/model_2_stage1 on the None dataset. It achieves the following results on the evaluation set:

—Loss: 2.6600
—Precision: 0.6346
—Recall: 0.7174
—F1: 0.6735

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
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 2025
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.2914	1.0	447	1.5544	0.5815	0.7754	0.6646
0.2523	2.0	894	1.6443	0.6469	0.6703	0.6584
0.16	3.0	1341	1.8783	0.6144	0.6812	0.6460
0.1354	4.0	1788	1.5711	0.6287	0.7790	0.6958
0.1321	5.0	2235	1.7032	0.6607	0.6703	0.6655
0.1108	6.0	2682	1.9982	0.6144	0.6812	0.6460
0.103	7.0	3129	2.2463	0.6146	0.6993	0.6542
0.0778	8.0	3576	2.3003	0.6304	0.6920	0.6598
0.0428	9.0	4023	2.6554	0.6226	0.6993	0.6587
0.0589	10.0	4470	2.4618	0.6237	0.6667	0.6445
0.046	11.0	4917	2.5882	0.6242	0.7101	0.6644
0.0311	12.0	5364	2.5561	0.6321	0.7283	0.6768
0.0288	13.0	5811	2.6707	0.6410	0.7246	0.6803
0.0296	14.0	6258	2.6000	0.6343	0.7101	0.6701
0.0002	15.0	6705	2.6600	0.6346	0.7174	0.6735

Framework versions

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