test7_balanced_and_sentence

This model is a fine-tuned version of ibaucells/RoBERTa-ca-CaWikiTC on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7381

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: 5e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
2.8474	1.0	63	2.8422
2.8221	2.0	126	2.8406
2.8228	3.0	189	2.8483
2.7804	4.0	252	2.8079
2.6707	5.0	315	2.7224
2.5542	6.0	378	2.6884
2.3782	7.0	441	2.5568
2.302	8.0	504	2.5003
1.9717	9.0	567	2.2786
1.7659	10.0	630	2.1437
1.4552	11.0	693	2.0261
1.1394	12.0	756	1.8772
0.8644	13.0	819	1.8367
0.826	14.0	882	1.6980
0.5626	15.0	945	1.8251
0.3684	16.0	1008	1.8207
0.2861	17.0	1071	2.0102
0.2056	18.0	1134	2.2188
0.1174	19.0	1197	2.1110
0.1485	20.0	1260	2.1932
0.1064	21.0	1323	2.2119
0.065	22.0	1386	2.3062
0.0528	23.0	1449	2.3949
0.0734	24.0	1512	2.3761
0.0342	25.0	1575	2.4951
0.0686	26.0	1638	2.5017
0.0281	27.0	1701	2.5199
0.0262	28.0	1764	2.5461
0.0346	29.0	1827	2.5469
0.0261	30.0	1890	2.5541

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2