README.md

metadata

license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: >-
      RE_NegREF_NSD_Nubes_Training_Development_dataset_xlm_RoBERTa_base_fine_tuned
    results: []

RE_NegREF_NSD_Nubes_Training_Development_dataset_xlm_RoBERTa_base_fine_tuned

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2774
• Negref Precision: 0.5671
• Negref Recall: 0.5899
• Negref F1: 0.5782
• Neg Precision: 0.9511
• Neg Recall: 0.9771
• Neg F1: 0.9639
• Nsco Precision: 0.8734
• Nsco Recall: 0.9181
• Nsco F1: 0.8952
• Precision: 0.8399
• Recall: 0.8727
• F1: 0.8560
• Accuracy: 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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Negref Precision	Negref Recall	Negref F1	Neg Precision	Neg Recall	Neg F1	Nsco Precision	Nsco Recall	Nsco F1	Precision	Recall	F1	Accuracy
0.1739	1.0	1729	0.1433	0.4553	0.4419	0.4485	0.9216	0.9629	0.9418	0.7944	0.8717	0.8313	0.7799	0.8180	0.7985	0.9555
0.1189	2.0	3458	0.1388	0.4859	0.5476	0.5149	0.9230	0.9683	0.9451	0.7951	0.8895	0.8397	0.7779	0.8494	0.8121	0.9569
0.0944	3.0	5187	0.1374	0.5771	0.5539	0.5653	0.9495	0.9640	0.9567	0.8535	0.8860	0.8695	0.8375	0.8476	0.8425	0.9615
0.0703	4.0	6916	0.1524	0.5415	0.6068	0.5723	0.9410	0.9749	0.9576	0.8476	0.8848	0.8658	0.8164	0.8628	0.8390	0.9602
0.0472	5.0	8645	0.1812	0.5306	0.5687	0.5490	0.9368	0.9716	0.9539	0.8440	0.8931	0.8679	0.8139	0.8566	0.8347	0.9585
0.0371	6.0	10374	0.2231	0.5371	0.5814	0.5584	0.9286	0.9803	0.9538	0.8448	0.9181	0.8799	0.8129	0.8723	0.8415	0.9588
0.031	7.0	12103	0.2036	0.5362	0.5793	0.5569	0.9509	0.9716	0.9611	0.8830	0.9145	0.8985	0.8340	0.8669	0.8501	0.9617
0.0226	8.0	13832	0.2390	0.5392	0.5666	0.5526	0.9507	0.9694	0.9600	0.8751	0.9157	0.8950	0.8335	0.8637	0.8483	0.9589
0.0174	9.0	15561	0.2462	0.5355	0.5899	0.5614	0.9443	0.9803	0.9620	0.8694	0.9169	0.8925	0.8258	0.8736	0.8491	0.9599
0.0098	10.0	17290	0.2751	0.5796	0.5772	0.5784	0.9490	0.9749	0.9618	0.8740	0.9145	0.8938	0.8443	0.8678	0.8559	0.9621
0.008	11.0	19019	0.2760	0.5611	0.5729	0.5669	0.9461	0.9771	0.9613	0.8695	0.9181	0.8931	0.8365	0.8691	0.8525	0.9606
0.0041	12.0	20748	0.2774	0.5671	0.5899	0.5782	0.9511	0.9771	0.9639	0.8734	0.9181	0.8952	0.8399	0.8727	0.8560	0.9615

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2