README.md

metadata

license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cased-te
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: 2404v5
    results: []

2404v5

This model is a fine-tuned version of projecte-aina/roberta-base-ca-v2-cased-te on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6586
• Accuracy: 0.8403
• Precision: 0.8407
• Recall: 0.8403
• F1: 0.8403
• Ratio: 0.5168

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: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 20
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.06
• lr_scheduler_warmup_steps: 4
• num_epochs: 4
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Ratio
3.0551	0.1626	10	1.7145	0.5	0.5	0.5	0.3733	0.0504
1.0346	0.3252	20	0.8860	0.5336	0.5558	0.5336	0.4822	0.8151
0.8531	0.4878	30	0.8174	0.5672	0.6156	0.5672	0.5166	0.1765
0.8279	0.6504	40	0.7147	0.7563	0.7928	0.7563	0.7485	0.6765
0.744	0.8130	50	0.6403	0.8067	0.8099	0.8067	0.8062	0.5504
0.6594	0.9756	60	0.6299	0.7983	0.8004	0.7983	0.7980	0.5420
0.5973	1.1382	70	0.6320	0.8193	0.8204	0.8193	0.8192	0.5294
0.5934	1.3008	80	0.6306	0.8151	0.8184	0.8151	0.8147	0.4496
0.5529	1.4634	90	0.6442	0.8193	0.8195	0.8193	0.8193	0.5126
0.5618	1.6260	100	0.6186	0.8193	0.8204	0.8193	0.8192	0.5294
0.5632	1.7886	110	0.5845	0.8361	0.8373	0.8361	0.8360	0.5294
0.5886	1.9512	120	0.5752	0.8361	0.8367	0.8361	0.8361	0.5210
0.5596	2.1138	130	0.5760	0.8403	0.8407	0.8403	0.8403	0.5168
0.4964	2.2764	140	0.6181	0.8361	0.8367	0.8361	0.8361	0.4790
0.5014	2.4390	150	0.6422	0.8361	0.8381	0.8361	0.8359	0.5378
0.5251	2.6016	160	0.6033	0.8403	0.8428	0.8403	0.8401	0.5420
0.4723	2.7642	170	0.5839	0.8487	0.8503	0.8487	0.8486	0.5336
0.4864	2.9268	180	0.5837	0.8613	0.8616	0.8613	0.8613	0.5126
0.4512	3.0894	190	0.5973	0.8487	0.8491	0.8487	0.8487	0.5168
0.477	3.2520	200	0.6159	0.8403	0.8404	0.8403	0.8403	0.5084
0.4198	3.4146	210	0.6523	0.8403	0.8407	0.8403	0.8403	0.5168
0.4322	3.5772	220	0.6646	0.8403	0.8407	0.8403	0.8403	0.5168
0.4889	3.7398	230	0.6632	0.8403	0.8407	0.8403	0.8403	0.5168
0.4409	3.9024	240	0.6589	0.8403	0.8407	0.8403	0.8403	0.5168

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1