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: 2404v6
    results: []

2404v6

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: 0.5736
Accuracy: 0.8487
Precision: 0.8491
Recall: 0.8487
F1: 0.8487
Ratio: 0.4832

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: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
3.6992	0.2597	10	1.6456	0.5378	0.5416	0.5378	0.5270	0.3487
1.4527	0.5195	20	1.1248	0.5336	0.5398	0.5336	0.5147	0.6975
0.9494	0.7792	30	0.9286	0.5756	0.6051	0.5756	0.5437	0.7647
0.9076	1.0390	40	0.8154	0.6849	0.6855	0.6849	0.6846	0.5294
0.8356	1.2987	50	0.7335	0.7647	0.7659	0.7647	0.7644	0.5336
0.7475	1.5584	60	0.7286	0.7437	0.7803	0.7437	0.7350	0.6807
0.7234	1.8182	70	0.6457	0.8025	0.8027	0.8025	0.8025	0.4874
0.67	2.0779	80	0.6208	0.8025	0.8043	0.8025	0.8022	0.5378
0.5994	2.3377	90	0.6106	0.8235	0.8236	0.8235	0.8235	0.4916
0.666	2.5974	100	0.5912	0.8361	0.8363	0.8361	0.8361	0.5126
0.6142	2.8571	110	0.5853	0.8319	0.8320	0.8319	0.8319	0.5084
0.6181	3.1169	120	0.5866	0.8361	0.8373	0.8361	0.8360	0.5294
0.5555	3.3766	130	0.5762	0.8487	0.8496	0.8487	0.8486	0.4748
0.5658	3.6364	140	0.5751	0.8487	0.8496	0.8487	0.8486	0.4748
0.5777	3.8961	150	0.5736	0.8487	0.8491	0.8487	0.8487	0.4832

Framework versions

Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1