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: stocks
    results: []

stocks

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: 0.6733
Accuracy: 0.8109
Precision: 0.8127
Recall: 0.8109
F1: 0.8107
Ratio: 0.5378

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: 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: 2
label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Ratio
3.8156	0.1626	10	1.9553	0.5378	0.5507	0.5378	0.5064	0.7521
1.3339	0.3252	20	1.2090	0.5546	0.5548	0.5546	0.5543	0.5252
1.103	0.4878	30	0.9577	0.5588	0.5588	0.5588	0.5588	0.5042
0.9108	0.6504	40	0.8881	0.5714	0.5770	0.5714	0.5635	0.6345
0.8716	0.8130	50	0.8426	0.6387	0.6563	0.6387	0.6282	0.6681
0.844	0.9756	60	0.7948	0.7017	0.7233	0.7017	0.6943	0.3445
0.7816	1.1382	70	0.7715	0.7227	0.7660	0.7227	0.7109	0.7017
0.7406	1.3008	80	0.7040	0.8067	0.8099	0.8067	0.8062	0.5504
0.6764	1.4634	90	0.6954	0.8025	0.8104	0.8025	0.8013	0.5798
0.7306	1.6260	100	0.6933	0.8109	0.8209	0.8109	0.8094	0.5882
0.6736	1.7886	110	0.6763	0.8067	0.8089	0.8067	0.8064	0.5420
0.714	1.9512	120	0.6733	0.8109	0.8127	0.8109	0.8107	0.5378

Framework versions

Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1