README.md

metadata

license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
  - generated_from_trainer
model-index:
  - name: robbert-v2-dutch-base-finetuned-emotion-valence
    results: []

robbert-v2-dutch-base-finetuned-emotion-valence

This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0327
• Rmse: 0.1808

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
0.0887	1.0	25	0.0611	0.2472
0.044	2.0	50	0.0403	0.2008
0.0356	3.0	75	0.0435	0.2085
0.0301	4.0	100	0.0415	0.2038
0.0246	5.0	125	0.0377	0.1941
0.0224	6.0	150	0.0355	0.1885
0.0218	7.0	175	0.0379	0.1946
0.0174	8.0	200	0.0436	0.2088
0.0156	9.0	225	0.0361	0.1901
0.0138	10.0	250	0.0379	0.1947
0.0135	11.0	275	0.0386	0.1965
0.013	12.0	300	0.0402	0.2005
0.0125	13.0	325	0.0325	0.1804
0.0117	14.0	350	0.0349	0.1868
0.0109	15.0	375	0.0366	0.1914
0.0108	16.0	400	0.0382	0.1953
0.0091	17.0	425	0.0336	0.1833
0.0097	18.0	450	0.0325	0.1802
0.0098	19.0	475	0.0406	0.2014
0.0094	20.0	500	0.0330	0.1816
0.0088	21.0	525	0.0349	0.1868
0.0087	22.0	550	0.0337	0.1835
0.0079	23.0	575	0.0340	0.1845
0.0074	24.0	600	0.0372	0.1928
0.007	25.0	625	0.0345	0.1856
0.0072	26.0	650	0.0333	0.1824
0.0074	27.0	675	0.0308	0.1756
0.0071	28.0	700	0.0314	0.1772
0.0067	29.0	725	0.0314	0.1772
0.0065	30.0	750	0.0333	0.1824
0.0072	31.0	775	0.0337	0.1837
0.0065	32.0	800	0.0351	0.1873
0.0057	33.0	825	0.0330	0.1818
0.0067	34.0	850	0.0367	0.1915
0.0061	35.0	875	0.0358	0.1893
0.0062	36.0	900	0.0353	0.1879
0.006	37.0	925	0.0317	0.1779
0.0059	38.0	950	0.0331	0.1819
0.0058	39.0	975	0.0308	0.1755
0.0057	40.0	1000	0.0338	0.1838
0.0055	41.0	1025	0.0324	0.1800
0.0056	42.0	1050	0.0333	0.1824
0.0054	43.0	1075	0.0331	0.1819
0.0062	44.0	1100	0.0329	0.1813
0.0056	45.0	1125	0.0325	0.1802
0.0051	46.0	1150	0.0324	0.1801
0.0056	47.0	1175	0.0322	0.1795
0.0056	48.0	1200	0.0331	0.1818
0.0053	49.0	1225	0.0322	0.1794
0.0056	50.0	1250	0.0327	0.1808

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1