metadata

license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: segundaprueba
    results: []

segundaprueba

This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.7005
Accuracy: 0.455

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.183	0.16	20	1.4843	0.35
1.34	0.32	40	1.4466	0.35
1.265	0.48	60	1.3036	0.39
1.3107	0.64	80	1.2656	0.415
1.0969	0.8	100	1.2302	0.455
1.1958	0.96	120	1.2676	0.465
1.0183	1.12	140	1.2523	0.45
0.8682	1.28	160	1.2620	0.495
0.9	1.44	180	1.2779	0.485
0.9613	1.6	200	1.5713	0.36
0.9667	1.76	220	1.3170	0.465
1.0284	1.92	240	1.2343	0.5
0.8681	2.08	260	1.2968	0.49
0.7134	2.24	280	1.4032	0.44
0.7311	2.4	300	1.3624	0.46
0.61	2.56	320	1.4416	0.44
0.7033	2.7200	340	1.5110	0.46
0.5881	2.88	360	1.3926	0.475
0.6666	3.04	380	1.3896	0.49
0.4299	3.2	400	1.4787	0.47
0.3613	3.36	420	1.5145	0.48
0.4714	3.52	440	1.5547	0.46
0.4698	3.68	460	1.5584	0.44
0.3191	3.84	480	1.5748	0.475
0.4044	4.0	500	1.7353	0.44
0.2275	4.16	520	1.6115	0.46
0.3171	4.32	540	1.6326	0.46
0.2005	4.48	560	1.6569	0.47
0.3165	4.64	580	1.6955	0.46
0.2543	4.8	600	1.6887	0.465
0.186	4.96	620	1.7005	0.455

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1