exp1_10partition_modelo_msl3000

This model is a fine-tuned version of vgaraujov/bart-base-spanish on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6555
• Model Preparation Time: 0.0043
• Bleu Msl: 0
• Bleu 1 Msl: 0.7733
• Bleu 2 Msl: 0.7239
• Bleu 3 Msl: 0.6660
• Bleu 4 Msl: 0.5599
• Ter Msl: 27.7311
• Bleu Asl: 0
• Bleu 1 Asl: 0
• Bleu 2 Asl: 0
• Bleu 3 Asl: 0
• Bleu 4 Asl: 0
• Ter Asl: 100

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Bleu Msl	Bleu 1 Msl	Bleu 2 Msl	Bleu 3 Msl	Bleu 4 Msl	Ter Msl	Bleu Asl	Bleu 1 Asl	Bleu 2 Asl	Bleu 3 Asl	Bleu 4 Asl	Ter Asl
No log	1.0	75	2.2335	0.0043	0	0.4775	0.3198	0.2148	0.1159	61.0647	0	0	0	0	0	100
No log	2.0	150	1.4608	0.0043	0	0.7664	0.6924	0.5970	0.4301	39.1441	0	0	0	0	0	100
No log	3.0	225	1.2861	0.0043	0	0.7181	0.6372	0.5454	0.4047	41.7537	0	0	0	0	0	100
No log	4.0	300	1.3358	0.0043	0	0.7238	0.6377	0.5408	0.3908	41.4405	0	0	0	0	0	100
No log	5.0	375	1.3312	0.0043	0	0.7741	0.6968	0.5963	0.4133	39.2484	0	0	0	0	0	100
No log	6.0	450	1.3337	0.0043	0	0.7785	0.7017	0.6054	0.4223	36.0125	0	0	0	0	0	100
1.1867	7.0	525	1.4274	0.0043	0	0.7568	0.6730	0.5668	0.3785	40.1879	0	0	0	0	0	100
1.1867	8.0	600	1.4615	0.0043	0	0.7202	0.6310	0.5224	0.3376	41.5449	0	0	0	0	0	100
1.1867	9.0	675	1.4116	0.0043	0	0.7328	0.6473	0.5479	0.3763	39.1441	0	0	0	0	0	100
1.1867	10.0	750	1.5938	0.0043	0	0.6833	0.6011	0.5069	0.3513	45.9290	0	0	0	0	0	100
1.1867	11.0	825	1.5407	0.0043	0	0.6913	0.6042	0.5062	0.3426	46.7641	0	0	0	0	0	100
1.1867	12.0	900	1.5493	0.0043	0	0.7533	0.6734	0.5739	0.3849	38.8309	0	0	0	0	0	100
1.1867	13.0	975	1.5355	0.0043	0	0.7013	0.6139	0.5029	0.3307	42.1712	0	0	0	0	0	100
0.088	14.0	1050	1.5902	0.0043	0	0.7335	0.6477	0.5398	0.3471	40.5010	0	0	0	0	0	100
0.088	15.0	1125	1.6769	0.0043	0	0.7415	0.6570	0.5534	0.3644	39.9791	0	0	0	0	0	100
0.088	16.0	1200	1.5847	0.0043	0	0.7202	0.6349	0.5387	0.3707	42.1712	0	0	0	0	0	100
0.088	17.0	1275	1.5717	0.0043	0	0.7257	0.6395	0.5369	0.3552	39.8747	0	0	0	0	0	100
0.088	18.0	1350	1.5541	0.0043	0	0.6389	0.5517	0.4405	0.2771	47.3904	0	0	0	0	0	100
0.088	19.0	1425	1.5610	0.0043	0	0.7105	0.6261	0.5124	0.3278	43.6326	0	0	0	0	0	100
0.0332	20.0	1500	1.4844	0.0043	0	0.6915	0.6006	0.4896	0.3121	45.6159	0	0	0	0	0	100
0.0332	21.0	1575	1.6116	0.0043	0	0.7221	0.6344	0.5267	0.3403	41.1273	0	0	0	0	0	100
0.0332	22.0	1650	1.5743	0.0043	0	0.6760	0.5882	0.4842	0.3093	45.9290	0	0	0	0	0	100
0.0332	23.0	1725	1.5927	0.0043	0	0.6800	0.5921	0.4861	0.3077	46.0334	0	0	0	0	0	100
0.0332	24.0	1800	1.5832	0.0043	0	0.7338	0.6492	0.5386	0.3470	40.7098	0	0	0	0	0	100
0.0332	25.0	1875	1.6395	0.0043	0	0.6888	0.6004	0.4927	0.3091	43.7370	0	0	0	0	0	100
0.0332	26.0	1950	1.6098	0.0043	0	0.6822	0.5971	0.4914	0.3143	43.0063	0	0	0	0	0	100
0.018	27.0	2025	1.6397	0.0043	0	0.6395	0.5506	0.4462	0.2808	47.0772	0	0	0	0	0	100
0.018	28.0	2100	1.6369	0.0043	0	0.6710	0.5837	0.4790	0.3075	43.8413	0	0	0	0	0	100
0.018	29.0	2175	1.6332	0.0043	0	0.6957	0.6103	0.5038	0.3213	43.6326	0	0	0	0	0	100
0.018	30.0	2250	1.6267	0.0043	0	0.6993	0.6140	0.5074	0.3252	43.0063	0	0	0	0	0	100

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1