exp1_10partition_modelo3000

This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-es on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9610
• Model Preparation Time: 0.0033
• Bleu Msl: 0
• Bleu 1 Msl: 0.8568
• Bleu 2 Msl: 0.7706
• Bleu 3 Msl: 0.6480
• Bleu 4 Msl: 0.5159
• Ter Msl: 21.6856
• 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	2.4535	0.0033	0	0.5307	0.3133	0.1706	0.0632	67.2850	0	0	0	0	0	100
No log	2.0	150	2.1474	0.0033	0	0.5321	0.3431	0.2027	0.1160	68.7184	0	0	0	0	0	100
No log	3.0	225	2.0004	0.0033	0	0.5274	0.3649	0.2433	0.1556	67.7066	0	0	0	0	0	100
No log	4.0	300	2.0284	0.0033	0	0.4805	0.3371	0.2262	0.1445	76.4755	0	0	0	0	0	100
No log	5.0	375	1.9322	0.0033	0	0.5986	0.4453	0.3150	0.2136	52.7825	0	0	0	0	0	100
No log	6.0	450	2.0577	0.0033	0	0.6499	0.5043	0.3926	0.3065	49.2411	0	0	0	0	0	100
0.56	7.0	525	2.1728	0.0033	0	0.6183	0.4642	0.3378	0.2219	52.1922	0	0	0	0	0	100
0.56	8.0	600	2.2936	0.0033	0	0.4600	0.3099	0.2008	0.1259	73.6088	0	0	0	0	0	100
0.56	9.0	675	2.0849	0.0033	0	0.6962	0.5335	0.4224	0.3273	49.1568	0	0	0	0	0	100
0.56	10.0	750	2.0557	0.0033	0	0.6408	0.4865	0.3668	0.2658	50.5059	0	0	0	0	0	100
0.56	11.0	825	2.2431	0.0033	0	0.5574	0.4058	0.2808	0.1780	53.8786	0	0	0	0	0	100
0.56	12.0	900	2.0426	0.0033	0	0.6569	0.4914	0.3635	0.2538	50.4216	0	0	0	0	0	100
0.56	13.0	975	2.1992	0.0033	0	0.6318	0.4709	0.3437	0.2325	51.4334	0	0	0	0	0	100
0.0455	14.0	1050	2.1651	0.0033	0	0.6463	0.4977	0.3803	0.2796	47.9764	0	0	0	0	0	100
0.0455	15.0	1125	2.2092	0.0033	0	0.6556	0.4884	0.3510	0.2458	53.5413	0	0	0	0	0	100
0.0455	16.0	1200	2.1342	0.0033	0	0.6886	0.5282	0.4028	0.2950	49.7470	0	0	0	0	0	100
0.0455	17.0	1275	2.1668	0.0033	0	0.6517	0.4995	0.3862	0.2940	50.0843	0	0	0	0	0	100
0.0455	18.0	1350	2.1777	0.0033	0	0.6503	0.4926	0.3731	0.2711	51.6863	0	0	0	0	0	100
0.0455	19.0	1425	2.2567	0.0033	0	0.6661	0.5120	0.3912	0.2934	48.9882	0	0	0	0	0	100
0.0209	20.0	1500	2.2123	0.0033	0	0.6685	0.5187	0.4081	0.3183	48.3980	0	0	0	0	0	100
0.0209	21.0	1575	2.2715	0.0033	0	0.6566	0.5012	0.3841	0.2893	48.9039	0	0	0	0	0	100
0.0209	22.0	1650	2.2539	0.0033	0	0.6533	0.4907	0.3675	0.2623	51.2648	0	0	0	0	0	100
0.0209	23.0	1725	2.2624	0.0033	0	0.6578	0.4998	0.3782	0.2715	49.4098	0	0	0	0	0	100
0.0209	24.0	1800	2.2808	0.0033	0	0.6400	0.4786	0.3568	0.2543	51.0118	0	0	0	0	0	100
0.0209	25.0	1875	2.2665	0.0033	0	0.6492	0.4911	0.3707	0.2698	50.5059	0	0	0	0	0	100
0.0209	26.0	1950	2.2563	0.0033	0	0.6454	0.4823	0.3569	0.2506	51.0961	0	0	0	0	0	100
0.0141	27.0	2025	2.2610	0.0033	0	0.6491	0.4892	0.3669	0.2658	50.7589	0	0	0	0	0	100
0.0141	28.0	2100	2.2689	0.0033	0	0.6498	0.4895	0.3684	0.2674	50.3373	0	0	0	0	0	100
0.0141	29.0	2175	2.2707	0.0033	0	0.6506	0.4901	0.3688	0.2678	50.0843	0	0	0	0	0	100
0.0141	30.0	2250	2.2715	0.0033	0	0.6506	0.4901	0.3688	0.2678	50.0843	0	0	0	0	0	100

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1