barto_exp1_10partition_modelo_asl3000

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: 0.1432
• Model Preparation Time: 0.0031
• Bleu Msl: 0
• Bleu 1 Msl: 0
• Bleu 2 Msl: 0
• Bleu 3 Msl: 0
• Bleu 4 Msl: 0
• Ter Msl: 100
• Bleu Asl: 0
• Bleu 1 Asl: 0.9666
• Bleu 2 Asl: 0.9452
• Bleu 3 Asl: 0.9194
• Bleu 4 Asl: 0.8890
• Ter Asl: 3.9051

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	0.2051	0.0031	0	0	0	0	0	100	0	0.9471	0.9166	0.8870	0.8548	6.7832
No log	2.0	150	0.1380	0.0031	0	0	0	0	0	100	0	0.9564	0.9316	0.9065	0.8757	5.1748
No log	3.0	225	0.1438	0.0031	0	0	0	0	0	100	0	0.9603	0.9361	0.9100	0.8804	5.1748
No log	4.0	300	0.1273	0.0031	0	0	0	0	0	100	0	0.9671	0.9470	0.9254	0.8985	3.9860
No log	5.0	375	0.1163	0.0031	0	0	0	0	0	100	0	0.9730	0.9557	0.9358	0.9114	3.4266
No log	6.0	450	0.1357	0.0031	0	0	0	0	0	100	0	0.9681	0.9474	0.9252	0.8985	3.9860
0.2716	7.0	525	0.1560	0.0031	0	0	0	0	0	100	0	0.9700	0.9521	0.9321	0.9069	3.6364
0.2716	8.0	600	0.1263	0.0031	0	0	0	0	0	100	0	0.9748	0.9585	0.9403	0.9171	2.9371
0.2716	9.0	675	0.1407	0.0031	0	0	0	0	0	100	0	0.9802	0.9663	0.9503	0.9300	2.3776
0.2716	10.0	750	0.1396	0.0031	0	0	0	0	0	100	0	0.9778	0.9633	0.9449	0.9217	2.7273
0.2716	11.0	825	0.1228	0.0031	0	0	0	0	0	100	0	0.9771	0.9636	0.9469	0.9263	3.0769
0.2716	12.0	900	0.1310	0.0031	0	0	0	0	0	100	0	0.9790	0.9661	0.9505	0.9301	2.5175
0.2716	13.0	975	0.1295	0.0031	0	0	0	0	0	100	0	0.9778	0.9648	0.9493	0.9296	2.7972
0.0167	14.0	1050	0.1349	0.0031	0	0	0	0	0	100	0	0.9766	0.9627	0.9461	0.9247	2.8671
0.0167	15.0	1125	0.1347	0.0031	0	0	0	0	0	100	0	0.9784	0.9643	0.9476	0.9266	2.8671
0.0167	16.0	1200	0.1330	0.0031	0	0	0	0	0	100	0	0.9772	0.9629	0.9455	0.9237	2.8671
0.0167	17.0	1275	0.1476	0.0031	0	0	0	0	0	100	0	0.9765	0.9624	0.9456	0.9244	3.0769
0.0167	18.0	1350	0.1475	0.0031	0	0	0	0	0	100	0	0.9754	0.9611	0.9441	0.9223	2.9371
0.0167	19.0	1425	0.1467	0.0031	0	0	0	0	0	100	0	0.9796	0.9660	0.9498	0.9290	2.4476
0.0061	20.0	1500	0.1371	0.0031	0	0	0	0	0	100	0	0.9778	0.9640	0.9468	0.9247	2.9371
0.0061	21.0	1575	0.1331	0.0031	0	0	0	0	0	100	0	0.9784	0.9647	0.9482	0.9271	2.7273
0.0061	22.0	1650	0.1366	0.0031	0	0	0	0	0	100	0	0.9771	0.9627	0.9449	0.9219	2.8671
0.0061	23.0	1725	0.1247	0.0031	0	0	0	0	0	100	0	0.9808	0.9684	0.9532	0.9337	2.3077
0.0061	24.0	1800	0.1282	0.0031	0	0	0	0	0	100	0	0.9808	0.9688	0.9537	0.9341	2.3776
0.0061	25.0	1875	0.1286	0.0031	0	0	0	0	0	100	0	0.9814	0.9698	0.9554	0.9366	2.3077
0.0061	26.0	1950	0.1291	0.0031	0	0	0	0	0	100	0	0.9814	0.9698	0.9553	0.9365	2.3077
0.0013	27.0	2025	0.1287	0.0031	0	0	0	0	0	100	0	0.9808	0.9688	0.9537	0.9344	2.3776
0.0013	28.0	2100	0.1303	0.0031	0	0	0	0	0	100	0	0.9802	0.9678	0.9521	0.9319	2.4476
0.0013	29.0	2175	0.1308	0.0031	0	0	0	0	0	100	0	0.9802	0.9678	0.9521	0.9319	2.4476
0.0013	30.0	2250	0.1309	0.0031	0	0	0	0	0	100	0	0.9802	0.9678	0.9521	0.9319	2.4476

Framework versions

• Transformers 4.51.1
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1