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	Ter Msl	Bleu 1 Asl	Bleu 2 Asl	Bleu 3 Asl	Bleu 4 Asl	Ter Asl
No log	1.0	75	0.3680	0.0033	100	0.9200	0.8733	0.8279	0.7802	9.4535
No log	2.0	150	0.1993	0.0033	100	0.9440	0.9095	0.8751	0.8371	6.4993
No log	3.0	225	0.2036	0.0033	100	0.9440	0.9070	0.8710	0.8333	6.6470
No log	4.0	300	0.1912	0.0033	100	0.9504	0.9183	0.8831	0.8440	5.6869
No log	5.0	375	0.1672	0.0033	100	0.8265	0.7909	0.7530	0.7063	5.1699
No log	6.0	450	0.1718	0.0033	100	0.9557	0.9258	0.8934	0.8576	4.9483
0.221	7.0	525	0.1878	0.0033	100	0.9556	0.9258	0.8936	0.8588	5.0222
0.221	8.0	600	0.1764	0.0033	100	0.9602	0.9333	0.9038	0.8729	4.3575
0.221	9.0	675	0.1879	0.0033	100	0.9607	0.9331	0.9028	0.8688	4.6529
0.221	10.0	750	0.1873	0.0033	100	0.9633	0.9368	0.9076	0.8754	4.2097
0.221	11.0	825	0.1869	0.0033	100	0.9595	0.9317	0.9020	0.8703	4.4313
0.221	12.0	900	0.1909	0.0033	100	0.9608	0.9339	0.9045	0.8732	4.4313
0.221	13.0	975	0.1881	0.0033	100	0.9620	0.9365	0.9094	0.8798	4.3575
0.0123	14.0	1050	0.1858	0.0033	100	0.9601	0.9340	0.9059	0.8756	4.6529
0.0123	15.0	1125	0.1826	0.0033	100	0.9639	0.9391	0.9114	0.8817	4.2836
0.0123	16.0	1200	0.1943	0.0033	100	0.9583	0.9308	0.9012	0.8691	4.6529
0.0123	17.0	1275	0.1968	0.0033	100	0.9608	0.9349	0.9062	0.8746	4.4313
0.0123	18.0	1350	0.2080	0.0033	100	0.9589	0.9315	0.9023	0.8706	4.6529
0.0123	19.0	1425	0.2031	0.0033	100	0.9608	0.9352	0.9074	0.8779	4.5052
0.0043	20.0	1500	0.1940	0.0033	100	0.9608	0.9353	0.9075	0.8777	4.4313
0.0043	21.0	1575	0.1980	0.0033	100	0.9608	0.9357	0.9084	0.8794	4.4313
0.0043	22.0	1650	0.1998	0.0033	100	0.9589	0.9318	0.9024	0.8703	4.7267
0.0043	23.0	1725	0.1979	0.0033	100	0.9640	0.9396	0.9129	0.8840	4.2836
0.0043	24.0	1800	0.1979	0.0033	100	0.9627	0.9378	0.9104	0.8808	4.2836
0.0043	25.0	1875	0.2000	0.0033	100	0.9608	0.9352	0.9070	0.8769	4.5052
0.0043	26.0	1950	0.2024	0.0033	100	0.9615	0.9356	0.9070	0.8765	4.3575
0.0023	27.0	2025	0.2016	0.0033	100	0.9608	0.9349	0.9061	0.8756	4.4313
0.0023	28.0	2100	0.2015	0.0033	100	0.9614	0.9359	0.9078	0.8775	4.4313
0.0023	29.0	2175	0.2024	0.0033	100	0.9614	0.9359	0.9078	0.8775	4.4313
0.0023	30.0	2250	0.2027	0.0033	100	0.9614	0.9359	0.9078	0.8775	4.4313

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

vania2911/exp4_10partition_modelo_asl3000

exp4_10partition_modelo_asl3000

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

vania2911/
exp4_10partition_modelo_asl3000