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	0.3093	0.0033	100	0.9375	0.8972	0.8554	0.8140	7.9940
No log	2.0	150	0.1597	0.0033	100	0.9518	0.9183	0.8819	0.8451	6.0332
No log	3.0	225	0.1440	0.0033	100	0.9592	0.9299	0.8962	0.8620	4.9774
No log	4.0	300	0.1384	0.0033	100	0.9566	0.9266	0.8926	0.8565	5.2036
No log	5.0	375	0.1177	0.0033	100	0.9637	0.9394	0.9110	0.8813	4.3741
No log	6.0	450	0.1189	0.0033	100	0.9604	0.9329	0.9025	0.8716	4.7511
0.2212	7.0	525	0.1211	0.0033	100	0.9637	0.9382	0.9091	0.8787	4.3741
0.2212	8.0	600	0.1220	0.0033	100	0.9637	0.9379	0.9076	0.8766	4.3741
0.2212	9.0	675	0.1243	0.0033	100	0.9643	0.9376	0.9076	0.8764	4.2986
0.2212	10.0	750	0.1168	0.0033	100	0.9643	0.9388	0.9094	0.8795	4.3741
0.2212	11.0	825	0.1232	0.0033	100	0.9682	0.9448	0.9182	0.8908	3.8462
0.2212	12.0	900	0.1250	0.0033	100	0.9682	0.9452	0.9195	0.8928	3.8462
0.2212	13.0	975	0.1289	0.0033	100	0.9675	0.9441	0.9170	0.8891	3.9216
0.0127	14.0	1050	0.1281	0.0033	100	0.9688	0.9460	0.9182	0.8893	3.8462
0.0127	15.0	1125	0.1210	0.0033	100	0.9701	0.9478	0.9208	0.8927	3.6953
0.0127	16.0	1200	0.1203	0.0033	100	0.9701	0.9482	0.9221	0.8946	3.6199
0.0127	17.0	1275	0.1154	0.0033	100	0.9727	0.9519	0.9276	0.9027	3.3183
0.0127	18.0	1350	0.1243	0.0033	100	0.9695	0.9471	0.9214	0.8948	3.6953
0.0127	19.0	1425	0.1180	0.0033	100	0.9708	0.9489	0.9233	0.8963	3.5445
0.0046	20.0	1500	0.1296	0.0033	100	0.9688	0.9464	0.9206	0.8940	3.7707
0.0046	21.0	1575	0.1250	0.0033	100	0.9682	0.9452	0.9181	0.8904	3.9216
0.0046	22.0	1650	0.1243	0.0033	100	0.9688	0.9464	0.9196	0.8921	3.8462
0.0046	23.0	1725	0.1271	0.0033	100	0.9701	0.9482	0.9221	0.8954	3.6953
0.0046	24.0	1800	0.1294	0.0033	100	0.9701	0.9478	0.9218	0.8952	3.6199
0.0046	25.0	1875	0.1229	0.0033	100	0.9695	0.9471	0.9203	0.8930	3.7707
0.0046	26.0	1950	0.1247	0.0033	100	0.9701	0.9482	0.9214	0.8938	3.6953
0.0024	27.0	2025	0.1225	0.0033	100	0.9701	0.9482	0.9214	0.8938	3.6953
0.0024	28.0	2100	0.1238	0.0033	100	0.9701	0.9482	0.9214	0.8938	3.6953
0.0024	29.0	2175	0.1236	0.0033	100	0.9695	0.9471	0.9203	0.8930	3.7707
0.0024	30.0	2250	0.1238	0.0033	100	0.9695	0.9471	0.9203	0.8930	3.7707

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

vania2911/exp5_10partition_modelo_asl3000

exp5_10partition_modelo_asl3000

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

vania2911/
exp5_10partition_modelo_asl3000