train_4

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 5000
num_epochs: 200

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf	Meteor	Gen Len
0.0315	1.0	7999	0.2397	41.3664	62.1386	0.6072	12.0471
0.031	2.0	15998	0.2417	41.2882	61.9925	0.6082	12.0537
0.0308	3.0	23997	0.2431	41.3403	62.1009	0.607	12.0402
0.0307	4.0	31996	0.2440	41.3147	62.0719	0.6058	12.0619
0.03	5.0	39995	0.2460	41.5271	62.2126	0.6075	12.0566
0.0294	6.0	47994	0.2482	41.4353	62.1959	0.6087	12.0842
0.0294	7.0	55993	0.2486	41.2568	62.2425	0.608	12.0799
0.029	8.0	63992	0.2501	41.1446	62.0782	0.6069	12.0694
0.0285	9.0	71991	0.2489	41.1554	61.9691	0.606	12.0449
0.0283	10.0	79990	0.2518	40.9903	62.0095	0.607	12.0369
0.0278	11.0	87989	0.2523	41.0357	62.2308	0.6075	12.0701
0.028	12.0	95988	0.2534	40.7796	61.9287	0.6058	12.0524
0.0275	13.0	103987	0.2546	41.2298	62.1716	0.6072	12.0691
0.027	14.0	111986	0.2565	41.0546	62.0676	0.6068	12.0681
0.0269	15.0	119985	0.2577	41.2507	62.1826	0.6075	12.0539
0.0265	16.0	127984	0.2578	41.0927	62.1228	0.607	12.0877
0.0265	17.0	135983	0.2609	41.0459	62.1203	0.607	12.067
0.0258	18.0	143982	0.2632	41.0598	62.0328	0.6064	12.077
0.0259	19.0	151981	0.2606	41.1115	62.1225	0.6077	12.0667
0.0256	20.0	159980	0.2634	41.2138	62.1018	0.6063	12.0513