tst-pt-gun_gub

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3706
• Bleu: 7.7265
• Gen Len: 63.152

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.7988	0.29	4000	2.5546	1.9592	58.376
2.3128	0.59	8000	2.1371	4.549	71.704
2.0843	0.88	12000	1.8790	5.7485	68.216
1.8776	1.18	16000	1.7351	6.2145	62.368
1.7898	1.47	20000	1.6494	6.7893	63.232
1.7111	1.77	24000	1.5318	7.4069	61.24
1.5854	2.06	28000	1.4736	8.2822	69.096
1.5539	2.36	32000	1.4256	8.0137	62.704
1.543	2.65	36000	1.3971	8.0144	62.144
1.5118	2.94	40000	1.3706	7.7265	63.152

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1