t5-base-translation-spa-guc

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0136
• Bleu: 1.4957
• Gen Len: 17.8854

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.3933	1.0	7668	1.5107	0.8563	18.0712
1.598	2.0	15336	1.3444	0.9626	18.0648
1.4277	3.0	23004	1.2551	1.1025	17.9695
1.4152	4.0	30672	1.2000	1.1361	17.9426
1.1671	5.0	38340	1.1565	1.2243	17.8416
1.1777	6.0	46008	1.1217	1.2874	17.8809
1.4485	7.0	53676	1.0955	1.3318	17.9663
1.3209	8.0	61344	1.0729	1.3889	17.967
1.394	9.0	69012	1.0557	1.4082	17.8646
1.0608	10.0	76680	1.0435	1.4463	17.9294
1.0713	11.0	84348	1.0323	1.4558	17.9015
0.976	12.0	92016	1.0248	1.4666	17.9103
1.0782	13.0	99684	1.0191	1.484	17.8929
1.045	14.0	107352	1.0150	1.4869	17.8875
0.9936	15.0	115020	1.0136	1.4957	17.8854

Framework versions

• Transformers 4.35.2
• Pytorch 1.13.1+cu117
• Datasets 2.15.0
• Tokenizers 0.15.0