<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-small-squad-finetuned
This model is a fine-tuned version of lmqg/t5-small-squad on the qg_squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.8668
- Bleu: 0.1873
- Precisions: [0.5110525491352382, 0.245362761211552, 0.15215077757561193, 0.09884530767928974]
- Brevity Penalty: 0.8988
- Length Ratio: 0.9036
- Translation Length: 108527
- Reference Length: 120107
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length |
|---|---|---|---|---|---|---|---|---|---|
| 1.9131 | 1.0 | 2367 | 1.8960 | 0.1861 | [0.5106522785325583, 0.24527605096325475, 0.15213089101620028, 0.09826831888082575] | 0.8944 | 0.8996 | 108052 | 120107 |
| 1.849 | 2.0 | 4734 | 1.8806 | 0.1849 | [0.5080246970549962, 0.24224047124755838, 0.1501267012945318, 0.09769844997651479] | 0.8972 | 0.9021 | 108353 | 120107 |
| 1.8168 | 3.0 | 7101 | 1.8727 | 0.1854 | [0.5098220476080425, 0.24339941601352388, 0.15093927730223472, 0.09804485712417446] | 0.8956 | 0.9007 | 108175 | 120107 |
| 1.7923 | 4.0 | 9468 | 1.8700 | 0.1863 | [0.5133830790362698, 0.24615653748790878, 0.15267642711989654, 0.09868749835608512] | 0.8916 | 0.8971 | 107748 | 120107 |
| 1.7748 | 5.0 | 11835 | 1.8689 | 0.1869 | [0.5141749342160318, 0.24699161674176884, 0.1534446643289472, 0.0998958319598096] | 0.8898 | 0.8954 | 107549 | 120107 |
| 1.7587 | 6.0 | 14202 | 1.8698 | 0.1864 | [0.5146328972484753, 0.24659953524399691, 0.1532201031824242, 0.09970271520116271] | 0.8884 | 0.8942 | 107395 | 120107 |
| 1.7468 | 7.0 | 16569 | 1.8680 | 0.1860 | [0.5112671501824734, 0.24460144371064352, 0.15145530742292898, 0.09809866056844169] | 0.8961 | 0.9012 | 108235 | 120107 |
| 1.7378 | 8.0 | 18936 | 1.8670 | 0.1876 | [0.5122261914652045, 0.24610537728997678, 0.15275308797724588, 0.09927828458817849] | 0.8970 | 0.9020 | 108333 | 120107 |
| 1.7312 | 9.0 | 21303 | 1.8676 | 0.1876 | [0.5117292997446746, 0.24587669400218548, 0.15249172858304044, 0.0989853996535511] | 0.8984 | 0.9033 | 108489 | 120107 |
| 1.7271 | 10.0 | 23670 | 1.8668 | 0.1873 | [0.5110525491352382, 0.245362761211552, 0.15215077757561193, 0.09884530767928974] | 0.8988 | 0.9036 | 108527 | 120107 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1
