| # for training an idiomifier | |
| idiomifier: | |
| ver: m-1-2 | |
| desc: just overfitting the model, but on the entire PIE dataset. | |
| bart: facebook/bart-base | |
| lr: 0.0001 | |
| literal2idiomatic_ver: d-1-2 | |
| idioms_ver: d-1-2 | |
| max_epochs: 2 | |
| batch_size: 40 | |
| shuffle: true | |
| seed: 104 | |
| # for building & uploading datasets or tokenizer | |
| idioms: | |
| ver: d-1-3 | |
| description: the set of idioms in the traning set of literal2idiomatic_d-1-3. Definitions of them are added as well. | |
| literal2idiomatic: | |
| ver: d-1-3 | |
| description: The idioms are annotated with <idiom> & </idiom>. | |
| train_ratio: 0.8 | |
| seed: 104 | |
| boi_token: <idiom> | |
| eoi_token: </idiom> | |
| tokenizer: | |
| ver: t-1-1 | |
| description: A pretrained BartTokenizer. The idiom special tokens are pre-added. | |
| bart: facebook/bart-base | |
| boi_token: <idiom> | |
| eoi_token: </idiom> | |