<!-- 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-squad
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8157
- Rouge1: 0.1335
- Rouge2: 0.0193
- Rougel: 0.1312
- Rougelsum: 0.1310
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: 1e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 0.53 | 100 | 3.2422 | 0.1221 | 0.0171 | 0.1210 | 0.1209 |
| No log | 1.06 | 200 | 2.9500 | 0.1248 | 0.0170 | 0.1224 | 0.1227 |
| No log | 1.6 | 300 | 2.8945 | 0.1258 | 0.0173 | 0.1229 | 0.1231 |
| No log | 2.13 | 400 | 2.8715 | 0.1295 | 0.0191 | 0.1270 | 0.1270 |
| 3.1266 | 2.66 | 500 | 2.8479 | 0.1299 | 0.0200 | 0.1275 | 0.1275 |
| 3.1266 | 3.19 | 600 | 2.8316 | 0.1307 | 0.0203 | 0.1285 | 0.1286 |
| 3.1266 | 3.72 | 700 | 2.8238 | 0.1324 | 0.0204 | 0.1301 | 0.1302 |
| 3.1266 | 4.26 | 800 | 2.8180 | 0.1339 | 0.0193 | 0.1316 | 0.1315 |
| 3.1266 | 4.79 | 900 | 2.8157 | 0.1335 | 0.0193 | 0.1312 | 0.1310 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
