FYP19
/

t5-small-finetuned-sql3

Text2Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

FYP19 commited on Jun 10, 2023

Commit

7165e50

•

1 Parent(s): 07720cf

update model card README.md

Files changed (1) hide show

README.md +14 -13

README.md CHANGED Viewed

@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [FYP19/t5-small-finetuned-wikisql](https://huggingface.co/FYP19/t5-small-finetuned-wikisql) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1196
-- Rouge2 Precision: 0.6028
-- Rouge2 Recall: 0.386
-- Rouge2 Fmeasure: 0.4419
 ## Model description
@@ -37,22 +37,23 @@ More information needed
 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: 5
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
-|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
-| 0.1554        | 1.0   | 1313 | 0.1346          | 0.5174           | 0.3275        | 0.373           |
-| 0.0965        | 2.0   | 2626 | 0.1237          | 0.5887           | 0.3811        | 0.4349          |
-| 0.0843        | 3.0   | 3939 | 0.1203          | 0.5985           | 0.3831        | 0.4387          |
-| 0.0745        | 4.0   | 5252 | 0.1200          | 0.5999           | 0.3865        | 0.4417          |
-| 0.0718        | 5.0   | 6565 | 0.1196          | 0.6028           | 0.386         | 0.4419          |
 ### Framework versions

 This model is a fine-tuned version of [FYP19/t5-small-finetuned-wikisql](https://huggingface.co/FYP19/t5-small-finetuned-wikisql) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0581
+- Rouge2 Precision: 0.6546
+- Rouge2 Recall: 0.4183
+- Rouge2 Fmeasure: 0.4794
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
 - num_epochs: 5
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
+|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
+| 0.0446        | 1.0   | 5250  | 0.0595          | 0.5997           | 0.3824        | 0.4385          |
+| 0.0301        | 2.0   | 10500 | 0.0573          | 0.6439           | 0.4169        | 0.476           |
+| 0.0256        | 3.0   | 15750 | 0.0564          | 0.642            | 0.4093        | 0.4695          |
+| 0.0222        | 4.0   | 21000 | 0.0581          | 0.6487           | 0.4165        | 0.4769          |
+| 0.0218        | 5.0   | 26250 | 0.0581          | 0.6546           | 0.4183        | 0.4794          |
 ### Framework versions