TeeA/T5-Text2SQL-Bilingual

README.md

@@ -1,8 +1,9 @@
 ---
-license: apache-2.0
-base_model: cssupport/t5-small-awesome-text-to-sql
+base_model: TeeA/T5-Text2SQL-Bilingual
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: Text2SQL-Bilingual
   results: []
@@ -13,18 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Text2SQL-Bilingual
 
-This model is a fine-tuned version of [cssupport/t5-small-awesome-text-to-sql](https://huggingface.co/cssupport/t5-small-awesome-text-to-sql) on an unknown dataset.
+This model is a fine-tuned version of [TeeA/T5-Text2SQL-Bilingual](https://huggingface.co/TeeA/T5-Text2SQL-Bilingual) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.7774
-- eval_rouge1: 0.8291
-- eval_rouge2: 0.7099
-- eval_rougeL: 0.8137
-- eval_rougeLsum: 0.8138
-- eval_runtime: 58.4843
-- eval_samples_per_second: 8.549
-- eval_steps_per_second: 2.137
-- epoch: 9.0
-- step: 39501
+- Loss: 1.5456
+- Rouge1: 0.8237
+- Rouge2: 0.7136
+- Rougel: 0.8142
+- Rougelsum: 0.8137
 
 ## Model description
 
@@ -52,6 +48,22 @@ The following hyperparameters were used during training:
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 1.891         | 1.0   | 4389  | 1.7024          | 0.8289 | 0.7133 | 0.8163 | 0.8159    |
+| 1.8333        | 2.0   | 8778  | 1.6619          | 0.8220 | 0.7113 | 0.8091 | 0.8089    |
+| 1.7995        | 3.0   | 13167 | 1.6317          | 0.8213 | 0.7100 | 0.8102 | 0.8098    |
+| 1.7632        | 4.0   | 17556 | 1.6076          | 0.8189 | 0.7074 | 0.8081 | 0.8076    |
+| 1.7368        | 5.0   | 21945 | 1.5912          | 0.8219 | 0.7107 | 0.8106 | 0.8104    |
+| 1.7121        | 6.0   | 26334 | 1.5715          | 0.8177 | 0.7052 | 0.8062 | 0.8060    |
+| 1.7042        | 7.0   | 30723 | 1.5595          | 0.8210 | 0.7098 | 0.8104 | 0.8103    |
+| 1.688         | 8.0   | 35112 | 1.5515          | 0.8220 | 0.7111 | 0.8118 | 0.8114    |
+| 1.6647        | 9.0   | 39501 | 1.5482          | 0.8236 | 0.7122 | 0.8135 | 0.8131    |
+| 1.6854        | 10.0  | 43890 | 1.5456          | 0.8237 | 0.7136 | 0.8142 | 0.8137    |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cssupport/t5-small-awesome-text-to-sql",
+  "_name_or_path": "TeeA/T5-Text2SQL-Bilingual",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c36a5f2097b6b594941fc8cb61942eb579e58cc2f67b93c30ff6b0867e89a1
+oid sha256:8e8024809e80ca5fe00d16d4c2002416172fb9e557c4e626df2e81c257a8c738
 size 282739752

runs/Mar14_07-25-00_618cbbff9d2b/events.out.tfevents.1710401142.618cbbff9d2b.164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6df957355c7feff3d3a4da19c029d7686c70cc2e57f0ba3f507d04d3e2aa3fc
+size 29737

tokenizer_config.json

@@ -931,9 +931,13 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "legacy": true,
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11c4d0b009c3245e71020ca63ab25d427ab8fbcd3edbfa5bf3ce8306a515072a
+oid sha256:f44cba0bd3facf025c99a6b61ee18166b309f146d60ad60b18c987e3c31c5942
 size 5048