End of training

README.md

@@ -4,7 +4,7 @@ base_model: google/mt5-small
 tags:
 - generated_from_trainer
 metrics:
-- rouge
+- accuracy
 model-index:
 - name: mt5-small-task3-dataset4
   results: []
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0208
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
-- Rougelsum: 0.0
+- Loss: 1.6010
+- Accuracy: 0.036
+- Mse: 6.3081
+- Log-distance: 0.6632
+- S Score: 0.4988
 
 ## Model description
 
@@ -41,30 +41,34 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- 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: 8
+- num_epochs: 12
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 3.225         | 1.0   | 500  | 0.0479          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0784        | 2.0   | 1000 | 0.0322          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0467        | 3.0   | 1500 | 0.0258          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0409        | 4.0   | 2000 | 0.0224          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0386        | 5.0   | 2500 | 0.0210          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0355        | 6.0   | 3000 | 0.0207          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0335        | 7.0   | 3500 | 0.0207          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0322        | 8.0   | 4000 | 0.0208          | 0.0    | 0.0    | 0.0    | 0.0       |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mse    | Log-distance | S Score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------------:|:-------:|
+| 10.7728       | 1.0   | 250  | 2.2587          | 0.022    | 7.0471 | 0.7963       | 0.4292  |
+| 3.1044        | 2.0   | 500  | 1.8035          | 0.014    | 5.9086 | 0.7763       | 0.4340  |
+| 2.3369        | 3.0   | 750  | 1.6404          | 0.058    | 7.0001 | 0.6805       | 0.4972  |
+| 2.0228        | 4.0   | 1000 | 1.6106          | 0.056    | 6.9718 | 0.6808       | 0.4948  |
+| 1.8688        | 5.0   | 1250 | 1.5910          | 0.044    | 5.8977 | 0.7091       | 0.4624  |
+| 1.8065        | 6.0   | 1500 | 1.6321          | 0.036    | 6.2658 | 0.6631       | 0.4992  |
+| 1.7671        | 7.0   | 1750 | 1.5987          | 0.058    | 6.9883 | 0.6792       | 0.4976  |
+| 1.7373        | 8.0   | 2000 | 1.6174          | 0.06     | 6.9132 | 0.6780       | 0.4960  |
+| 1.7366        | 9.0   | 2250 | 1.6105          | 0.042    | 6.6193 | 0.6712       | 0.4976  |
+| 1.7201        | 10.0  | 2500 | 1.6123          | 0.038    | 6.5863 | 0.6745       | 0.4960  |
+| 1.7171        | 11.0  | 2750 | 1.6034          | 0.032    | 6.1936 | 0.6719       | 0.4908  |
+| 1.7001        | 12.0  | 3000 | 1.6010          | 0.036    | 6.3081 | 0.6632       | 0.4988  |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.1.0+cu118
+- Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0