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-dataset3
   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: 0.0802
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
-- Rougelsum: 0.0
+- Loss: 1.4093
+- Accuracy: 0.128
+- Mse: 1.5841
+- Log-distance: 0.6809
+- S Score: 0.4800
 
 ## 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 |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 4.8701        | 1.0   | 500  | 0.1153          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.1204        | 2.0   | 1000 | 0.1054          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.1014        | 3.0   | 1500 | 0.0837          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0898        | 4.0   | 2000 | 0.0861          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.083         | 5.0   | 2500 | 0.0931          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0784        | 6.0   | 3000 | 0.0810          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0763        | 7.0   | 3500 | 0.0845          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 0.0743        | 8.0   | 4000 | 0.0802          | 0.0    | 0.0    | 0.0    | 0.0       |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mse    | Log-distance | S Score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------------:|:-------:|
+| 2.1991        | 1.0   | 250  | 1.5275          | 0.106    | 1.7120 | 0.7824       | 0.4048  |
+| 2.1115        | 2.0   | 500  | 1.5009          | 0.106    | 1.7469 | 0.8062       | 0.3844  |
+| 1.8295        | 3.0   | 750  | 1.4483          | 0.108    | 1.7239 | 0.7902       | 0.3972  |
+| 1.7033        | 4.0   | 1000 | 1.4335          | 0.112    | 1.7052 | 0.7759       | 0.4088  |
+| 1.6426        | 5.0   | 1250 | 1.4224          | 0.12     | 1.5337 | 0.6427       | 0.5112  |
+| 1.5923        | 6.0   | 1500 | 1.4236          | 0.126    | 1.6061 | 0.7015       | 0.4628  |
+| 1.5529        | 7.0   | 1750 | 1.4284          | 0.122    | 1.5984 | 0.6967       | 0.4676  |
+| 1.546         | 8.0   | 2000 | 1.4132          | 0.124    | 1.6032 | 0.6948       | 0.4704  |
+| 1.5364        | 9.0   | 2250 | 1.4306          | 0.116    | 1.6403 | 0.7282       | 0.4460  |
+| 1.5365        | 10.0  | 2500 | 1.4107          | 0.118    | 1.5702 | 0.6681       | 0.4948  |
+| 1.5145        | 11.0  | 2750 | 1.4182          | 0.118    | 1.6041 | 0.7063       | 0.4596  |
+| 1.5103        | 12.0  | 3000 | 1.4093          | 0.128    | 1.5841 | 0.6809       | 0.4800  |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.1.0+cu118
+- Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0