End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1652
+- Loss: 0.1618
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- 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
@@ -45,27 +45,41 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.3755        | 0.21  | 500  | 0.3205          |
-| 0.3306        | 0.43  | 1000 | 0.2600          |
-| 0.2602        | 0.64  | 1500 | 0.2322          |
-| 0.2603        | 0.86  | 2000 | 0.2078          |
-| 0.1898        | 1.07  | 2500 | 0.1976          |
-| 0.2054        | 1.28  | 3000 | 0.1907          |
-| 0.1807        | 1.5   | 3500 | 0.1841          |
-| 0.1843        | 1.71  | 4000 | 0.1781          |
-| 0.1655        | 1.93  | 4500 | 0.1728          |
-| 0.1419        | 2.14  | 5000 | 0.1745          |
-| 0.1367        | 2.35  | 5500 | 0.1700          |
-| 0.1277        | 2.57  | 6000 | 0.1665          |
-| 0.1328        | 2.78  | 6500 | 0.1661          |
-| 0.1472        | 3.0   | 7000 | 0.1652          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.4682        | 0.11  | 500   | 0.3839          |
+| 0.3647        | 0.21  | 1000  | 0.3068          |
+| 0.3853        | 0.32  | 1500  | 0.2709          |
+| 0.3194        | 0.43  | 2000  | 0.2515          |
+| 0.2892        | 0.54  | 2500  | 0.2369          |
+| 0.2493        | 0.64  | 3000  | 0.2202          |
+| 0.252         | 0.75  | 3500  | 0.2132          |
+| 0.2467        | 0.86  | 4000  | 0.1982          |
+| 0.2539        | 0.96  | 4500  | 0.1948          |
+| 0.1639        | 1.07  | 5000  | 0.1917          |
+| 0.1732        | 1.18  | 5500  | 0.1889          |
+| 0.1593        | 1.28  | 6000  | 0.1932          |
+| 0.1884        | 1.39  | 6500  | 0.1803          |
+| 0.1889        | 1.5   | 7000  | 0.1804          |
+| 0.1638        | 1.61  | 7500  | 0.1787          |
+| 0.1295        | 1.71  | 8000  | 0.1754          |
+| 0.2087        | 1.82  | 8500  | 0.1692          |
+| 0.147         | 1.93  | 9000  | 0.1700          |
+| 0.1269        | 2.03  | 9500  | 0.1725          |
+| 0.1214        | 2.14  | 10000 | 0.1693          |
+| 0.1124        | 2.25  | 10500 | 0.1717          |
+| 0.1169        | 2.35  | 11000 | 0.1654          |
+| 0.1136        | 2.46  | 11500 | 0.1658          |
+| 0.1217        | 2.57  | 12000 | 0.1630          |
+| 0.1287        | 2.68  | 12500 | 0.1631          |
+| 0.0997        | 2.78  | 13000 | 0.1622          |
+| 0.1094        | 2.89  | 13500 | 0.1623          |
+| 0.1051        | 3.0   | 14000 | 0.1618          |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
-- Pytorch 2.0.1
-- Datasets 2.14.5
-- Tokenizers 0.13.3
+- Transformers 4.34.1
+- Pytorch 2.1.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

generation_config.json

@@ -9,5 +9,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.33.3"
+  "transformers_version": "4.34.1"
 }