End of training

README.md

@@ -1,6 +1,7 @@
 ---
-base_model: facebook/bart-base
+library_name: transformers
 license: apache-2.0
+base_model: facebook/bart-base
 tags:
 - generated_from_trainer
 model-index:
@@ -15,7 +16,7 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0190
+- Loss: 0.0659
 
 ## Model description
 
@@ -44,25 +45,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step  | Validation Loss |
-|:-------------:|:------:|:-----:|:---------------:|
-| 0.3959        | 0.2440 | 1000  | 0.0680          |
-| 0.0739        | 0.4879 | 2000  | 0.0496          |
-| 0.0593        | 0.7319 | 3000  | 0.0397          |
-| 0.0506        | 0.9758 | 4000  | 0.0351          |
-| 0.0432        | 1.2198 | 5000  | 0.0308          |
-| 0.0397        | 1.4638 | 6000  | 0.0275          |
-| 0.0362        | 1.7077 | 7000  | 0.0253          |
-| 0.0347        | 1.9517 | 8000  | 0.0231          |
-| 0.0305        | 2.1957 | 9000  | 0.0222          |
-| 0.0288        | 2.4396 | 10000 | 0.0206          |
-| 0.0272        | 2.6836 | 11000 | 0.0196          |
-| 0.0264        | 2.9275 | 12000 | 0.0190          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4324        | 1.1641 | 1000 | 0.0876          |
+| 0.0963        | 2.3283 | 2000 | 0.0659          |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
-- Datasets 2.21.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
 - Tokenizers 0.19.1

generation_config.json

@@ -9,5 +9,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.44.2"
 }