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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1765
+- Loss: 0.1954
 
 ## Model description
 
@@ -41,16 +41,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 3
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2978        | 1.0   | 212  | 0.2297          |
-| 0.2449        | 2.0   | 424  | 0.2045          |
-| 0.1563        | 3.0   | 636  | 0.1765          |
+| 0.3049        | 1.0   | 212  | 0.2576          |
+| 0.223         | 2.0   | 424  | 0.2146          |
+| 0.1743        | 3.0   | 636  | 0.1954          |
+| 0.1553        | 4.0   | 848  | 0.2001          |
+| 0.1325        | 5.0   | 1060 | 0.2053          |
+| 0.1116        | 6.0   | 1272 | 0.2037          |
+| 0.099         | 7.0   | 1484 | 0.2124          |
+| 0.0845        | 8.0   | 1696 | 0.2265          |
+| 0.0607        | 9.0   | 1908 | 0.2339          |
+| 0.0548        | 10.0  | 2120 | 0.2390          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5aab926a0fd47b4c3cc9c26d21550e226974e4e4e910c2c40a91c4ed67caed0
+oid sha256:cf63be65db144c55e43f4f38089b18d485f38c5e3274bcd0f70ea587498d42dd
 size 557912620

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2208b8691625fac0549e4c585b2b7a030f1a156846516ea3103940cd5bdfa2d
+oid sha256:004ae601dd7135e019c109910b20e0b80bf2622f7887afe0e4d05b2b9edc199c
 size 4603