End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3846
+- Loss: 1.3039
 
 ## Model description
 
@@ -37,22 +37,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
+- train_batch_size: 10
+- eval_batch_size: 10
+- seed: 0
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9175        | 1.0   | 844  | 1.5880          |
-| 1.3592        | 2.0   | 1688 | 1.3049          |
-| 0.9444        | 3.0   | 2532 | 1.2852          |
-| 0.7299        | 4.0   | 3376 | 1.3328          |
-| 0.5885        | 5.0   | 4220 | 1.3846          |
+| 2.3688        | 1.0   | 1350 | 1.4871          |
+| 1.2342        | 2.0   | 2700 | 1.3039          |
+| 0.8185        | 3.0   | 4050 | 1.3300          |
+| 0.5646        | 4.0   | 5400 | 1.5053          |
+| 0.4032        | 5.0   | 6750 | 1.6240          |
+| 0.314         | 6.0   | 8100 | 1.7492          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153eea19850feb976c129f3794f7c52532ab1b21cbb9e0b2b01555dae4d1063a
+oid sha256:30216fcef907cc24138f696c613094ccc5372bc7cdfd3bab8044c8f5c38d8f2a
 size 260804645

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3004bbf7ce16ddc58419278186f47d22461bc5bc70664f0fc0c678a1070a4a0a
-size 4091
+oid sha256:af7b40f158b6d030a2d700d330bd149279208cf495c432ef44de4b5a809ea808
+size 4027