End of training

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # FirstTry
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0005
 
 ## Model description
 
@@ -40,13 +42,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 63   | 0.0016          |
+| No log        | 1.0   | 63   | 0.0009          |
+| No log        | 2.0   | 126  | 0.0006          |
+| No log        | 3.0   | 189  | 0.0005          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa124640a6a9b46ca38a0dd4a500cab01825a009fc671cb17a1ab3c3655c864
+oid sha256:1824b8774136a355093042a988149ae3771abb58de73b315a6de51ad345c56cf
 size 265470032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9ef528a783fe46c504130fc5b9398120e0f6c28ab4716a3b4acde17af0177f
+oid sha256:7e781d70ae6794b8783fce37c158d64adb55da0755d83537bcaf50e60978b3af
 size 4664