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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4334
+- Loss: 1.6146
 
 ## Model description
 
@@ -40,15 +40,17 @@ 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: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 300  | 1.8635          |
-| 2.6754        | 2.0   | 600  | 1.4835          |
-| 2.6754        | 3.0   | 900  | 1.4334          |
+| No log        | 1.0   | 300  | 2.1727          |
+| 2.6798        | 2.0   | 600  | 1.6308          |
+| 2.6798        | 3.0   | 900  | 1.5381          |
+| 1.2117        | 4.0   | 1200 | 1.5742          |
+| 0.8388        | 5.0   | 1500 | 1.6146          |
 
 
 ### Framework versions

runs/Apr06_21-18-39_Asus/events.out.tfevents.1712434720.Asus.20544.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69974d631b6e8c9d364f77e84892fa19b8d3b36d36409c5de5a499ffc9b364b5
-size 6157
+oid sha256:c42075dbc8e904f21ba86c1d36b0956bf98abfc200a200ca3164ba835f0b1d4c
+size 6782