version2 with whole word data collator

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4527
+- Loss: 1.2834
 
 ## Model description
 
@@ -41,16 +41,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8154        | 1.0   | 263  | 1.5616          |
-| 1.6307        | 2.0   | 526  | 1.4782          |
-| 1.5819        | 3.0   | 789  | 1.4527          |
+| 1.4437        | 1.0   | 263  | 1.4178          |
+| 1.4236        | 2.0   | 526  | 1.3673          |
+| 1.4316        | 3.0   | 789  | 1.3320          |
+| 1.4174        | 4.0   | 1052 | 1.3123          |
+| 1.4015        | 5.0   | 1315 | 1.2988          |
+| 1.3922        | 6.0   | 1578 | 1.2834          |
 
 
 ### Framework versions

runs/Jan21_03-02-35_07470f48d53d/events.out.tfevents.1737428561.07470f48d53d.4654.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec8b7040c98a268073aa3a4d0c733854f3de9fbf865f3702b584cdd16d6d8d9
-size 7711
+oid sha256:af7202da8f7a1c0e07096a171242c123c592961c3319c592b28b3699323fb1ba
+size 8336