End of training

README.md

@@ -15,18 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0554
-- Name Student Precision: 0.9535
+- Loss: 0.0466
+- Name Student Precision: 0.8966
 - Name Student Recall: 1.0
-- Name Student F1: 0.9762
-- Name Student Number: 41
-- Url Personal Precision: 0.0
-- Url Personal Recall: 0.0
-- Url Personal F1: 0.0
-- Url Personal Number: 1
-- Overall Precision: 0.9535
-- Overall Recall: 0.9762
-- Overall F1: 0.9647
+- Name Student F1: 0.9455
+- Name Student Number: 26
+- Overall Precision: 0.8966
+- Overall Recall: 1.0
+- Overall F1: 0.9455
 - Overall Accuracy: 0.9925
 
 ## Model description
@@ -60,10 +56,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Name Student Precision | Name Student Recall | Name Student F1 | Name Student Number | Url Personal Precision | Url Personal Recall | Url Personal F1 | Url Personal Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.0023        | 1.0   | 100  | 0.0549          | 0.9535                 | 1.0                 | 0.9762          | 41                  | 0.0                    | 0.0                 | 0.0             | 1                   | 0.9535            | 0.9762         | 0.9647     | 0.9925           |
-| 0.0009        | 2.0   | 200  | 0.0554          | 0.9535                 | 1.0                 | 0.9762          | 41                  | 0.0                    | 0.0                 | 0.0             | 1                   | 0.9535            | 0.9762         | 0.9647     | 0.9925           |
+| Training Loss | Epoch | Step | Validation Loss | Name Student Precision | Name Student Recall | Name Student F1 | Name Student Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.0012        | 1.0   | 100  | 0.0555          | 0.8966                 | 1.0                 | 0.9455          | 26                  | 0.8966            | 1.0            | 0.9455     | 0.9925           |
+| 0.0009        | 2.0   | 200  | 0.0466          | 0.8966                 | 1.0                 | 0.9455          | 26                  | 0.8966            | 1.0            | 0.9455     | 0.9925           |
 
 
 ### Framework versions

config.json

@@ -69,5 +69,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "type_vocab_size": 1,
-  "vocab_size": 50688
+  "vocab_size": 50272
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f481f6cca419d995a782136b2b9c72bd262b7877ba2e639e40f8d34079ee4f
-size 593648892
+oid sha256:0e9e8775e66a2f99f561d35fe74ed7f5e70a2fb80a3d94fcc10df333c28296e3
+size 592370940

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac423cb02aadebb07017fcd28a0ce79ad4e5a16ce750832bf14b5b45897e48bf
+oid sha256:3537e544e2641cfd2d391da23bc4a13326ac903aa3d88d1a8e37d4d6651005e4
 size 4920