Model save

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # py38-pylingual-v1-segmenter
 
-This model is a fine-tuned version of [syssec-utd/py38-pylingual-v1-mlm](https://huggingface.co/syssec-utd/py38-pylingual-v1-mlm) on the syssec-utd/segmentation-py38-pylingual-v1-tokenized dataset.
+This model is a fine-tuned version of [syssec-utd/py38-pylingual-v1-mlm](https://huggingface.co/syssec-utd/py38-pylingual-v1-mlm) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0027
+- Loss: 0.0025
 - Precision: 0.9968
 - Recall: 0.9968
 - F1: 0.9968
-- Accuracy: 0.9991
+- Accuracy: 0.9992
 
 ## Model description
 
@@ -57,13 +57,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0058        | 1.0   | 101234 | 0.0030          | 0.9961    | 0.9966 | 0.9963 | 0.9990   |
-| 0.0034        | 2.0   | 202468 | 0.0027          | 0.9968    | 0.9968 | 0.9968 | 0.9991   |
+| 0.0055        | 1.0   | 101234 | 0.0030          | 0.9956    | 0.9963 | 0.9959 | 0.9990   |
+| 0.0032        | 2.0   | 202468 | 0.0025          | 0.9968    | 0.9968 | 0.9968 | 0.9992   |
 
 
 ### Framework versions
 
 - Transformers 4.48.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
 - Tokenizers 0.21.0

runs/Feb04_20-25-51_syssec-ub1/events.out.tfevents.1738722395.syssec-ub1.44046.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72c15b89263c61d94bcfcd3e5726ce3256d39b763aa09a15028ec9113bbc162
-size 6287
+oid sha256:5f64c64e1b240f7ad80edc5bf0cf27ba525f0b30e1396a4e7f0b077c6430c2d8
+size 7128