End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: NlpHUST/ner-vietnamese-electra-base
+base_model: lilyyellow/my_awesome_ner-token_classification_v1.0.7-4
 tags:
 - generated_from_trainer
 metrics:
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_ner-token_classification_v1.0.7-4
 
-This model is a fine-tuned version of [NlpHUST/ner-vietnamese-electra-base](https://huggingface.co/NlpHUST/ner-vietnamese-electra-base) on an unknown dataset.
+This model is a fine-tuned version of [lilyyellow/my_awesome_ner-token_classification_v1.0.7-4](https://huggingface.co/lilyyellow/my_awesome_ner-token_classification_v1.0.7-4) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4590
-- Precision: 0.6294
-- Recall: 0.6897
-- F1: 0.6582
+- Loss: 0.5084
+- Precision: 0.6376
+- Recall: 0.6915
+- F1: 0.6634
 - Accuracy: 0.8858
 
 ## Model description
@@ -48,19 +48,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 15
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3719        | 1.9965  | 1156 | 0.3665          | 0.6111    | 0.6557 | 0.6326 | 0.8883   |
-| 0.2896        | 3.9931  | 2312 | 0.3670          | 0.6027    | 0.6884 | 0.6427 | 0.8862   |
-| 0.2171        | 5.9896  | 3468 | 0.3866          | 0.6089    | 0.6867 | 0.6455 | 0.8848   |
-| 0.1725        | 7.9862  | 4624 | 0.4091          | 0.6193    | 0.6900 | 0.6528 | 0.8864   |
-| 0.1559        | 9.9827  | 5780 | 0.4411          | 0.6263    | 0.6937 | 0.6583 | 0.8856   |
-| 0.1334        | 11.9793 | 6936 | 0.4540          | 0.6224    | 0.6905 | 0.6547 | 0.8846   |
-| 0.1334        | 13.9758 | 8092 | 0.4590          | 0.6294    | 0.6897 | 0.6582 | 0.8858   |
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1297        | 1.9965 | 1156 | 0.4660          | 0.6384    | 0.6812 | 0.6591 | 0.8855   |
+| 0.0986        | 3.9931 | 2312 | 0.5084          | 0.6376    | 0.6915 | 0.6634 | 0.8858   |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NlpHUST/ner-vietnamese-electra-base",
+  "_name_or_path": "lilyyellow/my_awesome_ner-token_classification_v1.0.7-4",
   "architectures": [
     "ElectraForTokenClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dfb176bcd5b58b996fe0220ec808c897fe301648fc379e8c4c146b3fc8491e0
+oid sha256:d5eb33a4ef16c6c389b66cd958486fcbd1cca8271f73f473c4da3617b85257bd
 size 532392452

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89c6f407e1c9c36def48115a0e1d0fb47811eba563849ebe6b78eaad11d007f
+oid sha256:5316323244d72b51310674729c9262494fe88c588716c16d1e5af204cefff2a1
 size 5112