End of training

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.6381977967570244
+      value: 0.6718920889537003
     - name: Recall
       type: recall
-      value: 0.621055167429535
+      value: 0.6659841002168152
     - name: F1
       type: f1
-      value: 0.6295097979366338
+      value: 0.6689250499062368
     - name: Accuracy
       type: accuracy
-      value: 0.9309591653454259
+      value: 0.9377446143270542
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ 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 the conll2002 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2431
-- Precision: 0.6382
-- Recall: 0.6211
-- F1: 0.6295
-- Accuracy: 0.9310
+- Loss: 0.2240
+- Precision: 0.6719
+- Recall: 0.6660
+- F1: 0.6689
+- Accuracy: 0.9377
 
 ## Model description
 
@@ -72,21 +72,22 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use 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: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3539        | 1.0   | 521  | 0.2735          | 0.5837    | 0.5829 | 0.5833 | 0.9218   |
-| 0.207         | 2.0   | 1042 | 0.2431          | 0.6382    | 0.6211 | 0.6295 | 0.9310   |
+| 0.3562        | 1.0   | 521  | 0.2669          | 0.6139    | 0.5870 | 0.6001 | 0.9250   |
+| 0.1976        | 2.0   | 1042 | 0.2408          | 0.6180    | 0.6697 | 0.6428 | 0.9303   |
+| 0.1519        | 3.0   | 1563 | 0.2240          | 0.6719    | 0.6660 | 0.6689 | 0.9377   |
 
 
 ### Framework versions
 
-- Transformers 4.45.1
-- Pytorch 2.4.0+cpu
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

runs/Nov23_00-35-10_e01600b1e65a/events.out.tfevents.1732322132.e01600b1e65a.382.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c3ab74cd35f1303fe3f4f223211ef73be4ad6c8d2272630c93e78dd6e1fbc0
-size 6957
+oid sha256:ecca718cf6f921babdd6858e524751332a3a228eb67a6a5912341a6cf2a3f1fe
+size 7783

runs/Nov23_00-35-10_e01600b1e65a/events.out.tfevents.1732322667.e01600b1e65a.382.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad1257f3105ecf0d73a0cb232027372c0ee0bbd95993f29d53e50eec44ecd39
+size 560