End of training

README.md

@@ -12,8 +12,6 @@ metrics:
 model-index:
 - name: legal_ai_India_ner_results
   results: []
-datasets:
-- opennyaiorg/InLegalNER
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -23,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0993
-- Precision: 0.8282
-- Recall: 0.8731
-- F1: 0.8501
-- Accuracy: 0.9751
+- Loss: 0.1057
+- Precision: 0.8370
+- Recall: 0.8742
+- F1: 0.8552
+- Accuracy: 0.9741
 
 ## Model description
 
@@ -52,16 +50,17 @@ 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: 4
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.4565        | 1.0   | 917  | 0.1275          | 0.7198    | 0.8134 | 0.7637 | 0.9639   |
-| 0.1035        | 2.0   | 1834 | 0.1027          | 0.7932    | 0.8666 | 0.8283 | 0.9702   |
-| 0.0661        | 3.0   | 2751 | 0.0980          | 0.8076    | 0.8713 | 0.8383 | 0.9730   |
-| 0.0501        | 4.0   | 3668 | 0.0993          | 0.8282    | 0.8731 | 0.8501 | 0.9751   |
+| 0.4633        | 1.0   | 917  | 0.1226          | 0.7624    | 0.8040 | 0.7827 | 0.9642   |
+| 0.1039        | 2.0   | 1834 | 0.1077          | 0.7996    | 0.8583 | 0.8279 | 0.9702   |
+| 0.0686        | 3.0   | 2751 | 0.1021          | 0.8054    | 0.8695 | 0.8362 | 0.9714   |
+| 0.048         | 4.0   | 3668 | 0.1084          | 0.8309    | 0.8706 | 0.8503 | 0.9732   |
+| 0.0368        | 5.0   | 4585 | 0.1057          | 0.8370    | 0.8742 | 0.8552 | 0.9741   |
 
 
 ### Framework versions
@@ -69,4 +68,4 @@ The following hyperparameters were used during training:
 - Transformers 4.48.3
 - Pytorch 2.5.1+cu124
 - Datasets 3.3.2
-- Tokenizers 0.21.0
+- Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e80eeb352b7b9bb9173e2e2c99b53dc96c6a54bc0a9bc127a3a73c6d415185d7
+oid sha256:81fe8e0acfd49f8e7c66118543231b1a627a65f0cafa5625592d596bbd42ad45
 size 435679140

runs/Feb25_15-28-14_a40ba512ca54/events.out.tfevents.1740497295.a40ba512ca54.408.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0cdeb6523d41005230a632547e5e66c4df390e04afc6b870de3e7fb62cb0652
-size 10684
+oid sha256:d0597d461869a76800e12a638a49037873642c1972aab65aaa306564a9e9f563
+size 11038