kalai_fine_tuned_model_3

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1547
-- Accuracy: 0.9730
+- Loss: 0.1628
+- Accuracy: 0.9550
 
 ## Model description
 
@@ -43,32 +43,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 28   | 0.5030          | 0.9189   |
-| No log        | 2.0   | 56   | 0.1776          | 0.9640   |
-| No log        | 3.0   | 84   | 1.1016          | 0.2793   |
-| No log        | 4.0   | 112  | 0.7159          | 0.8739   |
-| No log        | 5.0   | 140  | 0.1969          | 0.9550   |
-| No log        | 6.0   | 168  | 0.1550          | 0.9640   |
-| No log        | 7.0   | 196  | 0.1547          | 0.9730   |
-| No log        | 8.0   | 224  | 0.1794          | 0.9640   |
-| No log        | 9.0   | 252  | 0.1822          | 0.9640   |
-| No log        | 10.0  | 280  | 0.1845          | 0.9640   |
-| No log        | 11.0  | 308  | 0.1834          | 0.9640   |
-| No log        | 12.0  | 336  | 0.1827          | 0.9640   |
-| No log        | 13.0  | 364  | 0.1694          | 0.9730   |
-| No log        | 14.0  | 392  | 0.1714          | 0.9730   |
-| No log        | 15.0  | 420  | 0.1737          | 0.9730   |
+| No log        | 1.0   | 28   | 0.4061          | 0.9279   |
+| No log        | 2.0   | 56   | 0.2302          | 0.9550   |
+| No log        | 3.0   | 84   | 0.1830          | 0.9640   |
+| No log        | 4.0   | 112  | 0.1639          | 0.9550   |
+| No log        | 5.0   | 140  | 0.1628          | 0.9550   |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.2.1+cu121
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be7d88f1bfe6c26a82f6489b207e3665d4aafd164ab08cb6de11091c586c742
+oid sha256:801d33210083a55b202e7a290d4738fe5d81122332ee002b85902d1252bbde1f
 size 46746988