Model save

README.md

@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mdeberta-v3-base-on-custom-kural-500
 
-This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4734
-- Accuracy: 0.7933
+- Loss: 0.2705
+- Accuracy: 0.93
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,21 +49,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 11   | 0.5629          | 0.74     |
-| No log        | 2.0   | 22   | 0.5678          | 0.74     |
-| No log        | 3.0   | 33   | 0.5530          | 0.74     |
-| No log        | 4.0   | 44   | 0.5046          | 0.74     |
-| No log        | 5.0   | 55   | 0.5419          | 0.74     |
-| No log        | 6.0   | 66   | 0.5136          | 0.74     |
-| No log        | 7.0   | 77   | 0.5039          | 0.68     |
-| No log        | 8.0   | 88   | 0.4751          | 0.82     |
-| No log        | 9.0   | 99   | 0.4976          | 0.7733   |
-| No log        | 10.0  | 110  | 0.4734          | 0.7933   |
+| No log        | 1.0   | 25   | 0.4294          | 0.85     |
+| No log        | 2.0   | 50   | 0.2183          | 0.92     |
+| No log        | 3.0   | 75   | 0.4484          | 0.88     |
+| No log        | 4.0   | 100  | 0.5041          | 0.87     |
+| No log        | 5.0   | 125  | 0.2482          | 0.93     |
+| No log        | 6.0   | 150  | 0.9998          | 0.81     |
+| No log        | 7.0   | 175  | 0.2305          | 0.94     |
+| No log        | 8.0   | 200  | 0.2145          | 0.95     |
+| No log        | 9.0   | 225  | 0.2428          | 0.94     |
+| No log        | 10.0  | 250  | 0.2705          | 0.93     |
 
 
 ### Framework versions
 
 - Transformers 4.39.3
-- Pytorch 2.1.2
+- Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b9755b8c0da303f92fcf87859791ee50355da0bcc49b80b51c5b6363c57302a
+oid sha256:991dab563c7f3584bc317ee962c751767fc2945fca9d715e61b6b82555564c19
 size 1115268200

runs/Apr16_21-22-06_7464db25e7ec/events.out.tfevents.1713302651.7464db25e7ec.714.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5e7c498af554615344230d393daddbd7ef6119f859725b2cf078dcdc7b8297
+size 8387

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16f21b0c8d1bd0753355d21215fa7483a1dda12171416ab9f9bdae7a3c19dda
+oid sha256:cce1830204851b0838458efcac90e932eaf426a5d09242251863038a3d7644b1
 size 4984