End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bobbyw/deberta-v3-large_faster_learning_v2](https://huggingface.co/bobbyw/deberta-v3-large_faster_learning_v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0915
+- Loss: 0.0991
 - Accuracy: 0.0248
-- F1: 0.0277
-- Precision: 0.0142
-- Recall: 0.6364
+- F1: 0.0238
+- Precision: 0.0122
+- Recall: 0.5455
 - Learning Rate: 0.0
 
 ## Model description
@@ -44,26 +44,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-06
+- learning_rate: 1e-06
 - train_batch_size: 3
 - eval_batch_size: 3
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Rate   |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
-| 0.0652        | 1.0   | 689  | 0.0845          | 0.0198   | 0.0314 | 0.0160    | 0.7273 | 0.0018 |
-| 0.0644        | 2.0   | 1378 | 0.0888          | 0.0228   | 0.0296 | 0.0151    | 0.6818 | 0.0015 |
-| 0.0582        | 3.0   | 2067 | 0.0920          | 0.0238   | 0.0315 | 0.0161    | 0.7273 | 0.0012 |
-| 0.0536        | 4.0   | 2756 | 0.0849          | 0.0248   | 0.0277 | 0.0142    | 0.6364 | 0.001  |
-| 0.0559        | 5.0   | 3445 | 0.1012          | 0.0308   | 0.0298 | 0.0152    | 0.6818 | 0.0008 |
-| 0.0466        | 6.0   | 4134 | 0.0948          | 0.0268   | 0.0316 | 0.0161    | 0.7273 | 0.0005 |
-| 0.0436        | 7.0   | 4823 | 0.0957          | 0.0278   | 0.0297 | 0.0152    | 0.6818 | 0.0003 |
-| 0.0447        | 8.0   | 5512 | 0.0915          | 0.0248   | 0.0277 | 0.0142    | 0.6364 | 0.0    |
+| 0.0174        | 1.0   | 689  | 0.1018          | 0.0238   | 0.0238 | 0.0122    | 0.5455 | 0.0008 |
+| 0.019         | 2.0   | 1378 | 0.1014          | 0.0248   | 0.0258 | 0.0132    | 0.5909 | 0.0005 |
+| 0.0182        | 3.0   | 2067 | 0.0979          | 0.0228   | 0.0238 | 0.0122    | 0.5455 | 0.0003 |
+| 0.0171        | 4.0   | 2756 | 0.0991          | 0.0248   | 0.0238 | 0.0122    | 0.5455 | 0.0    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d04d84fa8d8a9c9a4fdeecfae53f09c8a152453a41e46fdf197409154a409c9
+oid sha256:b9411a2f0b5608ff3c03767c11d019c1f857a9987f849a2e17298cea09255d09
 size 1740120184

runs/Jun12_17-44-15_c86ebda74365/events.out.tfevents.1718214257.c86ebda74365.349.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8015b3cb56113e083c09d2f19601c02443725f9987c59cceda58deca0d33c84e
-size 8566
+oid sha256:2ee52e90f8361e3a509d1e4d0bc22a2058c981b4f7079e116807645d29d03cef
+size 9508