End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [makhataei/qa-persian-bert-fa-base-uncased](https://huggingface.co/makhataei/qa-persian-bert-fa-base-uncased) on the pquad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4982
+- Loss: 5.2170
 
 ## Model description
 
@@ -36,21 +36,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.001
 - train_batch_size: 24
-- eval_batch_size: 16
+- eval_batch_size: 12
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1247        | 1.0   | 2667 | 1.8245          |
-| 0.0725        | 2.0   | 5334 | 1.9386          |
-| 0.0263        | 3.0   | 8001 | 2.4982          |
+| 5.5015        | 1.0   | 2667 | 5.2170          |
+| 5.5039        | 2.0   | 5334 | 5.2170          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c8d28519488a2bdd68b2492a1061128ad1d8d4d0c7cb5345a73b4ef3cc6d60
+oid sha256:d1b1d490efa95123a4f84ce5febaf34939696f667524920599ae79c934b16686
 size 649032520

runs/Nov22_11-59-23_d4c2b514b428/events.out.tfevents.1700654370.d4c2b514b428.184.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda08c5898075737ecd0c59510a39cb46f798c05b68a76ca8ef98b07be4c9888
-size 6118
+oid sha256:b1d2fafc04deed0cd3552a56891286b53c5a2d57cec2f5f771a25be99d8cd0e7
+size 6743