Sentiment Fa

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: dadashzadeh/roberta-sentiment-persian
+base_model: HooshvareLab/bert-fa-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Bert-Sentiment-Fa
 
-This model is a fine-tuned version of [dadashzadeh/roberta-sentiment-persian](https://huggingface.co/dadashzadeh/roberta-sentiment-persian) on the None dataset.
+This model is a fine-tuned version of [HooshvareLab/bert-fa-base-uncased](https://huggingface.co/HooshvareLab/bert-fa-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4259
-- Accuracy: 0.825
-- F1: 0.8145
+- Loss: 1.0798
+- Accuracy: 0.5652
+- F1: 0.5901
 
 ## Model description
 
@@ -46,22 +46,17 @@ 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: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 270  | 1.0387          | 0.7917   | 0.7822 |
-| 0.2072        | 2.0   | 540  | 0.8945          | 0.825    | 0.8185 |
-| 0.2072        | 3.0   | 810  | 0.9836          | 0.8208   | 0.7983 |
-| 0.0871        | 4.0   | 1080 | 1.2439          | 0.8125   | 0.7994 |
-| 0.0871        | 5.0   | 1350 | 1.3258          | 0.8125   | 0.8016 |
-| 0.0281        | 6.0   | 1620 | 1.4928          | 0.8083   | 0.7910 |
-| 0.0281        | 7.0   | 1890 | 1.4261          | 0.8208   | 0.8054 |
-| 0.0207        | 8.0   | 2160 | 1.4747          | 0.825    | 0.8107 |
-| 0.0207        | 9.0   | 2430 | 1.4136          | 0.825    | 0.8145 |
-| 0.0035        | 10.0  | 2700 | 1.4259          | 0.825    | 0.8145 |
+| No log        | 1.0   | 52   | 1.0320          | 0.4130   | 0.2269 |
+| No log        | 2.0   | 104  | 0.9651          | 0.4783   | 0.4406 |
+| No log        | 3.0   | 156  | 1.0128          | 0.5435   | 0.5541 |
+| No log        | 4.0   | 208  | 1.0869          | 0.5870   | 0.6025 |
+| No log        | 5.0   | 260  | 1.0798          | 0.5652   | 0.5901 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85fc40a5f385dcd9a3ae1fcd8e0160791ba981aaa9801d7ce1d3e9df50ed3df6
+oid sha256:43c4947ac8b8a5ed9ec97286b130d2ace2d95c6d077f7d4478f8f3227b328fdd
 size 651398148

runs/Oct10_05-01-46_1a38898cabb0/events.out.tfevents.1728536518.1a38898cabb0.414.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c909f717285be45231046a891c7bbb4ba97d131f0880fdc90858345cc1c22e
-size 6866
+oid sha256:adea320e45107497a8261d0a9229833d0fe1145c7507e90143b0327c91791e86
+size 7220