Tanor
/

BERTicSENTPOS0

Text Classification

Generated from Trainer

Model card Files Files and versions

Tanor commited on Jul 13, 2023

Commit

6a8e6b4

·

1 Parent(s): 482a4e3

update model card README.md

Files changed (1) hide show

README.md +12 -19

README.md CHANGED Viewed

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [Tanor/BERTicSENTPOS0](https://huggingface.co/Tanor/BERTicSENTPOS0) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0221
-- F1: 0.7826
 ## Model description
@@ -43,28 +43,21 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 16
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 0.99  | 52   | 0.0244          | 0.6897 |
-| No log        | 2.0   | 105  | 0.0359          | 0.6250 |
-| No log        | 2.99  | 157  | 0.0297          | 0.6897 |
-| No log        | 4.0   | 210  | 0.0234          | 0.7407 |
-| No log        | 4.99  | 262  | 0.0175          | 0.8333 |
-| No log        | 6.0   | 315  | 0.0199          | 0.8    |
-| No log        | 6.99  | 367  | 0.0238          | 0.7407 |
-| No log        | 8.0   | 420  | 0.0244          | 0.7692 |
-| No log        | 8.99  | 472  | 0.0220          | 0.7826 |
-| 0.0015        | 10.0  | 525  | 0.0217          | 0.7826 |
-| 0.0015        | 10.99 | 577  | 0.0249          | 0.7692 |
-| 0.0015        | 12.0  | 630  | 0.0231          | 0.7826 |
-| 0.0015        | 12.99 | 682  | 0.0228          | 0.7500 |
-| 0.0015        | 14.0  | 735  | 0.0226          | 0.8    |
-| 0.0015        | 14.99 | 787  | 0.0222          | 0.7500 |
-| 0.0015        | 15.85 | 832  | 0.0221          | 0.7826 |
 ### Framework versions

 This model is a fine-tuned version of [Tanor/BERTicSENTPOS0](https://huggingface.co/Tanor/BERTicSENTPOS0) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0195
+- F1: 0.6667
 ## Model description
 - total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 32
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 0.99  | 52   | 0.0469          | 0.0    |
+| No log        | 2.0   | 105  | 0.0398          | 0.0    |
+| No log        | 2.99  | 157  | 0.0172          | 0.0    |
+| No log        | 4.0   | 210  | 0.0141          | 0.6364 |
+| No log        | 4.99  | 262  | 0.0135          | 0.6667 |
+| No log        | 6.0   | 315  | 0.0125          | 0.6667 |
+| No log        | 6.99  | 367  | 0.0175          | 0.6    |
+| No log        | 8.0   | 420  | 0.0249          | 0.6667 |
+| No log        | 8.99  | 472  | 0.0195          | 0.6667 |
 ### Framework versions