Model save

README.md

@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NLP-LTU/bertweet-large-sexism-detector](https://huggingface.co/NLP-LTU/bertweet-large-sexism-detector) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6489
-- Icm: 0.0711
-- Icmnorm: 0.5361
-- Fmeasure: 0.6886
+- Loss: 0.7233
+- Icm: 0.1739
+- Icmnorm: 0.5882
+- Fmeasure: 0.7274
 
 ## Model description
 
@@ -36,23 +36,32 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-06
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 12
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Icm    | Icmnorm | Fmeasure |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| 0.6499        | 1.0   | 771  | 0.5820          | 0.0093 | 0.5047  | 0.6732   |
-| 0.4108        | 2.0   | 1542 | 0.8449          | 0.0401 | 0.5204  | 0.6798   |
-| 0.2617        | 3.0   | 2313 | 1.6489          | 0.0711 | 0.5361  | 0.6886   |
+| No log        | 1.0   | 407  | 0.5823          | 0.0856 | 0.5434  | 0.6977   |
+| 0.7182        | 2.0   | 814  | 0.5689          | 0.0427 | 0.5217  | 0.6843   |
+| 0.5513        | 3.0   | 1221 | 0.5684          | 0.0904 | 0.5459  | 0.6999   |
+| 0.4941        | 4.0   | 1628 | 0.5851          | 0.1166 | 0.5591  | 0.7073   |
+| 0.4613        | 5.0   | 2035 | 0.6129          | 0.1405 | 0.5713  | 0.7164   |
+| 0.4613        | 6.0   | 2442 | 0.6221          | 0.1381 | 0.5701  | 0.7152   |
+| 0.4221        | 7.0   | 2849 | 0.6397          | 0.1548 | 0.5785  | 0.7207   |
+| 0.3863        | 8.0   | 3256 | 0.6702          | 0.1691 | 0.5858  | 0.7249   |
+| 0.3673        | 9.0   | 3663 | 0.6797          | 0.1572 | 0.5797  | 0.7219   |
+| 0.35          | 10.0  | 4070 | 0.7050          | 0.1572 | 0.5797  | 0.7219   |
+| 0.35          | 11.0  | 4477 | 0.7273          | 0.1715 | 0.5870  | 0.7262   |
+| 0.3388        | 12.0  | 4884 | 0.7233          | 0.1739 | 0.5882  | 0.7274   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d5681026b7c543afd6beaa5d130e2ca742bddd1d497da142b18576c02e0030
+oid sha256:b11ccaf8adb829ca545369400bc0f5e730086173fbedbfaa56036a435a6f8d69
 size 1421495416

runs/Apr25_15-50-44_tardis/events.out.tfevents.1714053047.tardis.149981.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85d5c918f5fe806dd9f07f3a750cf43bc0182a3f237f3177c1796754e3fef17
-size 11335
+oid sha256:8efb0cb88303f23c3ea1f1bec2597e1be45f621de0ddd99a156adff5bf3e6473
+size 12321

runs/Apr25_15-50-44_tardis/events.out.tfevents.1714054784.tardis.149981.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04609063a82b58bd8af36fc2c51fd66eb436964c390cfe5d7d928e57a909497d
+size 509