End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2805
-- F1: 0.9333
+- Loss: 0.3201
+- F1: 0.9356
 
 ## Model description
 
@@ -44,17 +44,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.5148        | 1.0   | 313  | 1.0922          | 0.8274 |
-| 0.5018        | 2.0   | 626  | 0.4500          | 0.9059 |
-| 0.2343        | 3.0   | 939  | 0.3308          | 0.9227 |
-| 0.1307        | 4.0   | 1252 | 0.2949          | 0.9300 |
-| 0.0681        | 5.0   | 1565 | 0.2805          | 0.9333 |
+| 1.4924        | 1.0   | 313  | 1.0900          | 0.8078 |
+| 0.4683        | 2.0   | 626  | 0.4458          | 0.9100 |
+| 0.2234        | 3.0   | 939  | 0.3289          | 0.9243 |
+| 0.1255        | 4.0   | 1252 | 0.3154          | 0.9245 |
+| 0.0512        | 5.0   | 1565 | 0.2927          | 0.9336 |
+| 0.0322        | 6.0   | 1878 | 0.3103          | 0.9343 |
+| 0.0189        | 7.0   | 2191 | 0.3133          | 0.9332 |
+| 0.0121        | 8.0   | 2504 | 0.3228          | 0.9346 |
+| 0.0068        | 9.0   | 2817 | 0.3183          | 0.9339 |
+| 0.0082        | 10.0  | 3130 | 0.3201          | 0.9356 |
 
 
 ### Framework versions

runs/Jan28_15-52-16_EmreSekeroglu/events.out.tfevents.1738068736.EmreSekeroglu.14136.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac5ad34b05bc05a3fadfcef0e638d0d985dd63fdec780869bb4722926af0161
-size 19779
+oid sha256:c9ca0d0e6b85fb4df69da30da022c5a2145a5a5708083dac8bad97b2050d4a6d
+size 20450

tokenizer_config.json

@@ -46,7 +46,7 @@
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 256,
+  "model_max_length": 384,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,