End of training

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3307
-- Precision: 0.2114
-- Recall: 0.2818
-- F1: 0.2416
-- Accuracy: 0.9011
+- Loss: 0.4984
+- Precision: 0.3858
+- Recall: 0.4441
+- F1: 0.4129
+- Accuracy: 0.9018
 
 ## Model description
 
@@ -51,22 +51,27 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 62   | 0.2391          | 0.1104    | 0.1917 | 0.1401 | 0.8961   |
-| 0.2911        | 2.0   | 124  | 0.2294          | 0.1429    | 0.2478 | 0.1812 | 0.8955   |
-| 0.2911        | 3.0   | 186  | 0.2336          | 0.1932    | 0.2832 | 0.2297 | 0.9040   |
-| 0.1439        | 4.0   | 248  | 0.2556          | 0.2079    | 0.2802 | 0.2387 | 0.9084   |
-| 0.0785        | 5.0   | 310  | 0.2805          | 0.2217    | 0.2950 | 0.2532 | 0.9075   |
+| No log        | 1.0   | 62   | 0.2853          | 0.3103    | 0.3648 | 0.3354 | 0.8888   |
+| 0.3754        | 2.0   | 124  | 0.2557          | 0.3672    | 0.4783 | 0.4155 | 0.8958   |
+| 0.3754        | 3.0   | 186  | 0.2704          | 0.3920    | 0.4983 | 0.4388 | 0.8972   |
+| 0.1772        | 4.0   | 248  | 0.2925          | 0.4431    | 0.5028 | 0.4711 | 0.9023   |
+| 0.096         | 5.0   | 310  | 0.3442          | 0.4179    | 0.5184 | 0.4628 | 0.8984   |
+| 0.096         | 6.0   | 372  | 0.3654          | 0.4395    | 0.5295 | 0.4803 | 0.9018   |
+| 0.0607        | 7.0   | 434  | 0.3743          | 0.4698    | 0.5184 | 0.4929 | 0.9063   |
+| 0.0607        | 8.0   | 496  | 0.4196          | 0.4614    | 0.5250 | 0.4912 | 0.9059   |
+| 0.0429        | 9.0   | 558  | 0.4325          | 0.4472    | 0.5417 | 0.4899 | 0.9025   |
+| 0.0298        | 10.0  | 620  | 0.4474          | 0.4609    | 0.5373 | 0.4961 | 0.9040   |
 
 
 ### Framework versions
 
 - Transformers 4.48.1
-- Pytorch 2.5.1+cu124
+- Pytorch 2.6.0+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -8,8 +8,18 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ee93102c313fa053118ec0dde2ea94f74379b8cf6111452bf0c2a1b5b0671d
-size 440136504
+oid sha256:8a371b9cf9290a47e322e9216994ed2d12d918f791432bef82807238d6cdd80e
+size 440139580

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bd84051974a80f3a9ca821ce5fa7f4a91a7422db73cb9d73013a74a588315f
+oid sha256:c348e93d74a7dbbc8d614dae368fe8c62d0cc12bd47ddaa098feb9a9eb85efe4
 size 5304