Training completed!

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8039
-- F1: 0.0
-- Roc Auc: 0.5
-- Accuracy: 0.25
+- Loss: 0.7384
+- F1: 0.7593
+- Roc Auc: 0.8588
+- Accuracy: 0.6506
 
 ## Model description
 
@@ -46,22 +46,27 @@ 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: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| No log        | 1.0   | 8    | 0.6953          | 0.5455 | 0.5857  | 0.25     |
-| No log        | 2.0   | 16   | 0.7251          | 0.0    | 0.4286  | 0.0      |
-| No log        | 3.0   | 24   | 0.7762          | 0.0    | 0.4286  | 0.25     |
-| No log        | 4.0   | 32   | 0.7932          | 0.0    | 0.5     | 0.25     |
-| No log        | 5.0   | 40   | 0.8039          | 0.0    | 0.5     | 0.25     |
+| No log        | 1.0   | 166  | 0.5907          | 0.7281 | 0.8497  | 0.5904   |
+| No log        | 2.0   | 332  | 0.5260          | 0.6836 | 0.8576  | 0.5181   |
+| No log        | 3.0   | 498  | 0.7023          | 0.7324 | 0.8381  | 0.6024   |
+| 0.3153        | 4.0   | 664  | 0.7848          | 0.7245 | 0.8168  | 0.5904   |
+| 0.3153        | 5.0   | 830  | 0.6979          | 0.7436 | 0.8666  | 0.5904   |
+| 0.3153        | 6.0   | 996  | 0.8550          | 0.7426 | 0.8337  | 0.6265   |
+| 0.1464        | 7.0   | 1162 | 0.7102          | 0.7830 | 0.8700  | 0.6747   |
+| 0.1464        | 8.0   | 1328 | 0.7172          | 0.7721 | 0.8662  | 0.6627   |
+| 0.1464        | 9.0   | 1494 | 0.7812          | 0.7664 | 0.8613  | 0.6506   |
+| 0.0781        | 10.0  | 1660 | 0.7384          | 0.7593 | 0.8588  | 0.6506   |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.15.0
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -8,16 +8,22 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "ram_agirlik",
-    "1": "ekran_karti_agirlik",
-    "2": "pil_agirlik"
+    "0": "i\u015flemci",
+    "1": "ekran_karti",
+    "2": "batarya",
+    "3": "ram",
+    "4": "ssd",
+    "5": "fiyat"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "ekran_karti_agirlik": 1,
-    "pil_agirlik": 2,
-    "ram_agirlik": 0
+    "batarya": 2,
+    "ekran_karti": 1,
+    "fiyat": 5,
+    "i\u015flemci": 0,
+    "ram": 3,
+    "ssd": 4
   },
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
@@ -40,7 +46,7 @@
   "relative_attention": true,
   "share_att_key": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "type_vocab_size": 0,
   "vocab_size": 251000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a417e19a31971986d45d75d3ccf52db6e1c7bd271d95c14d52ed5eca6682475
-size 1115271284
+oid sha256:17768fbebe9c5648633724348c9baa8a961df5d5398617ccb96617ffb3300148
+size 1115280512

runs/Jan03_15-34-28_7f1237313fba/events.out.tfevents.1704296069.7f1237313fba.1443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b97d3b417d5ebf0f5bfeec3bd448498156559baffcfcf41f570345fd4339f6
+size 9838

runs/Jan03_15-34-28_7f1237313fba/events.out.tfevents.1704296686.7f1237313fba.1443.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe8afff45055b94168921aa04979abd2b9a49fa0232bf4a3b199b1ef397c030
+size 9933

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1643979daaa01e290072bfbdc4677ef54abf5fb315a15799060414427297e6
-size 4600
+oid sha256:f4429bf45c59ef6604174bcbe41c829b303a841fda5ee3608b48edf2f2c63337
+size 4728