Training complete

README.md

@@ -0,0 +1,89 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1795
+- Accuracy: 0.9418
+- Precision: 0.9421
+- Recall: 0.9418
+- F1: 0.9419
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.4176        | 0.0667 | 500   | 0.3007          | 0.9030   | 0.9031    | 0.9030 | 0.9027 |
+| 0.265         | 0.1333 | 1000  | 0.2526          | 0.9161   | 0.9161    | 0.9161 | 0.9159 |
+| 0.2408        | 0.2    | 1500  | 0.2476          | 0.9226   | 0.9245    | 0.9226 | 0.9224 |
+| 0.231         | 0.2667 | 2000  | 0.2341          | 0.9297   | 0.9311    | 0.9297 | 0.9295 |
+| 0.2335        | 0.3333 | 2500  | 0.2143          | 0.9297   | 0.9296    | 0.9297 | 0.9297 |
+| 0.2417        | 0.4    | 3000  | 0.2000          | 0.9325   | 0.9338    | 0.9325 | 0.9327 |
+| 0.208         | 0.4667 | 3500  | 0.2060          | 0.9314   | 0.9323    | 0.9314 | 0.9315 |
+| 0.2133        | 0.5333 | 4000  | 0.2011          | 0.9346   | 0.9349    | 0.9346 | 0.9347 |
+| 0.2042        | 0.6    | 4500  | 0.2035          | 0.9345   | 0.9366    | 0.9345 | 0.9346 |
+| 0.1947        | 0.6667 | 5000  | 0.1945          | 0.9392   | 0.9392    | 0.9392 | 0.9392 |
+| 0.1954        | 0.7333 | 5500  | 0.1993          | 0.9367   | 0.9388    | 0.9367 | 0.9368 |
+| 0.1958        | 0.8    | 6000  | 0.2001          | 0.9411   | 0.9414    | 0.9411 | 0.9412 |
+| 0.2002        | 0.8667 | 6500  | 0.1906          | 0.9397   | 0.9403    | 0.9397 | 0.9399 |
+| 0.1885        | 0.9333 | 7000  | 0.1898          | 0.9420   | 0.9422    | 0.9420 | 0.9420 |
+| 0.1979        | 1.0    | 7500  | 0.1795          | 0.9418   | 0.9421    | 0.9418 | 0.9419 |
+| 0.1492        | 1.0667 | 8000  | 0.1933          | 0.9459   | 0.9460    | 0.9459 | 0.9459 |
+| 0.148         | 1.1333 | 8500  | 0.1978          | 0.9426   | 0.9437    | 0.9426 | 0.9427 |
+| 0.137         | 1.2    | 9000  | 0.1941          | 0.9466   | 0.9469    | 0.9466 | 0.9467 |
+| 0.1433        | 1.2667 | 9500  | 0.1988          | 0.9453   | 0.9457    | 0.9453 | 0.9453 |
+| 0.1403        | 1.3333 | 10000 | 0.1926          | 0.9441   | 0.9448    | 0.9441 | 0.9441 |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "World",
+    "1": "Sports",
+    "2": "Business",
+    "3": "Sci/Tech"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Business": 2,
+    "Sci/Tech": 3,
+    "Sports": 1,
+    "World": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4472230eac49417440cdc0381066e1936439bbd9337cd5a364423281db3ccd
+size 267838720

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ee064dc29029295a42e7a04c7e9f1204438e7419d4d36e1f27faeacbf465a3
+size 5240