fanaf91318/text-classification

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: text-classification
+  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. -->
+
+# text-classification
+
+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: 0.2852
+- Accuracy: 0.9314
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- 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
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2144        | 1.0   | 1563 | 0.2409          | 0.9072   |
+| 0.2246        | 2.0   | 3126 | 0.2292          | 0.9304   |
+| 0.1301        | 3.0   | 4689 | 0.2852          | 0.9314   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Avto",
+    "1": "Biznes",
+    "2": "Iqtisodiyot",
+    "3": "Kino",
+    "4": "Kitob",
+    "5": "Koinot",
+    "6": "Madaniyat",
+    "7": "Ob-havo",
+    "8": "Sayohat",
+    "9": "Sport",
+    "10": "Texnologiya"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Avto": 0,
+    "Biznes": 1,
+    "Iqtisodiyot": 2,
+    "Kino": 3,
+    "Kitob": 4,
+    "Koinot": 5,
+    "Madaniyat": 6,
+    "Ob-havo": 7,
+    "Sayohat": 8,
+    "Sport": 9,
+    "Texnologiya": 10
+  },
+  "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": "4.47.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d13dba3dd01cc92ed8f89471c3fcdaca04260c55c76141b99b26ff013ccadf
+size 267860252

runs/Dec22_12-25-25_0a6303ae3a38/events.out.tfevents.1734870327.0a6303ae3a38.649.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148d189da9a2818d8ed35e6844371a78da745b85314314ead37ee5adabccfa47
+size 5077

runs/Dec22_12-40-22_0a6303ae3a38/events.out.tfevents.1734871225.0a6303ae3a38.649.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0f6a5257ac64be480added802b9a2fe08d7be97c1f5e96869cadef9d0ce86b
+size 5376

runs/Dec22_12-40-43_0a6303ae3a38/events.out.tfevents.1734871245.0a6303ae3a38.649.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a758a5bc89e0fa833fd66159840a81fc14cee5129426df70bfbf253e84f144b0
+size 5377

runs/Dec22_12-44-32_0a6303ae3a38/events.out.tfevents.1734871474.0a6303ae3a38.649.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011f667e1a83322db7f2f524a2f6491694868ef15a1b98e7001ad18ae53bf0b2
+size 5377

runs/Dec22_12-45-14_0a6303ae3a38/events.out.tfevents.1734871516.0a6303ae3a38.649.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69285655ff38f5e5b2897aaa5ab36763e92978fe423addeda3f1fae7a51c2707
+size 5377

runs/Dec22_12-51-12_0a6303ae3a38/events.out.tfevents.1734871876.0a6303ae3a38.649.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89473a05db19da94267866dc57e4e7ee719020dfcb6dabd96003f6f51bb8f89
+size 5077

runs/Dec22_12-51-27_0a6303ae3a38/events.out.tfevents.1734871889.0a6303ae3a38.649.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5fa96ef354dec1b701c729bc38530f8057aaa30a2b128183fad1f6731fc15b
+size 5746

runs/Dec22_13-08-56_0a6303ae3a38/events.out.tfevents.1734872938.0a6303ae3a38.649.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9268ea7cbdf451c508a70ded095cd78696a696d5563cbac301c9ac1dde57ae42
+size 56085

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:c6e61ef333bdeea456d5761cc9bfc989e215ab84ee16a42aa998cb435f291cf7
+size 5368