data-silence/rus-news-multiclassifier_ft

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: sentence-transformers/LaBSE
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: news_classifier_ft
+  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. -->
+
+# news_classifier_ft
+
+This model is a fine-tuned version of [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3820
+- Accuracy: 0.9029
+- F1: 0.9025
+- Precision: 0.9030
+- Recall: 0.9029
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.3544        | 1.0   | 3596  | 0.3517          | 0.8861   | 0.8860 | 0.8915    | 0.8861 |
+| 0.2738        | 2.0   | 7192  | 0.3190          | 0.8995   | 0.8987 | 0.9025    | 0.8995 |
+| 0.19          | 3.0   | 10788 | 0.3524          | 0.9016   | 0.9015 | 0.9019    | 0.9016 |
+| 0.1402        | 4.0   | 14384 | 0.3820          | 0.9029   | 0.9025 | 0.9030    | 0.9029 |
+| 0.1055        | 5.0   | 17980 | 0.4399          | 0.9022   | 0.9018 | 0.9024    | 0.9022 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "sentence-transformers/LaBSE",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 501153
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e872749ec3e3ae732ccac9168a6232df9eb9cfdf77c0d1783261c3bb0b993ca4
+size 1883765172

runs/Aug12_18-51-16_97aac8777b25/events.out.tfevents.1723488678.97aac8777b25.1300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444f4c09b772c864473b1b24b7976f6588f0cc98c367d72413d95fb4a3249c9e
+size 5498

runs/Aug12_19-07-37_97aac8777b25/events.out.tfevents.1723489666.97aac8777b25.1300.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c98d429b8d8ec247805c4f78be1bca21e477b4bc65ad76261290f76d3651a82
+size 5498

runs/Aug12_19-16-07_97aac8777b25/events.out.tfevents.1723490180.97aac8777b25.1300.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c09c11b4a03078ee0ae7af02c7bd5d1b5652c745622b32a407c886c77ffc8a
+size 5498

runs/Aug12_19-26-49_97aac8777b25/events.out.tfevents.1723490820.97aac8777b25.1300.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33403b69b9b2d9d09ebb6a546711db15fd7f4ee5a57d64fa63f2938cf2692ba
+size 5498

runs/Aug12_19-40-51_97aac8777b25/events.out.tfevents.1723491745.97aac8777b25.1300.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cfb76d0d3746f304dc61ce6480449b6c2b6ed83671567c8bd8a30c55415335
+size 5497

runs/Aug12_19-57-12_97aac8777b25/events.out.tfevents.1723492664.97aac8777b25.1300.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15274ec6f7f9262c787e84d109a764414e53cd98faed8c6bf5fbf4be54deb85c
+size 5497

runs/Aug12_20-26-14_97aac8777b25/events.out.tfevents.1723494399.97aac8777b25.1300.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35bf653927aaebae787126aa61f4043c3d5b33782380c9bd27120fe5a867577
+size 15623

runs/Aug12_20-26-14_97aac8777b25/events.out.tfevents.1723500919.97aac8777b25.1300.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20eafec9c1de5b18aa0cfd1c4d528b606af1c36cb443b6481fad6a294695d89
+size 569

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac76f7bd3b31c3db616d53f341a9e2effaba86c3b3813b29e1251a98034691b
+size 5112