add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: rubert-base-cased-sentence-finetuned-headlines_X
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.952
+---
+
+<!-- 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. -->
+
+# rubert-base-cased-sentence-finetuned-headlines_X
+
+This model is a fine-tuned version of [DeepPavlov/rubert-base-cased-sentence](https://huggingface.co/DeepPavlov/rubert-base-cased-sentence) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2535
+- Accuracy: 0.952
+
+## 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: 32
+- eval_batch_size: 32
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 157  | 0.2759          | 0.912    |
+| No log        | 2.0   | 314  | 0.2538          | 0.936    |
+| No log        | 3.0   | 471  | 0.2556          | 0.945    |
+| 0.1908        | 4.0   | 628  | 0.2601          | 0.95     |
+| 0.1908        | 5.0   | 785  | 0.2535          | 0.952    |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "DeepPavlov/rubert-base-cased-sentence",
+  "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"
+  },
+  "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",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": "4.10.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f02f9ae48a72d0b35fa1df2ec383f138c7f89e7e88269b7a42b7cd6b71ac53a
+size 711507117

runs/Sep16_00-21-54_83d5b9720907/1631751762.9967196/events.out.tfevents.1631751762.83d5b9720907.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdd4c32b4152525df8e12bc02f5927ab6360d2b61537b35d3cf155a81cf0516
+size 4225

runs/Sep16_00-21-54_83d5b9720907/events.out.tfevents.1631751762.83d5b9720907.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168f2ade443ba7106dd2221a3498a67d2165d5e4de34be7a12dd73f9d37e13ea
+size 5493

runs/Sep16_00-21-54_83d5b9720907/events.out.tfevents.1631752423.83d5b9720907.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71143a89ee5f76e0ded7c0419c0d9eefcd593e7838c4a76983f1b9cfe8871ac5
+size 363

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/0c7965501fba622370adf334149813060bb231408a6582b155bf623cd1f81d47.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/rubert-base-cased-sentence", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e1f04498360a66cee2b21a13df66468c035ab8ef6f4357fefe1fa59acb7d6c
+size 2671