Model save

README.md

@@ -0,0 +1,71 @@
+---
+base_model: DeepPavlov/xlm-roberta-large-en-ru-mnli
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: books_text_class_roBERTa_ru_base_iliabel
+  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. -->
+
+# books_text_class_roBERTa_ru_base_iliabel
+
+This model is a fine-tuned version of [DeepPavlov/xlm-roberta-large-en-ru-mnli](https://huggingface.co/DeepPavlov/xlm-roberta-large-en-ru-mnli) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2345
+- Accuracy: 0.9723
+- F1-score: 0.9721
+- Mcc: 0.9620
+
+## 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: 1e-05
+- train_batch_size: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1-score | Mcc    |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:------:|
+| 0.4345        | 1.0   | 1516  | 0.3400          | 0.9190   | 0.9035   | 0.8902 |
+| 0.2621        | 2.0   | 3032  | 0.2285          | 0.9563   | 0.9557   | 0.9404 |
+| 0.2166        | 3.0   | 4548  | 0.2311          | 0.9661   | 0.9634   | 0.9536 |
+| 0.1465        | 4.0   | 6064  | 0.2608          | 0.9606   | 0.9591   | 0.9464 |
+| 0.0841        | 5.0   | 7580  | 0.3028          | 0.9581   | 0.9578   | 0.9430 |
+| 0.0736        | 6.0   | 9096  | 0.2167          | 0.9735   | 0.9734   | 0.9638 |
+| 0.0263        | 7.0   | 10612 | 0.2355          | 0.9738   | 0.9735   | 0.9642 |
+| 0.0294        | 8.0   | 12128 | 0.2305          | 0.9711   | 0.9707   | 0.9604 |
+| 0.0079        | 9.0   | 13644 | 0.2317          | 0.9726   | 0.9724   | 0.9625 |
+| 0.0051        | 10.0  | 15160 | 0.2345          | 0.9723   | 0.9721   | 0.9620 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "DeepPavlov/xlm-roberta-large-en-ru-mnli",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 35054
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0e67c9bb81f349edc7862d70ab51d3e108edfb3f84cb0cff5deb8e9972f2d0
+size 1359219820

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35053": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae006174e4d20f96b0c94be28d583d53407a6133409ef93e3b779412cccccfb
+size 4664