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: output
+  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. -->
+
+# output
+
+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: 0.3006
+- Accuracy: 0.9677
+- F1-score: 0.9674
+- Mcc: 0.9558
+
+## 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: 4
+- eval_batch_size: 4
+- 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    |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:------:|
+| 0.3994        | 1.0   | 1894  | 0.3931          | 0.8814   | 0.8622   | 0.8397 |
+| 0.2659        | 2.0   | 3788  | 0.2872          | 0.9590   | 0.9560   | 0.9440 |
+| 0.2262        | 3.0   | 5682  | 0.2528          | 0.9600   | 0.9566   | 0.9453 |
+| 0.1514        | 4.0   | 7576  | 0.2465          | 0.9569   | 0.9567   | 0.9413 |
+| 0.1319        | 5.0   | 9470  | 0.2808          | 0.9621   | 0.9617   | 0.9482 |
+| 0.0649        | 6.0   | 11364 | 0.2656          | 0.9661   | 0.9656   | 0.9536 |
+| 0.0513        | 7.0   | 13258 | 0.2716          | 0.9664   | 0.9662   | 0.9541 |
+| 0.0159        | 8.0   | 15152 | 0.2948          | 0.9667   | 0.9665   | 0.9545 |
+| 0.0121        | 9.0   | 17046 | 0.2972          | 0.9664   | 0.9662   | 0.9541 |
+| 0.009         | 10.0  | 18940 | 0.3006          | 0.9677   | 0.9674   | 0.9558 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,56 @@
+{
+  "_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",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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-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 sha256:4990a35b4c27cb32a45aad01a352f42bca9a08e3b563ed2f4199671355b42a98
+size 1359228020

runs/Dec17_19-52-36_12f0ce24703b/events.out.tfevents.1702842813.12f0ce24703b.264.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29957a90e8e7f84867108cb498a1499f7166684c071ad8c176dd580b09677e6d
+size 5357

runs/Dec17_20-12-04_12f0ce24703b/events.out.tfevents.1702843928.12f0ce24703b.264.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c47a0a74dd251245f666da768643afab04bc7d2517b35fdf4846282c3962c0
+size 88

runs/Dec17_20-12-20_12f0ce24703b/events.out.tfevents.1702843947.12f0ce24703b.264.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d3f895b3a308c34310d9516c830d39ffdf493d8a3a2204c06fd4f11dd2dc8f
+size 88

runs/Dec17_20-17-22_2774340f9fb3/events.out.tfevents.1702844253.2774340f9fb3.157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bf1bee74959ed668ca54e9e9e50023a44a5a44ba1b258f369c902b239376f9
+size 4888

runs/Dec17_20-17-57_2774340f9fb3/events.out.tfevents.1702844282.2774340f9fb3.157.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c155810f10b9ec3cba10c32edea42db3947903c68279822236a18af8e8296841
+size 4886

runs/Dec17_20-18-16_2774340f9fb3/events.out.tfevents.1702844301.2774340f9fb3.157.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b11f460683e40d680d8900251633635d82f4a5cdea1166cce728526684bdc5f
+size 5200

runs/Dec17_20-24-25_2774340f9fb3/events.out.tfevents.1702844670.2774340f9fb3.157.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad31c1f0837afd5f52ee24d753b6ddec363dddd85b8276c90511fce7c186454
+size 15355

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 sha256:7c0226ecdbd03af1c4b3332b6e30a18de66dbb7d1ab9390a5e73763c9c433eef
+size 4664