Training in progress, epoch 1

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "\u0411\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c,",
+    "1": "\u0411\u043b\u0430\u0433\u043e\u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u043e,",
+    "10": "\u042d\u043a\u043e\u043b\u043e\u0433\u0438\u044f,",
+    "11": "\u042d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0430",
+    "2": "\u0414\u043e\u0440\u043e\u0433\u0438,",
+    "3": "\u0416\u041a\u0425,",
+    "4": "\u0417\u0434\u0440\u0430\u0432\u043e\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0435,",
+    "5": "\u041e\u0431\u0440\u0430\u0437\u043e\u0432\u0430\u043d\u0438\u0435,",
+    "6": "\u0421\u043e\u0446\u0417\u0430\u0449\u0438\u0442\u0430,",
+    "7": "\u0421\u0442\u0440\u043e\u0438\u0442\u0435\u043b\u044c\u0441\u0442\u0432\u043e,",
+    "8": "\u041e\u0442\u0445\u043e\u0434\u044b,",
+    "9": "\u0422\u0440\u0430\u043d\u0441\u043f\u043e\u0440\u0442,"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "\u0411\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c,": "0",
+    "\u0411\u043b\u0430\u0433\u043e\u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u043e,": "1",
+    "\u0414\u043e\u0440\u043e\u0433\u0438,": "2",
+    "\u0416\u041a\u0425,": "3",
+    "\u0417\u0434\u0440\u0430\u0432\u043e\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0435,": "4",
+    "\u041e\u0431\u0440\u0430\u0437\u043e\u0432\u0430\u043d\u0438\u0435,": "5",
+    "\u041e\u0442\u0445\u043e\u0434\u044b,": "8",
+    "\u0421\u043e\u0446\u0417\u0430\u0449\u0438\u0442\u0430,": "6",
+    "\u0421\u0442\u0440\u043e\u0438\u0442\u0435\u043b\u044c\u0441\u0442\u0432\u043e,": "7",
+    "\u0422\u0440\u0430\u043d\u0441\u043f\u043e\u0440\u0442,": "9",
+    "\u042d\u043a\u043e\u043b\u043e\u0433\u0438\u044f,": "10",
+    "\u042d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0430": "11"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

logs/events.out.tfevents.1737654874.DESKTOP-ER3Q3E9.11248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ee2915624228ddabd6001f67cefb16bbf9705c97d9877ba446fd2bc93c0fe8
+size 9550

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0990470edd9d1c65c5784f1a63ccbcf587c4780beb74599f153f82c55a227341
+size 116796656

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fac6d5a2ce135d69434968a9f809c5d7c595e91373c886171e0bf300aeeef1
+size 5432