Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,58 @@
+{
+  "_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": "\u0416\u041a\u0425",
+    "1": "\u0422\u0440\u0430\u043d\u0441\u043f\u043e\u0440\u0442",
+    "10": "\u042d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0430",
+    "11": "\u041e\u0431\u0440\u0430\u0449\u0435\u043d\u0438\u0435 \u0441 \u043e\u0442\u0445\u043e\u0434\u0430\u043c\u0438",
+    "12": "\u042d\u043a\u043e\u043b\u043e\u0433\u0438\u044f",
+    "2": "\u0411\u043b\u0430\u0433\u043e\u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u043e",
+    "3": "\u0414\u0440\u0443\u0433\u043e\u0435",
+    "4": "\u0414\u043e\u0440\u043e\u0433\u0438",
+    "5": "\u041e\u0431\u0440\u0430\u0437\u043e\u0432\u0430\u043d\u0438\u0435",
+    "6": "\u0411\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c",
+    "7": "\u0417\u0434\u0440\u0430\u0432\u043e\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0435",
+    "8": "\u0421\u043e\u0446\u0438\u0430\u043b\u044c\u043d\u0430\u044f \u0437\u0430\u0449\u0438\u0442\u0430",
+    "9": "\u0421\u0442\u0440\u043e\u0438\u0442\u0435\u043b\u044c\u0441\u0442\u0432\u043e"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "\u0411\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c": "6",
+    "\u0411\u043b\u0430\u0433\u043e\u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u043e": "2",
+    "\u0414\u043e\u0440\u043e\u0433\u0438": "4",
+    "\u0414\u0440\u0443\u0433\u043e\u0435": "3",
+    "\u0416\u041a\u0425": "0",
+    "\u0417\u0434\u0440\u0430\u0432\u043e\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0435": "7",
+    "\u041e\u0431\u0440\u0430\u0437\u043e\u0432\u0430\u043d\u0438\u0435": "5",
+    "\u041e\u0431\u0440\u0430\u0449\u0435\u043d\u0438\u0435 \u0441 \u043e\u0442\u0445\u043e\u0434\u0430\u043c\u0438": "11",
+    "\u0421\u043e\u0446\u0438\u0430\u043b\u044c\u043d\u0430\u044f \u0437\u0430\u0449\u0438\u0442\u0430": "8",
+    "\u0421\u0442\u0440\u043e\u0438\u0442\u0435\u043b\u044c\u0441\u0442\u0432\u043e": "9",
+    "\u0422\u0440\u0430\u043d\u0441\u043f\u043e\u0440\u0442": "1",
+    "\u042d\u043a\u043e\u043b\u043e\u0433\u0438\u044f": "12",
+    "\u042d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0430": "10"
+  },
+  "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": "4.27.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

logs/1688380339.467617/events.out.tfevents.1688380339.SERVER-509.12044.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee205f5f6ae4f2de5836e8f716dd66475c38fbe39787ccb3735a2ec2b85fe733
+size 5827

logs/events.out.tfevents.1688380339.SERVER-509.12044.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023d5bee8eb00db2c9ce97ed8af698a1d690293904f420d6e6c0e7e01ca8b21a
+size 8623

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9176711ee9683020405c00a7285a215328495eda1453ebb9d209c1d25d6d509b
+size 116825951

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160676665998a481154c580cabcd2c300a69674f3d56100803e637ace7964e4c
+size 3643