Training in progress, epoch 1

config.json

@@ -0,0 +1,57 @@
+{
+  "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": "\u041e\u0431\u043c\u0435\u043d\u043d\u0438\u043a \u0432\u0430\u043b\u044e\u0442\u044b",
+    "1": "\u041f\u0440\u043e\u0434\u0430\u0436\u0430 \u043a\u0443\u0440\u0441\u043e\u0432",
+    "2": "\u0411\u043b\u0430\u0433\u043e\u0442\u0432\u043e\u0440\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0439 \u0441\u0431\u043e\u0440",
+    "3": "\u041c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u043e (\u0444\u0435\u0439\u043a\u043e\u0432\u044b\u0439 \u0440\u043e\u0437\u044b\u0433\u0440\u044b\u0448)",
+    "4": "\u041e\u0431\u043c\u0435\u043d \u043a\u0440\u0438\u043f\u0442\u043e\u0432\u0430\u043b\u044e\u0442\u044b",
+    "5": "\u0420\u0435\u043a\u043b\u0430\u043c\u0430 \u0444\u0438\u043d\u0430\u043d\u0441\u043e\u0432\u044b\u0445 \u0443\u0441\u043b\u0443\u0433",
+    "6": "\u0418\u043d\u0432\u0435\u0441\u0442\u0438\u0446\u0438\u043e\u043d\u043d\u044b\u0439 \u043f\u0443\u043b",
+    "7": "\u0424\u0435\u0439\u043a\u043e\u0432\u044b\u0439 \u0438\u043d\u0432\u0435\u0441\u0442\u0438\u0446\u0438\u043e\u043d\u043d\u044b\u0439 \u0444\u043e\u043d\u0434",
+    "8": "\u0410\u0440\u0435\u043d\u0434\u0430 \u043d\u0435\u0434\u0432\u0438\u0436\u0438\u043c\u043e\u0441\u0442\u0438",
+    "9": "\u041f\u0440\u043e\u0434\u0430\u0436\u0430 \u0442\u043e\u0432\u0430\u0440\u043e\u0432",
+    "10": "\u041a\u0440\u0430\u0443\u0434\u0444\u0430\u043d\u0434\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0442\u0430\u0440\u0442\u0430\u043f\u0430",
+    "11": "\u041e\u0442\u0437\u044b\u0432 \u043e \u0431\u0430\u043d\u043a\u0435",
+    "12": "\u041c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u043e (\u043f\u043e\u0434\u0434\u0435\u043b\u044c\u043d\u044b\u0439 \u0431\u0430\u043d\u043a)"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "\u0410\u0440\u0435\u043d\u0434\u0430 \u043d\u0435\u0434\u0432\u0438\u0436\u0438\u043c\u043e\u0441\u0442\u0438": 8,
+    "\u0411\u043b\u0430\u0433\u043e\u0442\u0432\u043e\u0440\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0439 \u0441\u0431\u043e\u0440": 2,
+    "\u0418\u043d\u0432\u0435\u0441\u0442\u0438\u0446\u0438\u043e\u043d\u043d\u044b\u0439 \u043f\u0443\u043b": 6,
+    "\u041a\u0440\u0430\u0443\u0434\u0444\u0430\u043d\u0434\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0442\u0430\u0440\u0442\u0430\u043f\u0430": 10,
+    "\u041c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u043e (\u043f\u043e\u0434\u0434\u0435\u043b\u044c\u043d\u044b\u0439 \u0431\u0430\u043d\u043a)": 12,
+    "\u041c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u043e (\u0444\u0435\u0439\u043a\u043e\u0432\u044b\u0439 \u0440\u043e\u0437\u044b\u0433\u0440\u044b\u0448)": 3,
+    "\u041e\u0431\u043c\u0435\u043d \u043a\u0440\u0438\u043f\u0442\u043e\u0432\u0430\u043b\u044e\u0442\u044b": 4,
+    "\u041e\u0431\u043c\u0435\u043d\u043d\u0438\u043a \u0432\u0430\u043b\u044e\u0442\u044b": 0,
+    "\u041e\u0442\u0437\u044b\u0432 \u043e \u0431\u0430\u043d\u043a\u0435": 11,
+    "\u041f\u0440\u043e\u0434\u0430\u0436\u0430 \u043a\u0443\u0440\u0441\u043e\u0432": 1,
+    "\u041f\u0440\u043e\u0434\u0430\u0436\u0430 \u0442\u043e\u0432\u0430\u0440\u043e\u0432": 9,
+    "\u0420\u0435\u043a\u043b\u0430\u043c\u0430 \u0444\u0438\u043d\u0430\u043d\u0441\u043e\u0432\u044b\u0445 \u0443\u0441\u043b\u0443\u0433": 5,
+    "\u0424\u0435\u0439\u043a\u043e\u0432\u044b\u0439 \u0438\u043d\u0432\u0435\u0441\u0442\u0438\u0446\u0438\u043e\u043d\u043d\u044b\u0439 \u0444\u043e\u043d\u0434": 7
+  },
+  "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": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ddfe4633a0a95546143d6ad88e1277ef1bdcd055b2f4b32f133817471f6ae4
+size 116797908

runs/May06_17-29-04_cd792dee2ff7/events.out.tfevents.1746552545.cd792dee2ff7.518.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7d802aa10297b9f8f75d00b68b9fc66f032c2fb3d71402ada7a5c8a3e76d7b
+size 8429

runs/May06_17-30-17_cd792dee2ff7/events.out.tfevents.1746552617.cd792dee2ff7.518.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055d6be3f4b076579d4bbade0efd4cb403b2c290d765e62e4ce972f410e549a3
+size 8746

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90aabea84e8d413d34ea8c8751f15c196be0d20bb3758a915483c073d74e7049
+size 5304