Training in progress, epoch 5

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "kz-transformers/kaz-roberta-conversational",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u04d8\u043b\u0435\u043c",
+    "1": "\u041c\u04d9\u0434\u0435\u043d\u0438\u0435\u0442",
+    "2": "\u041e\u049b\u0438\u0493\u0430",
+    "3": "\u0421\u043f\u043e\u0440\u0442",
+    "4": "\u0421\u0430\u044f\u0441\u0430\u0442",
+    "5": "\u042d\u043a\u043e\u043d\u043e\u043c\u0438\u043a\u0430"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

logs/events.out.tfevents.1721890273.f8cc7753d97e.233.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b6e3c97aee7c4cdaf511fcf098a5196c8c5c3daa9dad83571cfd776003648c
+size 1088137

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe41de98654e6c7dd87ef59a43e64af8b1803bf787a5ca7810db13931d97c048
+size 333834504

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4770ca57eb45c39b0893324153881bdf3c0c23c1cfd7a5b6b65ca27bca522cd
+size 5176