Training in progress, epoch 1

config.json

@@ -1,41 +1,34 @@
 {
-  "_name_or_path": "DeepPavlov/rubert-base-cased",
+  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 1
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ba12e6b2c499d4220e26afba60185c6d8e857838aba861b6e038ada3e7ff34
-size 711443456
+oid sha256:c68432d325a323a57c82f8cef903a6a8ede4c0a34107f337b8b8e4c30129ac8f
+size 541317368

tokenizer_config.json

@@ -43,17 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "max_length": 512,
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "max_length": 256,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "truncation": true,
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e975203539f92eec2ce369f989d98239c82960db08b8f8e9e03f8f1c4d0cd557
+oid sha256:3fa8db6b26f62d53725a46372fc5ee9c6fd0ed41906a5f2a8eda1646d3201fda
 size 5176